Skip to content

Instantly share code, notes, and snippets.

@NobuoTsukamoto

NobuoTsukamoto/ssdlite-mobilenet-v3-quantization-aware-training.ipynb Secret

Created March 26, 2020 13:10
Show Gist options
  • Save NobuoTsukamoto/b2ca173b62e933ceeb1c7f0df42bca5f to your computer and use it in GitHub Desktop.
Save NobuoTsukamoto/b2ca173b62e933ceeb1c7f0df42bca5f to your computer and use it in GitHub Desktop.
Download ZIP
SSDLite Mobilenet V3 quantization-aware training
Display the source blob
Display the rendered blob
Raw
ssdlite-mobilenet-v3-quantization-aware-training.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "SSDLite Mobilenet V3 quantization-aware training ",
"provenance": [],
"collapsed_sections": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/NobuoTsukamoto/b2ca173b62e933ceeb1c7f0df42bca5f/ssdlite-mobilenet-v3-quantization-aware-training.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "t67NpfjyBTnF",
"colab_type": "text"
},
"source": [
"# Install TensorFlow 1.x\n",
"Note: \"%tensorflow_version 1.x\" "
]
},
{
"cell_type": "code",
"metadata": {
"id": "45JZXAHmjdnf",
"colab_type": "code",
"colab": {}
},
"source": [
"%tensorflow_version 1.x"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "CnhOFVQTzoWD",
"colab_type": "code",
"outputId": "ac2d3dc5-a734-434e-ec9c-c6a2f84fe93e",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 306
}
},
"source": [
"!nvidia-smi"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"text": [
"Thu Mar 26 12:49:47 2020 \n",
"+-----------------------------------------------------------------------------+\n",
"| NVIDIA-SMI 440.64.00 Driver Version: 418.67 CUDA Version: 10.1 |\n",
"|-------------------------------+----------------------+----------------------+\n",
"| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\n",
"| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\n",
"|===============================+======================+======================|\n",
"| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |\n",
"| N/A 58C P8 10W / 70W | 0MiB / 15079MiB | 0% Default |\n",
"+-------------------------------+----------------------+----------------------+\n",
" \n",
"+-----------------------------------------------------------------------------+\n",
"| Processes: GPU Memory |\n",
"| GPU PID Type Process name Usage |\n",
"|=============================================================================|\n",
"| No running processes found |\n",
"+-----------------------------------------------------------------------------+\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "NDyZERnY4tez",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
},
"outputId": "7ed2391d-c194-41d1-eefb-55fba051499c"
},
"source": [
"!python3 --version"
],
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"text": [
"Python 3.6.9\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "y_owSZjMHN4-",
"colab_type": "text"
},
"source": [
"# Install models/research/object_detection"
]
},
{
"cell_type": "code",
"metadata": {
"id": "1ksaO1UDE6EF",
"colab_type": "code",
"outputId": "9b3cd8dd-69d5-40bc-9fe4-d20e4e0bdea8",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
},
"source": [
"!apt install --quiet protobuf-compiler python3-pil python3-lxml python3-tk\n",
"!pip install --quiet Cython\n",
"!pip install --quiet jupyter\n",
"!pip install --quiet matplotlib"
],
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"text": [
"Reading package lists...\n",
"Building dependency tree...\n",
"Reading state information...\n",
"protobuf-compiler is already the newest version (3.0.0-9.1ubuntu1).\n",
"python3-tk is already the newest version (3.6.9-1~18.04).\n",
"The following additional packages will be installed:\n",
" python3-bs4 python3-chardet python3-html5lib python3-olefile\n",
" python3-pkg-resources python3-six python3-webencodings\n",
"Suggested packages:\n",
" python3-genshi python3-lxml-dbg python-lxml-doc python-pil-doc\n",
" python3-pil-dbg python3-setuptools\n",
"The following NEW packages will be installed:\n",
" python3-bs4 python3-chardet python3-html5lib python3-lxml python3-olefile\n",
" python3-pil python3-pkg-resources python3-six python3-webencodings\n",
"0 upgraded, 9 newly installed, 0 to remove and 25 not upgraded.\n",
"Need to get 1,804 kB of archives.\n",
"After this operation, 7,686 kB of additional disk space will be used.\n",
"Get:1 http://archive.ubuntu.com/ubuntu bionic/main amd64 python3-bs4 all 4.6.0-1 [67.8 kB]\n",
"Get:2 http://archive.ubuntu.com/ubuntu bionic/main amd64 python3-pkg-resources all 39.0.1-2 [98.8 kB]\n",
"Get:3 http://archive.ubuntu.com/ubuntu bionic/main amd64 python3-chardet all 3.0.4-1 [80.3 kB]\n",
"Get:4 http://archive.ubuntu.com/ubuntu bionic/main amd64 python3-six all 1.11.0-2 [11.4 kB]\n",
"Get:5 http://archive.ubuntu.com/ubuntu bionic/main amd64 python3-webencodings all 0.5-2 [10.4 kB]\n",
"Get:6 http://archive.ubuntu.com/ubuntu bionic/main amd64 python3-html5lib all 0.999999999-1 [81.9 kB]\n",
"Get:7 http://archive.ubuntu.com/ubuntu bionic-updates/main amd64 python3-lxml amd64 4.2.1-1ubuntu0.1 [1,091 kB]\n",
"Get:8 http://archive.ubuntu.com/ubuntu bionic/main amd64 python3-olefile all 0.45.1-1 [33.3 kB]\n",
"Get:9 http://archive.ubuntu.com/ubuntu bionic-updates/main amd64 python3-pil amd64 5.1.0-1ubuntu0.2 [329 kB]\n",
"Fetched 1,804 kB in 0s (12.9 MB/s)\n",
"Selecting previously unselected package python3-bs4.\n",
"(Reading database ... 144542 files and directories currently installed.)\n",
"Preparing to unpack .../0-python3-bs4_4.6.0-1_all.deb ...\n",
"Unpacking python3-bs4 (4.6.0-1) ...\n",
"Selecting previously unselected package python3-pkg-resources.\n",
"Preparing to unpack .../1-python3-pkg-resources_39.0.1-2_all.deb ...\n",
"Unpacking python3-pkg-resources (39.0.1-2) ...\n",
"Selecting previously unselected package python3-chardet.\n",
"Preparing to unpack .../2-python3-chardet_3.0.4-1_all.deb ...\n",
"Unpacking python3-chardet (3.0.4-1) ...\n",
"Selecting previously unselected package python3-six.\n",
"Preparing to unpack .../3-python3-six_1.11.0-2_all.deb ...\n",
"Unpacking python3-six (1.11.0-2) ...\n",
"Selecting previously unselected package python3-webencodings.\n",
"Preparing to unpack .../4-python3-webencodings_0.5-2_all.deb ...\n",
"Unpacking python3-webencodings (0.5-2) ...\n",
"Selecting previously unselected package python3-html5lib.\n",
"Preparing to unpack .../5-python3-html5lib_0.999999999-1_all.deb ...\n",
"Unpacking python3-html5lib (0.999999999-1) ...\n",
"Selecting previously unselected package python3-lxml:amd64.\n",
"Preparing to unpack .../6-python3-lxml_4.2.1-1ubuntu0.1_amd64.deb ...\n",
"Unpacking python3-lxml:amd64 (4.2.1-1ubuntu0.1) ...\n",
"Selecting previously unselected package python3-olefile.\n",
"Preparing to unpack .../7-python3-olefile_0.45.1-1_all.deb ...\n",
"Unpacking python3-olefile (0.45.1-1) ...\n",
"Selecting previously unselected package python3-pil:amd64.\n",
"Preparing to unpack .../8-python3-pil_5.1.0-1ubuntu0.2_amd64.deb ...\n",
"Unpacking python3-pil:amd64 (5.1.0-1ubuntu0.2) ...\n",
"Setting up python3-pil:amd64 (5.1.0-1ubuntu0.2) ...\n",
"Setting up python3-webencodings (0.5-2) ...\n",
"Setting up python3-lxml:amd64 (4.2.1-1ubuntu0.1) ...\n",
"Setting up python3-olefile (0.45.1-1) ...\n",
"Setting up python3-six (1.11.0-2) ...\n",
"Setting up python3-pkg-resources (39.0.1-2) ...\n",
"Setting up python3-bs4 (4.6.0-1) ...\n",
"Setting up python3-chardet (3.0.4-1) ...\n",
"Setting up python3-html5lib (0.999999999-1) ...\n",
"Processing triggers for man-db (2.8.3-2ubuntu0.1) ...\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "aOmhjOddFpRL",
"colab_type": "code",
"outputId": "fc111ac6-703c-47f8-829b-1c70b3102906",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 119
}
},
"source": [
"!git clone https://github.com/tensorflow/models.git"
],
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"text": [
"Cloning into 'models'...\n",
"remote: Enumerating objects: 33037, done.\u001b[K\n",
"remote: Total 33037 (delta 0), reused 0 (delta 0), pack-reused 33037\u001b[K\n",
"Receiving objects: 100% (33037/33037), 511.88 MiB | 38.41 MiB/s, done.\n",
"Resolving deltas: 100% (21181/21181), done.\n",
"Checking out files: 100% (2464/2464), done.\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "3bcc58oQF43i",
"colab_type": "code",
"outputId": "490eac51-ae8f-4d98-965f-73f71fe9db19",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
},
"source": [
"!git clone https://github.com/cocodataset/cocoapi.git\n",
"!cd cocoapi/PythonAPI; make; cp -r pycocotools /content/models/research/"
],
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"text": [
"Cloning into 'cocoapi'...\n",
"remote: Enumerating objects: 975, done.\u001b[K\n",
"remote: Total 975 (delta 0), reused 0 (delta 0), pack-reused 975\u001b[K\n",
"Receiving objects: 100% (975/975), 11.72 MiB | 12.70 MiB/s, done.\n",
"Resolving deltas: 100% (576/576), done.\n",
"python setup.py build_ext --inplace\n",
"running build_ext\n",
"cythoning pycocotools/_mask.pyx to pycocotools/_mask.c\n",
"/usr/local/lib/python3.6/dist-packages/Cython/Compiler/Main.py:369: FutureWarning: Cython directive 'language_level' not set, using 2 for now (Py2). This will change in a later release! File: /content/cocoapi/PythonAPI/pycocotools/_mask.pyx\n",
" tree = Parsing.p_module(s, pxd, full_module_name)\n",
"building 'pycocotools._mask' extension\n",
"creating build\n",
"creating build/common\n",
"creating build/temp.linux-x86_64-3.6\n",
"creating build/temp.linux-x86_64-3.6/pycocotools\n",
"x86_64-linux-gnu-gcc -pthread -DNDEBUG -g -fwrapv -O2 -Wall -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.6/dist-packages/numpy/core/include -I../common -I/usr/include/python3.6m -c ../common/maskApi.c -o build/temp.linux-x86_64-3.6/../common/maskApi.o -Wno-cpp -Wno-unused-function -std=c99\n",
"\u001b[01m\u001b[K../common/maskApi.c:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[KrleDecode\u001b[m\u001b[K’:\n",
"\u001b[01m\u001b[K../common/maskApi.c:46:7:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kthis ‘\u001b[01m\u001b[Kfor\u001b[m\u001b[K’ clause does not guard... [\u001b[01;35m\u001b[K-Wmisleading-indentation\u001b[m\u001b[K]\n",
" \u001b[01;35m\u001b[Kfor\u001b[m\u001b[K( k=0; k<R[i].cnts[j]; k++ ) *(M++)=v; v=!v; }}\n",
" \u001b[01;35m\u001b[K^~~\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:46:49:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[K...this statement, but the latter is misleadingly indented as if it were guarded by the ‘\u001b[01m\u001b[Kfor\u001b[m\u001b[K’\n",
" for( k=0; k<R[i].cnts[j]; k++ ) *(M++)=v; \u001b[01;36m\u001b[Kv\u001b[m\u001b[K=!v; }}\n",
" \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[KrleFrPoly\u001b[m\u001b[K’:\n",
"\u001b[01m\u001b[K../common/maskApi.c:166:3:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kthis ‘\u001b[01m\u001b[Kfor\u001b[m\u001b[K’ clause does not guard... [\u001b[01;35m\u001b[K-Wmisleading-indentation\u001b[m\u001b[K]\n",
" \u001b[01;35m\u001b[Kfor\u001b[m\u001b[K(j=0; j<k; j++) x[j]=(int)(scale*xy[j*2+0]+.5); x[k]=x[0];\n",
" \u001b[01;35m\u001b[K^~~\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:166:54:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[K...this statement, but the latter is misleadingly indented as if it were guarded by the ‘\u001b[01m\u001b[Kfor\u001b[m\u001b[K’\n",
" for(j=0; j<k; j++) x[j]=(int)(scale*xy[j*2+0]+.5); \u001b[01;36m\u001b[Kx\u001b[m\u001b[K[k]=x[0];\n",
" \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:167:3:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kthis ‘\u001b[01m\u001b[Kfor\u001b[m\u001b[K’ clause does not guard... [\u001b[01;35m\u001b[K-Wmisleading-indentation\u001b[m\u001b[K]\n",
" \u001b[01;35m\u001b[Kfor\u001b[m\u001b[K(j=0; j<k; j++) y[j]=(int)(scale*xy[j*2+1]+.5); y[k]=y[0];\n",
" \u001b[01;35m\u001b[K^~~\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:167:54:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[K...this statement, but the latter is misleadingly indented as if it were guarded by the ‘\u001b[01m\u001b[Kfor\u001b[m\u001b[K’\n",
" for(j=0; j<k; j++) y[j]=(int)(scale*xy[j*2+1]+.5); \u001b[01;36m\u001b[Ky\u001b[m\u001b[K[k]=y[0];\n",
" \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[KrleToString\u001b[m\u001b[K’:\n",
"\u001b[01m\u001b[K../common/maskApi.c:212:7:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kthis ‘\u001b[01m\u001b[Kif\u001b[m\u001b[K’ clause does not guard... [\u001b[01;35m\u001b[K-Wmisleading-indentation\u001b[m\u001b[K]\n",
" \u001b[01;35m\u001b[Kif\u001b[m\u001b[K(more) c |= 0x20; c+=48; s[p++]=c;\n",
" \u001b[01;35m\u001b[K^~\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:212:27:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[K...this statement, but the latter is misleadingly indented as if it were guarded by the ‘\u001b[01m\u001b[Kif\u001b[m\u001b[K’\n",
" if(more) c |= 0x20; \u001b[01;36m\u001b[Kc\u001b[m\u001b[K+=48; s[p++]=c;\n",
" \u001b[01;36m\u001b[K^\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[KrleFrString\u001b[m\u001b[K’:\n",
"\u001b[01m\u001b[K../common/maskApi.c:220:3:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kthis ‘\u001b[01m\u001b[Kwhile\u001b[m\u001b[K’ clause does not guard... [\u001b[01;35m\u001b[K-Wmisleading-indentation\u001b[m\u001b[K]\n",
" \u001b[01;35m\u001b[Kwhile\u001b[m\u001b[K( s[m] ) m++; cnts=malloc(sizeof(uint)*m); m=0;\n",
" \u001b[01;35m\u001b[K^~~~~\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:220:22:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[K...this statement, but the latter is misleadingly indented as if it were guarded by the ‘\u001b[01m\u001b[Kwhile\u001b[m\u001b[K’\n",
" while( s[m] ) m++; \u001b[01;36m\u001b[Kcnts\u001b[m\u001b[K=malloc(sizeof(uint)*m); m=0;\n",
" \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:228:5:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[Kthis ‘\u001b[01m\u001b[Kif\u001b[m\u001b[K’ clause does not guard... [\u001b[01;35m\u001b[K-Wmisleading-indentation\u001b[m\u001b[K]\n",
" \u001b[01;35m\u001b[Kif\u001b[m\u001b[K(m>2) x+=(long) cnts[m-2]; cnts[m++]=(uint) x;\n",
" \u001b[01;35m\u001b[K^~\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:228:34:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[K...this statement, but the latter is misleadingly indented as if it were guarded by the ‘\u001b[01m\u001b[Kif\u001b[m\u001b[K’\n",
" if(m>2) x+=(long) cnts[m-2]; \u001b[01;36m\u001b[Kcnts\u001b[m\u001b[K[m++]=(uint) x;\n",
" \u001b[01;36m\u001b[K^~~~\u001b[m\u001b[K\n",
"\u001b[01m\u001b[K../common/maskApi.c:\u001b[m\u001b[K In function ‘\u001b[01m\u001b[KrleToBbox\u001b[m\u001b[K’:\n",
"\u001b[01m\u001b[K../common/maskApi.c:141:31:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kxp\u001b[m\u001b[K’ may be used uninitialized in this function [\u001b[01;35m\u001b[K-Wmaybe-uninitialized\u001b[m\u001b[K]\n",
" if(j%2==0) xp=x; else if\u001b[01;35m\u001b[K(\u001b[m\u001b[Kxp<x) { ys=0; ye=h-1; }\n",
" \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
"x86_64-linux-gnu-gcc -pthread -DNDEBUG -g -fwrapv -O2 -Wall -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -I/usr/local/lib/python3.6/dist-packages/numpy/core/include -I../common -I/usr/include/python3.6m -c pycocotools/_mask.c -o build/temp.linux-x86_64-3.6/pycocotools/_mask.o -Wno-cpp -Wno-unused-function -std=c99\n",
"creating build/lib.linux-x86_64-3.6\n",
"creating build/lib.linux-x86_64-3.6/pycocotools\n",
"x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.6/../common/maskApi.o build/temp.linux-x86_64-3.6/pycocotools/_mask.o -o build/lib.linux-x86_64-3.6/pycocotools/_mask.cpython-36m-x86_64-linux-gnu.so\n",
"copying build/lib.linux-x86_64-3.6/pycocotools/_mask.cpython-36m-x86_64-linux-gnu.so -> pycocotools\n",
"rm -rf build\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "4F3kd4rEGIgo",
"colab_type": "code",
"outputId": "04b0a6e4-675b-4dc2-8ed0-4ba2064df422",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"%cd /content/models/research"
],
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"text": [
"/content/models/research\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "XRfEVbHijRiq",
"colab_type": "code",
"colab": {}
},
"source": [
"import os\n",
"os.environ['PYTHONPATH'] = '/content/models/research:/content/models/research/slim:' + os.environ['PYTHONPATH']"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "YP6phSrlka9x",
"colab_type": "code",
"outputId": "c96008a5-bec7-4d8c-dbd0-9edab2007d8d",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"!echo $PYTHONPATH"
],
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"text": [
"/content/models/research:/content/models/research/slim:/tensorflow-1.15.0/python3.6:/env/python\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "O1BJHshKHBYE",
"colab_type": "code",
"colab": {}
},
"source": [
"!protoc object_detection/protos/*.proto --python_out=."
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "Y_uBeLzBHHVH",
"colab_type": "code",
"outputId": "d8259adf-4f39-4f03-c820-1f4d09a23dfb",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 816
}
},
"source": [
"!python object_detection/builders/model_builder_test.py"
],
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"text": [
"WARNING:tensorflow:\n",
"The TensorFlow contrib module will not be included in TensorFlow 2.0.\n",
"For more information, please see:\n",
" * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md\n",
" * https://github.com/tensorflow/addons\n",
" * https://github.com/tensorflow/io (for I/O related ops)\n",
"If you depend on functionality not listed there, please file an issue.\n",
"\n",
"Running tests under Python 3.6.9: /usr/bin/python3\n",
"[ RUN ] ModelBuilderTest.test_create_experimental_model\n",
"[ OK ] ModelBuilderTest.test_create_experimental_model\n",
"[ RUN ] ModelBuilderTest.test_create_faster_rcnn_model_from_config_with_example_miner\n",
"[ OK ] ModelBuilderTest.test_create_faster_rcnn_model_from_config_with_example_miner\n",
"[ RUN ] ModelBuilderTest.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul\n",
"[ OK ] ModelBuilderTest.test_create_faster_rcnn_models_from_config_faster_rcnn_with_matmul\n",
"[ RUN ] ModelBuilderTest.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul\n",
"[ OK ] ModelBuilderTest.test_create_faster_rcnn_models_from_config_faster_rcnn_without_matmul\n",
"[ RUN ] ModelBuilderTest.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul\n",
"[ OK ] ModelBuilderTest.test_create_faster_rcnn_models_from_config_mask_rcnn_with_matmul\n",
"[ RUN ] ModelBuilderTest.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul\n",
"[ OK ] ModelBuilderTest.test_create_faster_rcnn_models_from_config_mask_rcnn_without_matmul\n",
"[ RUN ] ModelBuilderTest.test_create_rfcn_model_from_config\n",
"[ OK ] ModelBuilderTest.test_create_rfcn_model_from_config\n",
"[ RUN ] ModelBuilderTest.test_create_ssd_fpn_model_from_config\n",
"[ OK ] ModelBuilderTest.test_create_ssd_fpn_model_from_config\n",
"[ RUN ] ModelBuilderTest.test_create_ssd_models_from_config\n",
"[ OK ] ModelBuilderTest.test_create_ssd_models_from_config\n",
"[ RUN ] ModelBuilderTest.test_invalid_faster_rcnn_batchnorm_update\n",
"[ OK ] ModelBuilderTest.test_invalid_faster_rcnn_batchnorm_update\n",
"[ RUN ] ModelBuilderTest.test_invalid_first_stage_nms_iou_threshold\n",
"[ OK ] ModelBuilderTest.test_invalid_first_stage_nms_iou_threshold\n",
"[ RUN ] ModelBuilderTest.test_invalid_model_config_proto\n",
"[ OK ] ModelBuilderTest.test_invalid_model_config_proto\n",
"[ RUN ] ModelBuilderTest.test_invalid_second_stage_batch_size\n",
"[ OK ] ModelBuilderTest.test_invalid_second_stage_batch_size\n",
"[ RUN ] ModelBuilderTest.test_session\n",
"[ SKIPPED ] ModelBuilderTest.test_session\n",
"[ RUN ] ModelBuilderTest.test_unknown_faster_rcnn_feature_extractor\n",
"[ OK ] ModelBuilderTest.test_unknown_faster_rcnn_feature_extractor\n",
"[ RUN ] ModelBuilderTest.test_unknown_meta_architecture\n",
"[ OK ] ModelBuilderTest.test_unknown_meta_architecture\n",
"[ RUN ] ModelBuilderTest.test_unknown_ssd_feature_extractor\n",
"[ OK ] ModelBuilderTest.test_unknown_ssd_feature_extractor\n",
"----------------------------------------------------------------------\n",
"Ran 17 tests in 0.172s\n",
"\n",
"OK (skipped=1)\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iKdLuAihHhFA",
"colab_type": "text"
},
"source": [
"# Download Pet dataset and create tf-record"
]
},
{
"cell_type": "code",
"metadata": {
"id": "rZG8f4LsnpNl",
"colab_type": "code",
"outputId": "666a594d-b73c-4b1d-9ccd-f9635af48341",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"%set_env DATA_DIR=/content/data\n",
"%set_env TF_RECORD_DIR=/content/data/tf_record"
],
"execution_count": 13,
"outputs": [
{
"output_type": "stream",
"text": [
"env: DATA_DIR=/content/data\n",
"env: TF_RECORD_DIR=/content/data/tf_record\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "8ANpO7QmHjbo",
"colab_type": "code",
"outputId": "51ed772f-bc0d-4320-9d5c-c2d85e735cfd",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 391
}
},
"source": [
"!mkdir ${DATA_DIR}\n",
"!mkdir ${TF_RECORD_DIR}\n",
"!wget http://www.robots.ox.ac.uk/~vgg/data/pets/data/images.tar.gz -P ${DATA_DIR}\n",
"!wget http://www.robots.ox.ac.uk/~vgg/data/pets/data/annotations.tar.gz -P ${DATA_DIR}"
],
"execution_count": 14,
"outputs": [
{
"output_type": "stream",
"text": [
"--2020-03-26 12:51:20-- http://www.robots.ox.ac.uk/~vgg/data/pets/data/images.tar.gz\n",
"Resolving www.robots.ox.ac.uk (www.robots.ox.ac.uk)... 129.67.94.2\n",
"Connecting to www.robots.ox.ac.uk (www.robots.ox.ac.uk)|129.67.94.2|:80... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 791918971 (755M) [application/x-gzip]\n",
"Saving to: ‘/content/data/images.tar.gz’\n",
"\n",
"images.tar.gz 100%[===================>] 755.23M 76.3MB/s in 10s \n",
"\n",
"2020-03-26 12:51:30 (74.3 MB/s) - ‘/content/data/images.tar.gz’ saved [791918971/791918971]\n",
"\n",
"--2020-03-26 12:51:32-- http://www.robots.ox.ac.uk/~vgg/data/pets/data/annotations.tar.gz\n",
"Resolving www.robots.ox.ac.uk (www.robots.ox.ac.uk)... 129.67.94.2\n",
"Connecting to www.robots.ox.ac.uk (www.robots.ox.ac.uk)|129.67.94.2|:80... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 19173078 (18M) [application/x-gzip]\n",
"Saving to: ‘/content/data/annotations.tar.gz’\n",
"\n",
"annotations.tar.gz 100%[===================>] 18.28M 60.4MB/s in 0.3s \n",
"\n",
"2020-03-26 12:51:32 (60.4 MB/s) - ‘/content/data/annotations.tar.gz’ saved [19173078/19173078]\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "wuzR596y1sAH",
"colab_type": "code",
"colab": {}
},
"source": [
"!tar xf ${DATA_DIR}/images.tar.gz -C ${DATA_DIR}\n",
"!tar xf ${DATA_DIR}/annotations.tar.gz -C ${DATA_DIR}"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "hn8UN-aC4aN7",
"colab_type": "code",
"outputId": "3afe1f03-d45c-4dbf-e902-8ad3c259f550",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
},
"source": [
"!python object_detection/dataset_tools/create_pet_tf_record.py \\\n",
" --label_map_path=./object_detection/data/pet_label_map.pbtxt \\\n",
" --data_dir=\"${DATA_DIR}\" \\\n",
" --output_dir=\"${TF_RECORD_DIR}\""
],
"execution_count": 16,
"outputs": [
{
"output_type": "stream",
"text": [
"WARNING:tensorflow:From object_detection/dataset_tools/create_pet_tf_record.py:318: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/utils/label_map_util.py:138: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.\n",
"\n",
"W0326 12:51:46.843916 140573736023936 module_wrapper.py:139] From /content/models/research/object_detection/utils/label_map_util.py:138: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.\n",
"\n",
"I0326 12:51:46.846961 140573736023936 create_pet_tf_record.py:273] Reading from Pet dataset.\n",
"I0326 12:51:46.857559 140573736023936 create_pet_tf_record.py:288] 2576 training and 1104 validation examples.\n",
"WARNING:tensorflow:From /content/models/research/object_detection/dataset_tools/tf_record_creation_util.py:43: The name tf.python_io.TFRecordWriter is deprecated. Please use tf.io.TFRecordWriter instead.\n",
"\n",
"W0326 12:51:46.857765 140573736023936 module_wrapper.py:139] From /content/models/research/object_detection/dataset_tools/tf_record_creation_util.py:43: The name tf.python_io.TFRecordWriter is deprecated. Please use tf.io.TFRecordWriter instead.\n",
"\n",
"I0326 12:51:46.858592 140573736023936 create_pet_tf_record.py:241] On image 0 of 2576\n",
"/content/models/research/object_detection/utils/dataset_util.py:79: FutureWarning: The behavior of this method will change in future versions. Use specific 'len(elem)' or 'elem is not None' test instead.\n",
" if not xml:\n",
"I0326 12:51:47.083195 140573736023936 create_pet_tf_record.py:241] On image 100 of 2576\n",
"I0326 12:51:47.292751 140573736023936 create_pet_tf_record.py:241] On image 200 of 2576\n",
"I0326 12:51:47.503732 140573736023936 create_pet_tf_record.py:241] On image 300 of 2576\n",
"I0326 12:51:47.706442 140573736023936 create_pet_tf_record.py:241] On image 400 of 2576\n",
"I0326 12:51:47.899457 140573736023936 create_pet_tf_record.py:241] On image 500 of 2576\n",
"W0326 12:51:48.045289 140573736023936 create_pet_tf_record.py:246] Could not find /content/data/annotations/xmls/Egyptian_Mau_14.xml, ignoring example.\n",
"W0326 12:51:48.079262 140573736023936 create_pet_tf_record.py:246] Could not find /content/data/annotations/xmls/saint_bernard_15.xml, ignoring example.\n",
"I0326 12:51:48.101510 140573736023936 create_pet_tf_record.py:241] On image 600 of 2576\n",
"W0326 12:51:48.109645 140573736023936 create_pet_tf_record.py:246] Could not find /content/data/annotations/xmls/Ragdoll_199.xml, ignoring example.\n",
"I0326 12:51:48.296629 140573736023936 create_pet_tf_record.py:241] On image 700 of 2576\n",
"I0326 12:51:48.500024 140573736023936 create_pet_tf_record.py:241] On image 800 of 2576\n",
"I0326 12:51:48.694274 140573736023936 create_pet_tf_record.py:241] On image 900 of 2576\n",
"I0326 12:51:48.893217 140573736023936 create_pet_tf_record.py:241] On image 1000 of 2576\n",
"I0326 12:51:49.094558 140573736023936 create_pet_tf_record.py:241] On image 1100 of 2576\n",
"I0326 12:51:49.359411 140573736023936 create_pet_tf_record.py:241] On image 1200 of 2576\n",
"I0326 12:51:49.577455 140573736023936 create_pet_tf_record.py:241] On image 1300 of 2576\n",
"I0326 12:51:49.832014 140573736023936 create_pet_tf_record.py:241] On image 1400 of 2576\n",
"W0326 12:51:49.944490 140573736023936 create_pet_tf_record.py:246] Could not find /content/data/annotations/xmls/Egyptian_Mau_186.xml, ignoring example.\n",
"I0326 12:51:50.041374 140573736023936 create_pet_tf_record.py:241] On image 1500 of 2576\n",
"W0326 12:51:50.175854 140573736023936 create_pet_tf_record.py:246] Could not find /content/data/annotations/xmls/Bengal_175.xml, ignoring example.\n",
"I0326 12:51:50.242223 140573736023936 create_pet_tf_record.py:241] On image 1600 of 2576\n",
"I0326 12:51:50.439038 140573736023936 create_pet_tf_record.py:241] On image 1700 of 2576\n",
"W0326 12:51:50.569970 140573736023936 create_pet_tf_record.py:246] Could not find /content/data/annotations/xmls/samoyed_10.xml, ignoring example.\n",
"I0326 12:51:50.644374 140573736023936 create_pet_tf_record.py:241] On image 1800 of 2576\n",
"I0326 12:51:50.854284 140573736023936 create_pet_tf_record.py:241] On image 1900 of 2576\n",
"I0326 12:51:51.053976 140573736023936 create_pet_tf_record.py:241] On image 2000 of 2576\n",
"I0326 12:51:51.258865 140573736023936 create_pet_tf_record.py:241] On image 2100 of 2576\n",
"W0326 12:51:51.334646 140573736023936 create_pet_tf_record.py:246] Could not find /content/data/annotations/xmls/Egyptian_Mau_156.xml, ignoring example.\n",
"I0326 12:51:51.474264 140573736023936 create_pet_tf_record.py:241] On image 2200 of 2576\n",
"I0326 12:51:51.685006 140573736023936 create_pet_tf_record.py:241] On image 2300 of 2576\n",
"I0326 12:51:51.931207 140573736023936 create_pet_tf_record.py:241] On image 2400 of 2576\n",
"I0326 12:51:52.148934 140573736023936 create_pet_tf_record.py:241] On image 2500 of 2576\n",
"W0326 12:51:52.268724 140573736023936 create_pet_tf_record.py:246] Could not find /content/data/annotations/xmls/Abyssinian_104.xml, ignoring example.\n",
"I0326 12:51:52.332354 140573736023936 create_pet_tf_record.py:241] On image 0 of 1104\n",
"I0326 12:51:52.540646 140573736023936 create_pet_tf_record.py:241] On image 100 of 1104\n",
"I0326 12:51:52.747583 140573736023936 create_pet_tf_record.py:241] On image 200 of 1104\n",
"I0326 12:51:52.945310 140573736023936 create_pet_tf_record.py:241] On image 300 of 1104\n",
"I0326 12:51:53.154044 140573736023936 create_pet_tf_record.py:241] On image 400 of 1104\n",
"I0326 12:51:53.350758 140573736023936 create_pet_tf_record.py:241] On image 500 of 1104\n",
"I0326 12:51:53.565596 140573736023936 create_pet_tf_record.py:241] On image 600 of 1104\n",
"I0326 12:51:53.762596 140573736023936 create_pet_tf_record.py:241] On image 700 of 1104\n",
"I0326 12:51:54.015244 140573736023936 create_pet_tf_record.py:241] On image 800 of 1104\n",
"W0326 12:51:54.106797 140573736023936 create_pet_tf_record.py:246] Could not find /content/data/annotations/xmls/Bengal_111.xml, ignoring example.\n",
"I0326 12:51:54.231238 140573736023936 create_pet_tf_record.py:241] On image 900 of 1104\n",
"I0326 12:51:54.444205 140573736023936 create_pet_tf_record.py:241] On image 1000 of 1104\n",
"I0326 12:51:54.667312 140573736023936 create_pet_tf_record.py:241] On image 1100 of 1104\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "rebVEGNRkv_v",
"colab_type": "code",
"outputId": "28569303-5656-4e4c-a008-02adf0ce8e4d",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 187
}
},
"source": [
"!ls ${TF_RECORD_DIR}"
],
"execution_count": 17,
"outputs": [
{
"output_type": "stream",
"text": [
"pet_faces_train.record-00000-of-00010 pet_faces_val.record-00000-of-00010\n",
"pet_faces_train.record-00001-of-00010 pet_faces_val.record-00001-of-00010\n",
"pet_faces_train.record-00002-of-00010 pet_faces_val.record-00002-of-00010\n",
"pet_faces_train.record-00003-of-00010 pet_faces_val.record-00003-of-00010\n",
"pet_faces_train.record-00004-of-00010 pet_faces_val.record-00004-of-00010\n",
"pet_faces_train.record-00005-of-00010 pet_faces_val.record-00005-of-00010\n",
"pet_faces_train.record-00006-of-00010 pet_faces_val.record-00006-of-00010\n",
"pet_faces_train.record-00007-of-00010 pet_faces_val.record-00007-of-00010\n",
"pet_faces_train.record-00008-of-00010 pet_faces_val.record-00008-of-00010\n",
"pet_faces_train.record-00009-of-00010 pet_faces_val.record-00009-of-00010\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Ndb6N895JwJ6",
"colab_type": "text"
},
"source": [
"# Get the pretrained model for transfer learning\n",
"\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "at-wzrEXkDIe",
"colab_type": "code",
"outputId": "4fef14df-c8a9-43ae-f6b7-cc536f0bdbbd",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 204
}
},
"source": [
"!wget http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v3_large_coco_2020_01_14.tar.gz -P ${DATA_DIR}"
],
"execution_count": 18,
"outputs": [
{
"output_type": "stream",
"text": [
"--2020-03-26 12:51:58-- http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v3_large_coco_2020_01_14.tar.gz\n",
"Resolving download.tensorflow.org (download.tensorflow.org)... 173.194.79.128, 2a00:1450:4013:c01::80\n",
"Connecting to download.tensorflow.org (download.tensorflow.org)|173.194.79.128|:80... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 49318766 (47M) [application/gzip]\n",
"Saving to: ‘/content/data/ssd_mobilenet_v3_large_coco_2020_01_14.tar.gz’\n",
"\n",
"ssd_mobilenet_v3_la 100%[===================>] 47.03M 54.1MB/s in 0.9s \n",
"\n",
"2020-03-26 12:51:59 (54.1 MB/s) - ‘/content/data/ssd_mobilenet_v3_large_coco_2020_01_14.tar.gz’ saved [49318766/49318766]\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "qrZckBblkP8x",
"colab_type": "code",
"colab": {}
},
"source": [
"!tar xf ${DATA_DIR}/ssd_mobilenet_v3_large_coco_2020_01_14.tar.gz -C ${DATA_DIR}"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "KlCKFYLmBvI6",
"colab_type": "text"
},
"source": [
"# Create config file"
]
},
{
"cell_type": "code",
"metadata": {
"id": "jkPGN1qW8T__",
"colab_type": "code",
"colab": {}
},
"source": [
"!cp .//object_detection/samples/configs/ssdlite_mobilenet_v3_large_320x320_coco.config ${DATA_DIR}/ssdlite_mobilenet_v3_large_320x320_pet_quant.config"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "wpRIcKWn_NnN",
"colab_type": "code",
"colab": {}
},
"source": [
"%%bash\n",
"cat <<EOF > ${DATA_DIR}/config.patch\n",
"--- ssdlite_mobilenet_v3_large_320x320_coco.config\t2020-03-25 18:08:14.091572323 +0900\n",
"+++ ssdlite_mobilenet_v3_large_320x320_pet_quant.config\t2020-03-25 21:43:17.108732045 +0900\n",
"@@ -11,7 +11,7 @@ model {\n",
" ssd {\n",
" inplace_batchnorm_update: true\n",
" freeze_batchnorm: false\n",
"- num_classes: 90\n",
"+ num_classes: 37\n",
" box_coder {\n",
" faster_rcnn_box_coder {\n",
" y_scale: 10.0\n",
"@@ -147,7 +147,7 @@ model {\n",
" }\n",
" \n",
" train_config: {\n",
"- batch_size: 512\n",
"+ batch_size: 8\n",
" sync_replicas: true\n",
" startup_delay_steps: 0\n",
" replicas_to_aggregate: 32\n",
"@@ -180,21 +180,28 @@ train_config: {\n",
" \n",
" train_input_reader: {\n",
" tf_record_input_reader {\n",
"- input_path: \"PATH_TO_BE_CONFIGURED/mscoco_train.record-?????-of-00100\"\n",
"+ input_path: \"/content/data/tf_record/pet_faces_train.record-?????-of-00010\"\n",
" }\n",
"- label_map_path: \"PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt\"\n",
"+ label_map_path: \"/content/models/research/object_detection/data/pet_label_map.pbtxt\"\n",
" }\n",
" \n",
" eval_config: {\n",
"- num_examples: 8000\n",
"+ num_examples: 1104\n",
" }\n",
" \n",
" eval_input_reader: {\n",
" tf_record_input_reader {\n",
"- input_path: \"PATH_TO_BE_CONFIGURED/mscoco_val.record-?????-of-00010\"\n",
"+ input_path: \"/content/data/tf_record/pet_faces_train.record-?????-of-00010\"\n",
" }\n",
"- label_map_path: \"PATH_TO_BE_CONFIGURED/mscoco_label_map.pbtxt\"\n",
"+ label_map_path: \"/content/models/research/object_detection/data/pet_label_map.pbtxt\"\n",
" shuffle: false\n",
" num_readers: 1\n",
" }\n",
" \n",
"+graph_rewriter {\n",
"+ quantization {\n",
"+ delay: 40000\n",
"+ activation_bits: 8\n",
"+ weight_bits: 8\n",
"+ }\n",
"+}\n",
"EOF"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "_89sZTiQAngu",
"colab_type": "code",
"outputId": "85064493-7d1c-41d6-f674-db1abff4255a",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"!patch -u ${DATA_DIR}/ssdlite_mobilenet_v3_large_320x320_pet_quant.config < ${DATA_DIR}/config.patch"
],
"execution_count": 22,
"outputs": [
{
"output_type": "stream",
"text": [
"patching file /content/data/ssdlite_mobilenet_v3_large_320x320_pet_quant.config\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "SwbAVryqA5t7",
"colab_type": "code",
"outputId": "e972f119-0060-4131-986d-eb66e186c1d6",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
},
"source": [
"!cat ${DATA_DIR}/ssdlite_mobilenet_v3_large_320x320_pet_quant.config"
],
"execution_count": 23,
"outputs": [
{
"output_type": "stream",
"text": [
"# SSDLite with Mobilenet v3 large feature extractor.\n",
"# Trained on COCO14, initialized from scratch.\n",
"# 3.22M parameters, 1.02B FLOPs\n",
"# TPU-compatible.\n",
"# Users should configure the fine_tune_checkpoint field in the train config as\n",
"# well as the label_map_path and input_path fields in the train_input_reader and\n",
"# eval_input_reader. Search for \"PATH_TO_BE_CONFIGURED\" to find the fields that\n",
"# should be configured.\n",
"\n",
"model {\n",
" ssd {\n",
" inplace_batchnorm_update: true\n",
" freeze_batchnorm: false\n",
" num_classes: 37\n",
" box_coder {\n",
" faster_rcnn_box_coder {\n",
" y_scale: 10.0\n",
" x_scale: 10.0\n",
" height_scale: 5.0\n",
" width_scale: 5.0\n",
" }\n",
" }\n",
" matcher {\n",
" argmax_matcher {\n",
" matched_threshold: 0.5\n",
" unmatched_threshold: 0.5\n",
" ignore_thresholds: false\n",
" negatives_lower_than_unmatched: true\n",
" force_match_for_each_row: true\n",
" use_matmul_gather: true\n",
" }\n",
" }\n",
" similarity_calculator {\n",
" iou_similarity {\n",
" }\n",
" }\n",
" encode_background_as_zeros: true\n",
" anchor_generator {\n",
" ssd_anchor_generator {\n",
" num_layers: 6\n",
" min_scale: 0.2\n",
" max_scale: 0.95\n",
" aspect_ratios: 1.0\n",
" aspect_ratios: 2.0\n",
" aspect_ratios: 0.5\n",
" aspect_ratios: 3.0\n",
" aspect_ratios: 0.3333\n",
" }\n",
" }\n",
" image_resizer {\n",
" fixed_shape_resizer {\n",
" height: 320\n",
" width: 320\n",
" }\n",
" }\n",
" box_predictor {\n",
" convolutional_box_predictor {\n",
" min_depth: 0\n",
" max_depth: 0\n",
" num_layers_before_predictor: 0\n",
" use_dropout: false\n",
" dropout_keep_probability: 0.8\n",
" kernel_size: 3\n",
" use_depthwise: true\n",
" box_code_size: 4\n",
" apply_sigmoid_to_scores: false\n",
" class_prediction_bias_init: -4.6\n",
" conv_hyperparams {\n",
" activation: RELU_6,\n",
" regularizer {\n",
" l2_regularizer {\n",
" weight: 0.00004\n",
" }\n",
" }\n",
" initializer {\n",
" random_normal_initializer {\n",
" stddev: 0.03\n",
" mean: 0.0\n",
" }\n",
" }\n",
" batch_norm {\n",
" train: true,\n",
" scale: true,\n",
" center: true,\n",
" decay: 0.97,\n",
" epsilon: 0.001,\n",
" }\n",
" }\n",
" }\n",
" }\n",
" feature_extractor {\n",
" type: 'ssd_mobilenet_v3_large'\n",
" min_depth: 16\n",
" depth_multiplier: 1.0\n",
" use_depthwise: true\n",
" conv_hyperparams {\n",
" activation: RELU_6,\n",
" regularizer {\n",
" l2_regularizer {\n",
" weight: 0.00004\n",
" }\n",
" }\n",
" initializer {\n",
" truncated_normal_initializer {\n",
" stddev: 0.03\n",
" mean: 0.0\n",
" }\n",
" }\n",
" batch_norm {\n",
" train: true,\n",
" scale: true,\n",
" center: true,\n",
" decay: 0.97,\n",
" epsilon: 0.001,\n",
" }\n",
" }\n",
" override_base_feature_extractor_hyperparams: true\n",
" }\n",
" loss {\n",
" classification_loss {\n",
" weighted_sigmoid_focal {\n",
" alpha: 0.75,\n",
" gamma: 2.0\n",
" }\n",
" }\n",
" localization_loss {\n",
" weighted_smooth_l1 {\n",
" delta: 1.0\n",
" }\n",
" }\n",
" classification_weight: 1.0\n",
" localization_weight: 1.0\n",
" }\n",
" normalize_loss_by_num_matches: true\n",
" normalize_loc_loss_by_codesize: true\n",
" post_processing {\n",
" batch_non_max_suppression {\n",
" score_threshold: 1e-8\n",
" iou_threshold: 0.6\n",
" max_detections_per_class: 100\n",
" max_total_detections: 100\n",
" use_static_shapes: true\n",
" }\n",
" score_converter: SIGMOID\n",
" }\n",
" }\n",
"}\n",
"\n",
"train_config: {\n",
" batch_size: 8\n",
" sync_replicas: true\n",
" startup_delay_steps: 0\n",
" replicas_to_aggregate: 32\n",
" num_steps: 400000\n",
" data_augmentation_options {\n",
" random_horizontal_flip {\n",
" }\n",
" }\n",
" data_augmentation_options {\n",
" ssd_random_crop {\n",
" }\n",
" }\n",
" optimizer {\n",
" momentum_optimizer: {\n",
" learning_rate: {\n",
" cosine_decay_learning_rate {\n",
" learning_rate_base: 0.4\n",
" total_steps: 400000\n",
" warmup_learning_rate: 0.13333\n",
" warmup_steps: 2000\n",
" }\n",
" }\n",
" momentum_optimizer_value: 0.9\n",
" }\n",
" use_moving_average: false\n",
" }\n",
" max_number_of_boxes: 100\n",
" unpad_groundtruth_tensors: false\n",
"}\n",
"\n",
"train_input_reader: {\n",
" tf_record_input_reader {\n",
" input_path: \"/content/data/tf_record/pet_faces_train.record-?????-of-00010\"\n",
" }\n",
" label_map_path: \"/content/models/research/object_detection/data/pet_label_map.pbtxt\"\n",
"}\n",
"\n",
"eval_config: {\n",
" num_examples: 1104\n",
"}\n",
"\n",
"eval_input_reader: {\n",
" tf_record_input_reader {\n",
" input_path: \"/content/data/tf_record/pet_faces_train.record-?????-of-00010\"\n",
" }\n",
" label_map_path: \"/content/models/research/object_detection/data/pet_label_map.pbtxt\"\n",
" shuffle: false\n",
" num_readers: 1\n",
"}\n",
"\n",
"graph_rewriter {\n",
" quantization {\n",
" delay: 40000\n",
" activation_bits: 8\n",
" weight_bits: 8\n",
" }\n",
"}\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "rF7J2C_aUb0n",
"colab_type": "text"
},
"source": [
"# Train the model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "gs57oAxVUery",
"colab_type": "code",
"outputId": "74d7dcad-b302-4c96-e7b3-9dbc590c59c0",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
},
"source": [
"!python ./object_detection/model_main.py \\\n",
" --alsologtostderr \\\n",
" --pipeline_config_path=${DATA_DIR}/ssdlite_mobilenet_v3_large_320x320_pet_quant.config \\\n",
" --num_train_steps=500000 \\\n",
" --sample_1_of_n_eval_examples=1 \\\n",
" --model_dir=${DATA_DIR}/train_ssdlite_mobilenet_v3_large_320x320_pet_quant"
],
"execution_count": 24,
"outputs": [
{
"output_type": "stream",
"text": [
"WARNING:tensorflow:\n",
"The TensorFlow contrib module will not be included in TensorFlow 2.0.\n",
"For more information, please see:\n",
" * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md\n",
" * https://github.com/tensorflow/addons\n",
" * https://github.com/tensorflow/io (for I/O related ops)\n",
"If you depend on functionality not listed there, please file an issue.\n",
"\n",
"WARNING:tensorflow:From ./object_detection/model_main.py:109: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/utils/config_util.py:102: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.\n",
"\n",
"W0326 12:52:14.309029 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/utils/config_util.py:102: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/model_lib.py:628: The name tf.logging.warning is deprecated. Please use tf.compat.v1.logging.warning instead.\n",
"\n",
"W0326 12:52:14.312200 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/model_lib.py:628: The name tf.logging.warning is deprecated. Please use tf.compat.v1.logging.warning instead.\n",
"\n",
"WARNING:tensorflow:Forced number of epochs for all eval validations to be 1.\n",
"W0326 12:52:14.312340 140541047973760 model_lib.py:629] Forced number of epochs for all eval validations to be 1.\n",
"WARNING:tensorflow:From /content/models/research/object_detection/utils/config_util.py:488: The name tf.logging.info is deprecated. Please use tf.compat.v1.logging.info instead.\n",
"\n",
"W0326 12:52:14.312434 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/utils/config_util.py:488: The name tf.logging.info is deprecated. Please use tf.compat.v1.logging.info instead.\n",
"\n",
"INFO:tensorflow:Maybe overwriting train_steps: 500000\n",
"I0326 12:52:14.312507 140541047973760 config_util.py:488] Maybe overwriting train_steps: 500000\n",
"INFO:tensorflow:Maybe overwriting use_bfloat16: False\n",
"I0326 12:52:14.312583 140541047973760 config_util.py:488] Maybe overwriting use_bfloat16: False\n",
"INFO:tensorflow:Maybe overwriting sample_1_of_n_eval_examples: 1\n",
"I0326 12:52:14.312639 140541047973760 config_util.py:488] Maybe overwriting sample_1_of_n_eval_examples: 1\n",
"INFO:tensorflow:Maybe overwriting eval_num_epochs: 1\n",
"I0326 12:52:14.312697 140541047973760 config_util.py:488] Maybe overwriting eval_num_epochs: 1\n",
"INFO:tensorflow:Maybe overwriting load_pretrained: True\n",
"I0326 12:52:14.312751 140541047973760 config_util.py:488] Maybe overwriting load_pretrained: True\n",
"INFO:tensorflow:Ignoring config override key: load_pretrained\n",
"I0326 12:52:14.312804 140541047973760 config_util.py:498] Ignoring config override key: load_pretrained\n",
"WARNING:tensorflow:Expected number of evaluation epochs is 1, but instead encountered `eval_on_train_input_config.num_epochs` = 0. Overwriting `num_epochs` to 1.\n",
"W0326 12:52:14.313339 140541047973760 model_lib.py:645] Expected number of evaluation epochs is 1, but instead encountered `eval_on_train_input_config.num_epochs` = 0. Overwriting `num_epochs` to 1.\n",
"INFO:tensorflow:create_estimator_and_inputs: use_tpu False, export_to_tpu False\n",
"I0326 12:52:14.313416 140541047973760 model_lib.py:680] create_estimator_and_inputs: use_tpu False, export_to_tpu False\n",
"INFO:tensorflow:Using config: {'_model_dir': '/content/data/train_ssdlite_mobilenet_v3_large_320x320_pet_quant', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true\n",
"graph_options {\n",
" rewrite_options {\n",
" meta_optimizer_iterations: ONE\n",
" }\n",
"}\n",
", '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x7fd1db401278>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}\n",
"I0326 12:52:14.313771 140541047973760 estimator.py:212] Using config: {'_model_dir': '/content/data/train_ssdlite_mobilenet_v3_large_320x320_pet_quant', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true\n",
"graph_options {\n",
" rewrite_options {\n",
" meta_optimizer_iterations: ONE\n",
" }\n",
"}\n",
", '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x7fd1db401278>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}\n",
"WARNING:tensorflow:Estimator's model_fn (<function create_model_fn.<locals>.model_fn at 0x7fd1db4110d0>) includes params argument, but params are not passed to Estimator.\n",
"W0326 12:52:14.313978 140541047973760 model_fn.py:630] Estimator's model_fn (<function create_model_fn.<locals>.model_fn at 0x7fd1db4110d0>) includes params argument, but params are not passed to Estimator.\n",
"INFO:tensorflow:Not using Distribute Coordinator.\n",
"I0326 12:52:14.314560 140541047973760 estimator_training.py:186] Not using Distribute Coordinator.\n",
"INFO:tensorflow:Running training and evaluation locally (non-distributed).\n",
"I0326 12:52:14.314706 140541047973760 training.py:612] Running training and evaluation locally (non-distributed).\n",
"INFO:tensorflow:Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 600.\n",
"I0326 12:52:14.314934 140541047973760 training.py:700] Start train and evaluate loop. The evaluate will happen after every checkpoint. Checkpoint frequency is determined based on RunConfig arguments: save_checkpoints_steps None or save_checkpoints_secs 600.\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/python/training/training_util.py:236: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.\n",
"W0326 12:52:14.319812 140541047973760 deprecation.py:323] From /tensorflow-1.15.0/python3.6/tensorflow_core/python/training/training_util.py:236: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.\n",
"WARNING:tensorflow:From /content/models/research/object_detection/data_decoders/tf_example_decoder.py:182: The name tf.FixedLenFeature is deprecated. Please use tf.io.FixedLenFeature instead.\n",
"\n",
"W0326 12:52:14.329651 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/data_decoders/tf_example_decoder.py:182: The name tf.FixedLenFeature is deprecated. Please use tf.io.FixedLenFeature instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/data_decoders/tf_example_decoder.py:197: The name tf.VarLenFeature is deprecated. Please use tf.io.VarLenFeature instead.\n",
"\n",
"W0326 12:52:14.329837 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/data_decoders/tf_example_decoder.py:197: The name tf.VarLenFeature is deprecated. Please use tf.io.VarLenFeature instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/builders/dataset_builder.py:64: The name tf.gfile.Glob is deprecated. Please use tf.io.gfile.glob instead.\n",
"\n",
"W0326 12:52:14.349049 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/builders/dataset_builder.py:64: The name tf.gfile.Glob is deprecated. Please use tf.io.gfile.glob instead.\n",
"\n",
"WARNING:tensorflow:num_readers has been reduced to 10 to match input file shards.\n",
"W0326 12:52:14.350166 140541047973760 dataset_builder.py:72] num_readers has been reduced to 10 to match input file shards.\n",
"WARNING:tensorflow:From /content/models/research/object_detection/builders/dataset_builder.py:86: parallel_interleave (from tensorflow.contrib.data.python.ops.interleave_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.data.experimental.parallel_interleave(...)`.\n",
"W0326 12:52:14.355205 140541047973760 deprecation.py:323] From /content/models/research/object_detection/builders/dataset_builder.py:86: parallel_interleave (from tensorflow.contrib.data.python.ops.interleave_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.data.experimental.parallel_interleave(...)`.\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/contrib/data/python/ops/interleave_ops.py:77: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.experimental.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.experimental_determinstic`.\n",
"W0326 12:52:14.355346 140541047973760 deprecation.py:323] From /tensorflow-1.15.0/python3.6/tensorflow_core/contrib/data/python/ops/interleave_ops.py:77: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.experimental.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.experimental_determinstic`.\n",
"WARNING:tensorflow:From /content/models/research/object_detection/builders/dataset_builder.py:155: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.data.Dataset.map()\n",
"W0326 12:52:14.375086 140541047973760 deprecation.py:323] From /content/models/research/object_detection/builders/dataset_builder.py:155: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.data.Dataset.map()\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.logging.warn is deprecated. Please use tf.compat.v1.logging.warn instead.\n",
"\n",
"W0326 12:52:15.495286 140541047973760 module_wrapper.py:139] From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.logging.warn is deprecated. Please use tf.compat.v1.logging.warn instead.\n",
"\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.is_nan is deprecated. Please use tf.math.is_nan instead.\n",
"\n",
"W0326 12:52:21.758614 140541047973760 module_wrapper.py:139] From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.is_nan is deprecated. Please use tf.math.is_nan instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/utils/ops.py:493: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use tf.where in 2.0, which has the same broadcast rule as np.where\n",
"W0326 12:52:21.827741 140541047973760 deprecation.py:323] From /content/models/research/object_detection/utils/ops.py:493: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use tf.where in 2.0, which has the same broadcast rule as np.where\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n",
"\n",
"W0326 12:52:23.739733 140541047973760 module_wrapper.py:139] From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n",
"\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/operators/control_flow.py:1004: sample_distorted_bounding_box (from tensorflow.python.ops.image_ops_impl) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"`seed2` arg is deprecated.Use sample_distorted_bounding_box_v2 instead.\n",
"W0326 12:52:26.693611 140541047973760 api.py:332] From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/operators/control_flow.py:1004: sample_distorted_bounding_box (from tensorflow.python.ops.image_ops_impl) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"`seed2` arg is deprecated.Use sample_distorted_bounding_box_v2 instead.\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.image.resize_images is deprecated. Please use tf.image.resize instead.\n",
"\n",
"W0326 12:52:29.754335 140541047973760 module_wrapper.py:139] From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.image.resize_images is deprecated. Please use tf.image.resize instead.\n",
"\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.image.resize_nearest_neighbor is deprecated. Please use tf.compat.v1.image.resize_nearest_neighbor instead.\n",
"\n",
"W0326 12:52:29.755270 140541047973760 module_wrapper.py:139] From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.image.resize_nearest_neighbor is deprecated. Please use tf.compat.v1.image.resize_nearest_neighbor instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/inputs.py:166: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.cast` instead.\n",
"W0326 12:52:30.124233 140541047973760 deprecation.py:323] From /content/models/research/object_detection/inputs.py:166: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.cast` instead.\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.string_to_hash_bucket_fast is deprecated. Please use tf.strings.to_hash_bucket_fast instead.\n",
"\n",
"W0326 12:52:31.618521 140541047973760 module_wrapper.py:139] From /tensorflow-1.15.0/python3.6/tensorflow_core/python/autograph/converters/directives.py:119: The name tf.string_to_hash_bucket_fast is deprecated. Please use tf.strings.to_hash_bucket_fast instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/builders/dataset_builder.py:158: batch_and_drop_remainder (from tensorflow.contrib.data.python.ops.batching) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.data.Dataset.batch(..., drop_remainder=True)`.\n",
"W0326 12:52:32.187494 140541047973760 deprecation.py:323] From /content/models/research/object_detection/builders/dataset_builder.py:158: batch_and_drop_remainder (from tensorflow.contrib.data.python.ops.batching) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.data.Dataset.batch(..., drop_remainder=True)`.\n",
"INFO:tensorflow:Calling model_fn.\n",
"I0326 12:52:32.199613 140541047973760 estimator.py:1148] Calling model_fn.\n",
"WARNING:tensorflow:From /content/models/research/object_detection/meta_architectures/ssd_meta_arch.py:597: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.\n",
"\n",
"W0326 12:52:32.205116 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/meta_architectures/ssd_meta_arch.py:597: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.\n",
"\n",
"WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/contrib/layers/python/layers/layers.py:1057: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Please use `layer.__call__` method instead.\n",
"W0326 12:52:32.207756 140541047973760 deprecation.py:323] From /tensorflow-1.15.0/python3.6/tensorflow_core/contrib/layers/python/layers/layers.py:1057: Layer.apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Please use `layer.__call__` method instead.\n",
"WARNING:tensorflow:From /content/models/research/object_detection/core/anchor_generator.py:171: The name tf.assert_equal is deprecated. Please use tf.compat.v1.assert_equal instead.\n",
"\n",
"W0326 12:52:34.691858 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/core/anchor_generator.py:171: The name tf.assert_equal is deprecated. Please use tf.compat.v1.assert_equal instead.\n",
"\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 12:52:34.701515 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 12:52:34.784972 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 12:52:34.868394 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 12:52:34.954049 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 12:52:35.042302 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 12:52:35.128274 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"WARNING:tensorflow:From /content/models/research/object_detection/box_coders/faster_rcnn_box_coder.py:82: The name tf.log is deprecated. Please use tf.math.log instead.\n",
"\n",
"W0326 12:52:35.312079 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/box_coders/faster_rcnn_box_coder.py:82: The name tf.log is deprecated. Please use tf.math.log instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/meta_architectures/ssd_meta_arch.py:1163: The name tf.summary.scalar is deprecated. Please use tf.compat.v1.summary.scalar instead.\n",
"\n",
"W0326 12:52:36.414136 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/meta_architectures/ssd_meta_arch.py:1163: The name tf.summary.scalar is deprecated. Please use tf.compat.v1.summary.scalar instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/core/losses.py:177: The name tf.losses.huber_loss is deprecated. Please use tf.compat.v1.losses.huber_loss instead.\n",
"\n",
"W0326 12:52:36.419421 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/core/losses.py:177: The name tf.losses.huber_loss is deprecated. Please use tf.compat.v1.losses.huber_loss instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/core/losses.py:183: The name tf.losses.Reduction is deprecated. Please use tf.compat.v1.losses.Reduction instead.\n",
"\n",
"W0326 12:52:36.420530 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/core/losses.py:183: The name tf.losses.Reduction is deprecated. Please use tf.compat.v1.losses.Reduction instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/meta_architectures/ssd_meta_arch.py:1275: The name tf.get_collection is deprecated. Please use tf.compat.v1.get_collection instead.\n",
"\n",
"W0326 12:52:36.450853 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/meta_architectures/ssd_meta_arch.py:1275: The name tf.get_collection is deprecated. Please use tf.compat.v1.get_collection instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/meta_architectures/ssd_meta_arch.py:1275: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.\n",
"\n",
"W0326 12:52:36.451048 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/meta_architectures/ssd_meta_arch.py:1275: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/builders/graph_rewriter_builder.py:36: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
"\n",
"W0326 12:52:36.454129 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/builders/graph_rewriter_builder.py:36: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
"\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/Conv/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:39.178736 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/Conv/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:39.629275 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:39.689242 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:39.747247 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:39.804186 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.101855 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.158033 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.315417 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.376410 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.529573 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.587970 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.644420 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.700639 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.849004 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.900222 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:40.953678 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:41.014138 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:41.157772 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:41.213422 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/Conv_1/hard_swish/add, because its followed by an activation.\n",
"I0326 12:52:41.371108 140541047973760 quantize.py:201] Skipping FeatureExtractor/MobilenetV3/Conv_1/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 12:52:41.962776 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 12:52:42.277287 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 12:52:42.557505 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 12:52:42.782041 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 12:52:43.005202 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 12:52:43.173555 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 12:52:43.399762 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 12:52:43.560143 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/add\n",
"I0326 12:52:45.914775 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/mul\n",
"I0326 12:52:45.915014 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/mul_1\n",
"I0326 12:52:45.963007 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/add\n",
"I0326 12:52:46.007141 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/mul\n",
"I0326 12:52:46.007357 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/mul\n",
"I0326 12:52:46.055569 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/add\n",
"I0326 12:52:46.107729 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/mul\n",
"I0326 12:52:46.107956 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/mul\n",
"I0326 12:52:46.160009 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/add\n",
"I0326 12:52:46.207118 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/mul\n",
"I0326 12:52:46.207297 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/mul\n",
"I0326 12:52:46.254517 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/add\n",
"I0326 12:52:46.296639 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/mul\n",
"I0326 12:52:46.296786 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/mul_1\n",
"I0326 12:52:46.338740 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/add\n",
"I0326 12:52:46.384228 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/mul\n",
"I0326 12:52:46.384373 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/mul_1\n",
"I0326 12:52:46.427589 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/add\n",
"I0326 12:52:46.469341 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/mul\n",
"I0326 12:52:46.469481 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/mul_1\n",
"I0326 12:52:46.511838 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/add\n",
"I0326 12:52:46.553445 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/mul\n",
"I0326 12:52:46.553601 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/mul_1\n",
"I0326 12:52:46.602624 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/add\n",
"I0326 12:52:46.651503 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/mul\n",
"I0326 12:52:46.651661 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/mul_1\n",
"I0326 12:52:46.696034 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/add\n",
"I0326 12:52:46.746289 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/mul\n",
"I0326 12:52:46.746500 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/mul_1\n",
"I0326 12:52:46.794007 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/add\n",
"I0326 12:52:46.846582 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/mul\n",
"I0326 12:52:46.846828 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/mul_1\n",
"I0326 12:52:46.893006 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/add\n",
"I0326 12:52:46.939928 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/mul\n",
"I0326 12:52:46.940144 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/mul_1\n",
"I0326 12:52:46.987476 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/add\n",
"I0326 12:52:47.036957 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/mul\n",
"I0326 12:52:47.037233 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/mul_1\n",
"I0326 12:52:47.081943 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/add\n",
"I0326 12:52:47.130381 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/mul\n",
"I0326 12:52:47.130619 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/mul_1\n",
"I0326 12:52:47.178846 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/add\n",
"I0326 12:52:47.225315 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/mul\n",
"I0326 12:52:47.225530 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/mul\n",
"I0326 12:52:47.270516 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/add\n",
"I0326 12:52:47.316034 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/mul\n",
"I0326 12:52:47.316212 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/mul_1\n",
"I0326 12:52:47.359321 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/add\n",
"I0326 12:52:47.405507 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/mul\n",
"I0326 12:52:47.405679 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/mul_1\n",
"I0326 12:52:47.449866 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/add\n",
"I0326 12:52:47.492255 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/mul\n",
"I0326 12:52:47.492445 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/mul\n",
"I0326 12:52:47.534546 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/add\n",
"I0326 12:52:47.577088 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/mul\n",
"I0326 12:52:47.577260 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/mul_1\n",
"I0326 12:52:47.620008 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/add\n",
"I0326 12:52:47.674261 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/mul\n",
"I0326 12:52:47.674453 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/mul_1\n",
"I0326 12:52:47.726766 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/add\n",
"I0326 12:52:47.778934 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/mul\n",
"I0326 12:52:47.779161 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/mul\n",
"I0326 12:52:47.827464 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/add\n",
"I0326 12:52:47.872175 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/mul\n",
"I0326 12:52:47.872362 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/mul_1\n",
"I0326 12:52:47.916526 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/add\n",
"I0326 12:52:47.963000 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/mul\n",
"I0326 12:52:47.963185 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/mul_1\n",
"I0326 12:52:48.007937 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/add\n",
"I0326 12:52:48.052159 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/mul\n",
"I0326 12:52:48.052350 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/mul\n",
"I0326 12:52:48.098970 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/add\n",
"I0326 12:52:48.142588 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/mul\n",
"I0326 12:52:48.142825 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/mul_1\n",
"I0326 12:52:48.192094 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/add\n",
"I0326 12:52:48.241811 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/mul\n",
"I0326 12:52:48.242073 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/mul_1\n",
"I0326 12:52:48.299874 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/add\n",
"I0326 12:52:48.348566 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/mul\n",
"I0326 12:52:48.348783 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/mul\n",
"I0326 12:52:48.401658 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/add\n",
"I0326 12:52:48.447884 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/mul\n",
"I0326 12:52:48.448120 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/mul_1\n",
"I0326 12:52:48.494658 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/mul_1\n",
"WARNING:tensorflow:From /content/models/research/object_detection/model_lib.py:380: The name tf.train.get_or_create_global_step is deprecated. Please use tf.compat.v1.train.get_or_create_global_step instead.\n",
"\n",
"W0326 12:52:48.587976 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/model_lib.py:380: The name tf.train.get_or_create_global_step is deprecated. Please use tf.compat.v1.train.get_or_create_global_step instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/builders/optimizer_builder.py:58: The name tf.train.MomentumOptimizer is deprecated. Please use tf.compat.v1.train.MomentumOptimizer instead.\n",
"\n",
"W0326 12:52:48.600636 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/builders/optimizer_builder.py:58: The name tf.train.MomentumOptimizer is deprecated. Please use tf.compat.v1.train.MomentumOptimizer instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/model_lib.py:398: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.\n",
"\n",
"W0326 12:52:48.600857 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/model_lib.py:398: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/model_lib.py:515: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.\n",
"\n",
"W0326 12:53:00.044078 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/model_lib.py:515: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/model_lib.py:519: The name tf.add_to_collection is deprecated. Please use tf.compat.v1.add_to_collection instead.\n",
"\n",
"W0326 12:53:01.392883 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/model_lib.py:519: The name tf.add_to_collection is deprecated. Please use tf.compat.v1.add_to_collection instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/model_lib.py:520: The name tf.train.Scaffold is deprecated. Please use tf.compat.v1.train.Scaffold instead.\n",
"\n",
"W0326 12:53:01.393186 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/model_lib.py:520: The name tf.train.Scaffold is deprecated. Please use tf.compat.v1.train.Scaffold instead.\n",
"\n",
"INFO:tensorflow:Done calling model_fn.\n",
"I0326 12:53:01.393512 140541047973760 estimator.py:1150] Done calling model_fn.\n",
"INFO:tensorflow:Create CheckpointSaverHook.\n",
"I0326 12:53:01.394748 140541047973760 basic_session_run_hooks.py:541] Create CheckpointSaverHook.\n",
"INFO:tensorflow:Graph was finalized.\n",
"I0326 12:53:07.651153 140541047973760 monitored_session.py:240] Graph was finalized.\n",
"2020-03-26 12:53:07.651604: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX512F\n",
"2020-03-26 12:53:07.662888: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2000134999 Hz\n",
"2020-03-26 12:53:07.664986: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x244972c0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:\n",
"2020-03-26 12:53:07.665027: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version\n",
"2020-03-26 12:53:07.670573: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1\n",
"2020-03-26 12:53:07.868330: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 12:53:07.869060: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x24497100 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:\n",
"2020-03-26 12:53:07.869094: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Tesla T4, Compute Capability 7.5\n",
"2020-03-26 12:53:07.870393: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 12:53:07.870972: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: \n",
"name: Tesla T4 major: 7 minor: 5 memoryClockRate(GHz): 1.59\n",
"pciBusID: 0000:00:04.0\n",
"2020-03-26 12:53:07.871309: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1\n",
"2020-03-26 12:53:07.872851: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10\n",
"2020-03-26 12:53:07.874439: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10\n",
"2020-03-26 12:53:07.874766: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10\n",
"2020-03-26 12:53:07.876405: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10\n",
"2020-03-26 12:53:07.898135: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10\n",
"2020-03-26 12:53:07.901246: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7\n",
"2020-03-26 12:53:07.901356: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 12:53:07.901888: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 12:53:07.902356: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0\n",
"2020-03-26 12:53:07.906135: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1\n",
"2020-03-26 12:53:07.909885: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:\n",
"2020-03-26 12:53:07.909923: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 \n",
"2020-03-26 12:53:07.909934: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N \n",
"2020-03-26 12:53:07.912425: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 12:53:07.912983: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 12:53:07.913454: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:39] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0.\n",
"2020-03-26 12:53:07.913486: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14221 MB memory) -> physical GPU (device: 0, name: Tesla T4, pci bus id: 0000:00:04.0, compute capability: 7.5)\n",
"INFO:tensorflow:Running local_init_op.\n",
"I0326 12:53:20.598163 140541047973760 session_manager.py:500] Running local_init_op.\n",
"INFO:tensorflow:Done running local_init_op.\n",
"I0326 12:53:21.242310 140541047973760 session_manager.py:502] Done running local_init_op.\n",
"INFO:tensorflow:Saving checkpoints for 0 into /content/data/train_ssdlite_mobilenet_v3_large_320x320_pet_quant/model.ckpt.\n",
"I0326 12:53:38.316448 140541047973760 basic_session_run_hooks.py:606] Saving checkpoints for 0 into /content/data/train_ssdlite_mobilenet_v3_large_320x320_pet_quant/model.ckpt.\n",
"2020-03-26 12:54:07.861334: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10\n",
"2020-03-26 12:54:10.515879: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7\n",
"INFO:tensorflow:loss = 548.23346, step = 0\n",
"I0326 12:54:17.665866 140541047973760 basic_session_run_hooks.py:262] loss = 548.23346, step = 0\n",
"Corrupt JPEG data: premature end of data segment\n",
"INFO:tensorflow:global_step/sec: 1.69261\n",
"I0326 12:55:16.745522 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 1.69261\n",
"INFO:tensorflow:loss = 50.30002, step = 100 (59.081 sec)\n",
"I0326 12:55:16.746708 140541047973760 basic_session_run_hooks.py:260] loss = 50.30002, step = 100 (59.081 sec)\n",
"Corrupt JPEG data: premature end of data segment\n",
"INFO:tensorflow:global_step/sec: 2.85448\n",
"I0326 12:55:51.778176 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.85448\n",
"INFO:tensorflow:loss = 49.457554, step = 200 (35.033 sec)\n",
"I0326 12:55:51.779216 140541047973760 basic_session_run_hooks.py:260] loss = 49.457554, step = 200 (35.033 sec)\n",
"INFO:tensorflow:global_step/sec: 2.83186\n",
"I0326 12:56:27.090658 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.83186\n",
"INFO:tensorflow:loss = 49.062817, step = 300 (35.313 sec)\n",
"I0326 12:56:27.091768 140541047973760 basic_session_run_hooks.py:260] loss = 49.062817, step = 300 (35.313 sec)\n",
"INFO:tensorflow:global_step/sec: 2.85119\n",
"I0326 12:57:02.163691 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.85119\n",
"INFO:tensorflow:loss = 48.28302, step = 400 (35.073 sec)\n",
"I0326 12:57:02.164724 140541047973760 basic_session_run_hooks.py:260] loss = 48.28302, step = 400 (35.073 sec)\n",
"INFO:tensorflow:global_step/sec: 2.8746\n",
"I0326 12:57:36.951155 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.8746\n",
"INFO:tensorflow:loss = 49.690887, step = 500 (34.788 sec)\n",
"I0326 12:57:36.952299 140541047973760 basic_session_run_hooks.py:260] loss = 49.690887, step = 500 (34.788 sec)\n",
"INFO:tensorflow:global_step/sec: 2.87794\n",
"I0326 12:58:11.698275 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.87794\n",
"INFO:tensorflow:loss = 46.701126, step = 600 (34.747 sec)\n",
"I0326 12:58:11.699541 140541047973760 basic_session_run_hooks.py:260] loss = 46.701126, step = 600 (34.747 sec)\n",
"INFO:tensorflow:global_step/sec: 2.88798\n",
"I0326 12:58:46.324640 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.88798\n",
"INFO:tensorflow:loss = 46.240574, step = 700 (34.626 sec)\n",
"I0326 12:58:46.325747 140541047973760 basic_session_run_hooks.py:260] loss = 46.240574, step = 700 (34.626 sec)\n",
"INFO:tensorflow:global_step/sec: 2.85551\n",
"I0326 12:59:21.344581 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.85551\n",
"INFO:tensorflow:loss = 45.345108, step = 800 (35.020 sec)\n",
"I0326 12:59:21.346133 140541047973760 basic_session_run_hooks.py:260] loss = 45.345108, step = 800 (35.020 sec)\n",
"INFO:tensorflow:global_step/sec: 2.89423\n",
"I0326 12:59:55.896104 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.89423\n",
"INFO:tensorflow:loss = 44.308956, step = 900 (34.551 sec)\n",
"I0326 12:59:55.897064 140541047973760 basic_session_run_hooks.py:260] loss = 44.308956, step = 900 (34.551 sec)\n",
"Corrupt JPEG data: premature end of data segment\n",
"Corrupt JPEG data: premature end of data segment\n",
"INFO:tensorflow:global_step/sec: 2.85378\n",
"I0326 13:00:30.937528 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.85378\n",
"INFO:tensorflow:loss = 43.11552, step = 1000 (35.042 sec)\n",
"I0326 13:00:30.938813 140541047973760 basic_session_run_hooks.py:260] loss = 43.11552, step = 1000 (35.042 sec)\n",
"INFO:tensorflow:global_step/sec: 2.88133\n",
"I0326 13:01:05.643435 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.88133\n",
"INFO:tensorflow:loss = 42.79482, step = 1100 (34.706 sec)\n",
"I0326 13:01:05.644313 140541047973760 basic_session_run_hooks.py:260] loss = 42.79482, step = 1100 (34.706 sec)\n",
"INFO:tensorflow:global_step/sec: 2.8925\n",
"I0326 13:01:40.215581 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.8925\n",
"INFO:tensorflow:loss = 41.46504, step = 1200 (34.573 sec)\n",
"I0326 13:01:40.216994 140541047973760 basic_session_run_hooks.py:260] loss = 41.46504, step = 1200 (34.573 sec)\n",
"INFO:tensorflow:global_step/sec: 2.87714\n",
"I0326 13:02:14.972344 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.87714\n",
"INFO:tensorflow:loss = 40.642002, step = 1300 (34.757 sec)\n",
"I0326 13:02:14.973648 140541047973760 basic_session_run_hooks.py:260] loss = 40.642002, step = 1300 (34.757 sec)\n",
"INFO:tensorflow:global_step/sec: 2.92442\n",
"I0326 13:02:49.167197 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.92442\n",
"INFO:tensorflow:loss = 39.68215, step = 1400 (34.195 sec)\n",
"I0326 13:02:49.168452 140541047973760 basic_session_run_hooks.py:260] loss = 39.68215, step = 1400 (34.195 sec)\n",
"INFO:tensorflow:global_step/sec: 2.88702\n",
"I0326 13:03:23.804987 140541047973760 basic_session_run_hooks.py:692] global_step/sec: 2.88702\n",
"INFO:tensorflow:loss = 39.0761, step = 1500 (34.637 sec)\n",
"I0326 13:03:23.805949 140541047973760 basic_session_run_hooks.py:260] loss = 39.0761, step = 1500 (34.637 sec)\n",
"INFO:tensorflow:Saving checkpoints for 1554 into /content/data/train_ssdlite_mobilenet_v3_large_320x320_pet_quant/model.ckpt.\n",
"I0326 13:03:42.388208 140541047973760 basic_session_run_hooks.py:606] Saving checkpoints for 1554 into /content/data/train_ssdlite_mobilenet_v3_large_320x320_pet_quant/model.ckpt.\n",
"INFO:tensorflow:Calling model_fn.\n",
"I0326 13:03:45.596246 140541047973760 estimator.py:1148] Calling model_fn.\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 13:03:47.797970 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 13:03:47.887693 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 13:03:47.961450 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 13:03:48.034571 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 13:03:48.113776 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:depth of additional conv before box predictor: 0\n",
"I0326 13:03:48.188019 140541047973760 convolutional_box_predictor.py:151] depth of additional conv before box predictor: 0\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/Conv/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:49.987735 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/Conv/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 13:03:50.112384 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 13:03:50.179824 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 13:03:50.230767 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.248049 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.265524 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.296381 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.313331 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.330073 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.347207 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.364099 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.381071 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.398221 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.415096 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 13:03:50.443581 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.471651 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.490949 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 13:03:50.519048 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.535744 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.553043 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 13:03:50.581362 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.610728 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.627686 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 13:03:50.660952 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.683765 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.710401 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"I0326 13:03:50.749312 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping FeatureExtractor/MobilenetV3/Conv_1/hard_swish/add, because its followed by an activation.\n",
"I0326 13:03:50.767923 140541047973760 quantize.py:166] Skipping FeatureExtractor/MobilenetV3/Conv_1/hard_swish/add, because its followed by an activation.\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/add\n",
"I0326 13:03:51.503894 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/mul\n",
"I0326 13:03:51.504190 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/mul_1\n",
"I0326 13:03:51.511427 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/add\n",
"I0326 13:03:51.518624 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/mul\n",
"I0326 13:03:51.518771 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/mul\n",
"I0326 13:03:51.525046 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_3/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/add\n",
"I0326 13:03:51.531382 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/mul\n",
"I0326 13:03:51.531512 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/mul\n",
"I0326 13:03:51.537277 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_4/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/add\n",
"I0326 13:03:51.543438 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/mul\n",
"I0326 13:03:51.543587 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/mul\n",
"I0326 13:03:51.549991 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_5/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/add\n",
"I0326 13:03:51.556511 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/mul\n",
"I0326 13:03:51.556667 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/mul_1\n",
"I0326 13:03:51.562924 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/add\n",
"I0326 13:03:51.569037 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/mul\n",
"I0326 13:03:51.569175 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/mul_1\n",
"I0326 13:03:51.574991 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_6/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/add\n",
"I0326 13:03:51.580933 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/mul\n",
"I0326 13:03:51.581068 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/mul_1\n",
"I0326 13:03:51.587148 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/add\n",
"I0326 13:03:51.593025 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/mul\n",
"I0326 13:03:51.593156 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/mul_1\n",
"I0326 13:03:51.599456 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_7/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/add\n",
"I0326 13:03:51.605802 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/mul\n",
"I0326 13:03:51.605971 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/mul_1\n",
"I0326 13:03:51.611707 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/add\n",
"I0326 13:03:51.617595 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/mul\n",
"I0326 13:03:51.617720 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/mul_1\n",
"I0326 13:03:51.623514 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_8/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/add\n",
"I0326 13:03:51.629576 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/mul\n",
"I0326 13:03:51.629701 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/mul_1\n",
"I0326 13:03:51.635436 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/add\n",
"I0326 13:03:51.641324 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/mul\n",
"I0326 13:03:51.641449 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/mul_1\n",
"I0326 13:03:51.647418 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_9/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/add\n",
"I0326 13:03:51.653325 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/mul\n",
"I0326 13:03:51.653451 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/mul_1\n",
"I0326 13:03:51.659275 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/add\n",
"I0326 13:03:51.665311 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/mul\n",
"I0326 13:03:51.665438 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/mul_1\n",
"I0326 13:03:51.671355 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/add\n",
"I0326 13:03:51.677196 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/mul\n",
"I0326 13:03:51.677321 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/mul\n",
"I0326 13:03:51.683049 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_10/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/add\n",
"I0326 13:03:51.690477 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/mul\n",
"I0326 13:03:51.690628 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/mul_1\n",
"I0326 13:03:51.697235 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/add\n",
"I0326 13:03:51.704172 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/mul\n",
"I0326 13:03:51.704336 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/mul_1\n",
"I0326 13:03:51.710099 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/add\n",
"I0326 13:03:51.716210 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/mul\n",
"I0326 13:03:51.716369 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/mul\n",
"I0326 13:03:51.722210 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_11/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/add\n",
"I0326 13:03:51.728561 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/mul\n",
"I0326 13:03:51.728715 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/mul_1\n",
"I0326 13:03:51.734544 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/add\n",
"I0326 13:03:51.740438 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/mul\n",
"I0326 13:03:51.740590 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/mul_1\n",
"I0326 13:03:51.749255 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/add\n",
"I0326 13:03:51.756073 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/mul\n",
"I0326 13:03:51.756245 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/mul\n",
"I0326 13:03:51.763788 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_12/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/add\n",
"I0326 13:03:51.769960 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/mul\n",
"I0326 13:03:51.770114 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/mul_1\n",
"I0326 13:03:51.775867 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/add\n",
"I0326 13:03:51.781850 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/mul\n",
"I0326 13:03:51.782026 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/mul_1\n",
"I0326 13:03:51.789208 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/add\n",
"I0326 13:03:51.795083 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/mul\n",
"I0326 13:03:51.795242 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/mul\n",
"I0326 13:03:51.801879 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_13/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/add\n",
"I0326 13:03:51.810980 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/mul\n",
"I0326 13:03:51.811165 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/mul_1\n",
"I0326 13:03:51.818194 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/expand/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/add\n",
"I0326 13:03:51.824401 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/mul\n",
"I0326 13:03:51.824563 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/mul_1\n",
"I0326 13:03:51.831788 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/depthwise/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/add\n",
"I0326 13:03:51.838604 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/mul\n",
"I0326 13:03:51.838778 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/Conv_1/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/mul\n",
"I0326 13:03:51.844957 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/expanded_conv_14/squeeze_excite/mul\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/add\n",
"I0326 13:03:51.851257 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/add\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/mul\n",
"I0326 13:03:51.851409 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/mul\n",
"INFO:tensorflow:Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/mul_1\n",
"I0326 13:03:51.857419 140541047973760 quantize.py:262] Inserting fake quant op activation_Mul_quant after FeatureExtractor/MobilenetV3/Conv_1/hard_swish/mul_1\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv/depthwise/add_fold\n",
"I0326 13:03:51.877525 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv/depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_1/expand/add_fold\n",
"I0326 13:03:51.877858 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_1/expand/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_1/depthwise/add_fold\n",
"I0326 13:03:51.878072 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_1/depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_2/expand/add_fold\n",
"I0326 13:03:51.878337 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_2/expand/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_2/depthwise/add_fold\n",
"I0326 13:03:51.878518 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_2/depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_3/expand/add_fold\n",
"I0326 13:03:51.878777 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_3/expand/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_3/depthwise/add_fold\n",
"I0326 13:03:51.878970 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_3/depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_4/expand/add_fold\n",
"I0326 13:03:51.879239 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_4/expand/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_4/depthwise/add_fold\n",
"I0326 13:03:51.879421 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_4/depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_5/expand/add_fold\n",
"I0326 13:03:51.879674 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_5/expand/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_5/depthwise/add_fold\n",
"I0326 13:03:51.879850 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/expanded_conv_5/depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_1_Conv2d_2_1x1_256/add_fold\n",
"I0326 13:03:51.882462 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_1_Conv2d_2_1x1_256/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_2_3x3_s2_512_depthwise/add_fold\n",
"I0326 13:03:51.882678 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_2_3x3_s2_512_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_2_3x3_s2_512/add_fold\n",
"I0326 13:03:51.882910 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_2_3x3_s2_512/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_1_Conv2d_3_1x1_128/add_fold\n",
"I0326 13:03:51.883119 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_1_Conv2d_3_1x1_128/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_3_3x3_s2_256_depthwise/add_fold\n",
"I0326 13:03:51.883322 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_3_3x3_s2_256_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_3_3x3_s2_256/add_fold\n",
"I0326 13:03:51.883514 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_3_3x3_s2_256/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_1_Conv2d_4_1x1_128/add_fold\n",
"I0326 13:03:51.883707 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_1_Conv2d_4_1x1_128/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_4_3x3_s2_256_depthwise/add_fold\n",
"I0326 13:03:51.883926 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_4_3x3_s2_256_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_4_3x3_s2_256/add_fold\n",
"I0326 13:03:51.884132 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_4_3x3_s2_256/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_1_Conv2d_5_1x1_64/add_fold\n",
"I0326 13:03:51.884313 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_1_Conv2d_5_1x1_64/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_5_3x3_s2_128_depthwise/add_fold\n",
"I0326 13:03:51.884499 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_5_3x3_s2_128_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_5_3x3_s2_128/add_fold\n",
"I0326 13:03:51.884678 140541047973760 quantize.py:299] Skipping quant after FeatureExtractor/MobilenetV3/layer_17_2_Conv2d_5_3x3_s2_128/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_0/BoxEncodingPredictor_depthwise/add_fold\n",
"I0326 13:03:51.884868 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_0/BoxEncodingPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_0/ClassPredictor_depthwise/add_fold\n",
"I0326 13:03:51.885078 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_0/ClassPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_1/BoxEncodingPredictor_depthwise/add_fold\n",
"I0326 13:03:51.885269 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_1/BoxEncodingPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_1/ClassPredictor_depthwise/add_fold\n",
"I0326 13:03:51.885458 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_1/ClassPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_2/BoxEncodingPredictor_depthwise/add_fold\n",
"I0326 13:03:51.885650 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_2/BoxEncodingPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_2/ClassPredictor_depthwise/add_fold\n",
"I0326 13:03:51.885829 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_2/ClassPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_3/BoxEncodingPredictor_depthwise/add_fold\n",
"I0326 13:03:51.886022 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_3/BoxEncodingPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_3/ClassPredictor_depthwise/add_fold\n",
"I0326 13:03:51.886205 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_3/ClassPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_4/BoxEncodingPredictor_depthwise/add_fold\n",
"I0326 13:03:51.886386 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_4/BoxEncodingPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_4/ClassPredictor_depthwise/add_fold\n",
"I0326 13:03:51.886562 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_4/ClassPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_5/BoxEncodingPredictor_depthwise/add_fold\n",
"I0326 13:03:51.886741 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_5/BoxEncodingPredictor_depthwise/add_fold\n",
"INFO:tensorflow:Skipping quant after BoxPredictor_5/ClassPredictor_depthwise/add_fold\n",
"I0326 13:03:51.886931 140541047973760 quantize.py:299] Skipping quant after BoxPredictor_5/ClassPredictor_depthwise/add_fold\n",
"WARNING:tensorflow:From /content/models/research/object_detection/eval_util.py:796: to_int64 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.cast` instead.\n",
"W0326 13:03:51.911580 140541047973760 deprecation.py:323] From /content/models/research/object_detection/eval_util.py:796: to_int64 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Use `tf.cast` instead.\n",
"WARNING:tensorflow:From /content/models/research/object_detection/utils/visualization_utils.py:498: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"tf.py_func is deprecated in TF V2. Instead, there are two\n",
" options available in V2.\n",
" - tf.py_function takes a python function which manipulates tf eager\n",
" tensors instead of numpy arrays. It's easy to convert a tf eager tensor to\n",
" an ndarray (just call tensor.numpy()) but having access to eager tensors\n",
" means `tf.py_function`s can use accelerators such as GPUs as well as\n",
" being differentiable using a gradient tape.\n",
" - tf.numpy_function maintains the semantics of the deprecated tf.py_func\n",
" (it is not differentiable, and manipulates numpy arrays). It drops the\n",
" stateful argument making all functions stateful.\n",
" \n",
"W0326 13:03:52.095837 140541047973760 deprecation.py:323] From /content/models/research/object_detection/utils/visualization_utils.py:498: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"tf.py_func is deprecated in TF V2. Instead, there are two\n",
" options available in V2.\n",
" - tf.py_function takes a python function which manipulates tf eager\n",
" tensors instead of numpy arrays. It's easy to convert a tf eager tensor to\n",
" an ndarray (just call tensor.numpy()) but having access to eager tensors\n",
" means `tf.py_function`s can use accelerators such as GPUs as well as\n",
" being differentiable using a gradient tape.\n",
" - tf.numpy_function maintains the semantics of the deprecated tf.py_func\n",
" (it is not differentiable, and manipulates numpy arrays). It drops the\n",
" stateful argument making all functions stateful.\n",
" \n",
"WARNING:tensorflow:From /content/models/research/object_detection/utils/visualization_utils.py:1044: The name tf.summary.image is deprecated. Please use tf.compat.v1.summary.image instead.\n",
"\n",
"W0326 13:03:52.235122 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/utils/visualization_utils.py:1044: The name tf.summary.image is deprecated. Please use tf.compat.v1.summary.image instead.\n",
"\n",
"WARNING:tensorflow:From /content/models/research/object_detection/model_lib.py:484: The name tf.metrics.mean is deprecated. Please use tf.compat.v1.metrics.mean instead.\n",
"\n",
"W0326 13:03:52.312635 140541047973760 module_wrapper.py:139] From /content/models/research/object_detection/model_lib.py:484: The name tf.metrics.mean is deprecated. Please use tf.compat.v1.metrics.mean instead.\n",
"\n",
"INFO:tensorflow:Done calling model_fn.\n",
"I0326 13:03:53.057369 140541047973760 estimator.py:1150] Done calling model_fn.\n",
"INFO:tensorflow:Starting evaluation at 2020-03-26T13:03:53Z\n",
"I0326 13:03:53.072892 140541047973760 evaluation.py:255] Starting evaluation at 2020-03-26T13:03:53Z\n",
"INFO:tensorflow:Graph was finalized.\n",
"I0326 13:03:54.177124 140541047973760 monitored_session.py:240] Graph was finalized.\n",
"2020-03-26 13:03:54.178279: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 13:03:54.178768: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: \n",
"name: Tesla T4 major: 7 minor: 5 memoryClockRate(GHz): 1.59\n",
"pciBusID: 0000:00:04.0\n",
"2020-03-26 13:03:54.178879: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1\n",
"2020-03-26 13:03:54.178933: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10\n",
"2020-03-26 13:03:54.178964: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10\n",
"2020-03-26 13:03:54.178989: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10\n",
"2020-03-26 13:03:54.179019: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10\n",
"2020-03-26 13:03:54.179044: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10\n",
"2020-03-26 13:03:54.179068: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7\n",
"2020-03-26 13:03:54.179156: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 13:03:54.179631: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 13:03:54.180061: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1746] Adding visible gpu devices: 0\n",
"2020-03-26 13:03:54.180119: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix:\n",
"2020-03-26 13:03:54.180136: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] 0 \n",
"2020-03-26 13:03:54.180149: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1178] 0: N \n",
"2020-03-26 13:03:54.180260: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 13:03:54.180713: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:983] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
"2020-03-26 13:03:54.181150: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1304] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14221 MB memory) -> physical GPU (device: 0, name: Tesla T4, pci bus id: 0000:00:04.0, compute capability: 7.5)\n",
"INFO:tensorflow:Restoring parameters from /content/data/train_ssdlite_mobilenet_v3_large_320x320_pet_quant/model.ckpt-1554\n",
"I0326 13:03:54.182206 140541047973760 saver.py:1284] Restoring parameters from /content/data/train_ssdlite_mobilenet_v3_large_320x320_pet_quant/model.ckpt-1554\n",
"2020-03-26 13:03:55.497317: W tensorflow/core/framework/op_kernel.cc:1651] OP_REQUIRES failed at save_restore_v2_ops.cc:184 : Not found: Key FeatureExtractor/MobilenetV3/Conv/conv_quant/max not found in checkpoint\n",
"Traceback (most recent call last):\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/client/session.py\", line 1365, in _do_call\n",
" return fn(*args)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/client/session.py\", line 1350, in _run_fn\n",
" target_list, run_metadata)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/client/session.py\", line 1443, in _call_tf_sessionrun\n",
" run_metadata)\n",
"tensorflow.python.framework.errors_impl.NotFoundError: 2 root error(s) found.\n",
" (0) Not found: Key FeatureExtractor/MobilenetV3/Conv/conv_quant/max not found in checkpoint\n",
"\t [[{{node save/RestoreV2}}]]\n",
" (1) Not found: Key FeatureExtractor/MobilenetV3/Conv/conv_quant/max not found in checkpoint\n",
"\t [[{{node save/RestoreV2}}]]\n",
"\t [[save/RestoreV2/_301]]\n",
"0 successful operations.\n",
"0 derived errors ignored.\n",
"\n",
"During handling of the above exception, another exception occurred:\n",
"\n",
"Traceback (most recent call last):\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 1290, in restore\n",
" {self.saver_def.filename_tensor_name: save_path})\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/client/session.py\", line 956, in run\n",
" run_metadata_ptr)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/client/session.py\", line 1180, in _run\n",
" feed_dict_tensor, options, run_metadata)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/client/session.py\", line 1359, in _do_run\n",
" run_metadata)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/client/session.py\", line 1384, in _do_call\n",
" raise type(e)(node_def, op, message)\n",
"tensorflow.python.framework.errors_impl.NotFoundError: 2 root error(s) found.\n",
" (0) Not found: Key FeatureExtractor/MobilenetV3/Conv/conv_quant/max not found in checkpoint\n",
"\t [[node save/RestoreV2 (defined at /tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py:1748) ]]\n",
" (1) Not found: Key FeatureExtractor/MobilenetV3/Conv/conv_quant/max not found in checkpoint\n",
"\t [[node save/RestoreV2 (defined at /tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py:1748) ]]\n",
"\t [[save/RestoreV2/_301]]\n",
"0 successful operations.\n",
"0 derived errors ignored.\n",
"\n",
"Original stack trace for 'save/RestoreV2':\n",
" File \"./object_detection/model_main.py\", line 109, in <module>\n",
" tf.app.run()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/platform/app.py\", line 40, in run\n",
" _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)\n",
" File \"/usr/local/lib/python3.6/dist-packages/absl/app.py\", line 299, in run\n",
" _run_main(main, args)\n",
" File \"/usr/local/lib/python3.6/dist-packages/absl/app.py\", line 250, in _run_main\n",
" sys.exit(main(argv))\n",
" File \"./object_detection/model_main.py\", line 105, in main\n",
" tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0])\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 473, in train_and_evaluate\n",
" return executor.run()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 613, in run\n",
" return self.run_local()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 714, in run_local\n",
" saving_listeners=saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 370, in train\n",
" loss = self._train_model(input_fn, hooks, saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1161, in _train_model\n",
" return self._train_model_default(input_fn, hooks, saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1195, in _train_model_default\n",
" saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1494, in _train_with_estimator_spec\n",
" _, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 754, in run\n",
" run_metadata=run_metadata)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1259, in run\n",
" run_metadata=run_metadata)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1345, in run\n",
" return self._sess.run(*args, **kwargs)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1426, in run\n",
" run_metadata=run_metadata))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/basic_session_run_hooks.py\", line 594, in after_run\n",
" if self._save(run_context.session, global_step):\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/basic_session_run_hooks.py\", line 619, in _save\n",
" if l.after_save(session, step):\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 519, in after_save\n",
" self._evaluate(global_step_value) # updates self.eval_result\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 539, in _evaluate\n",
" self._evaluator.evaluate_and_export())\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 920, in evaluate_and_export\n",
" hooks=self._eval_spec.hooks)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 480, in evaluate\n",
" name=name)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 522, in _actual_eval\n",
" return _evaluate()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 504, in _evaluate\n",
" self._evaluate_build_graph(input_fn, hooks, checkpoint_path))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1511, in _evaluate_build_graph\n",
" self._call_model_fn_eval(input_fn, self.config))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1547, in _call_model_fn_eval\n",
" features, labels, ModeKeys.EVAL, config)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1149, in _call_model_fn\n",
" model_fn_results = self._model_fn(features=features, **kwargs)\n",
" File \"/content/models/research/object_detection/model_lib.py\", line 518, in model_fn\n",
" save_relative_paths=True)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 828, in __init__\n",
" self.build()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 840, in build\n",
" self._build(self._filename, build_save=True, build_restore=True)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 878, in _build\n",
" build_restore=build_restore)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 502, in _build_internal\n",
" restore_sequentially, reshape)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 381, in _AddShardedRestoreOps\n",
" name=\"restore_shard\"))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 328, in _AddRestoreOps\n",
" restore_sequentially)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 575, in bulk_restore\n",
" return io_ops.restore_v2(filename_tensor, names, slices, dtypes)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/ops/gen_io_ops.py\", line 1696, in restore_v2\n",
" name=name)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/op_def_library.py\", line 794, in _apply_op_helper\n",
" op_def=op_def)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/util/deprecation.py\", line 507, in new_func\n",
" return func(*args, **kwargs)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py\", line 3357, in create_op\n",
" attrs, op_def, compute_device)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py\", line 3426, in _create_op_internal\n",
" op_def=op_def)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py\", line 1748, in __init__\n",
" self._traceback = tf_stack.extract_stack()\n",
"\n",
"\n",
"During handling of the above exception, another exception occurred:\n",
"\n",
"Traceback (most recent call last):\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 1300, in restore\n",
" names_to_keys = object_graph_key_mapping(save_path)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 1618, in object_graph_key_mapping\n",
" object_graph_string = reader.get_tensor(trackable.OBJECT_GRAPH_PROTO_KEY)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/pywrap_tensorflow_internal.py\", line 915, in get_tensor\n",
" return CheckpointReader_GetTensor(self, compat.as_bytes(tensor_str))\n",
"tensorflow.python.framework.errors_impl.NotFoundError: Key _CHECKPOINTABLE_OBJECT_GRAPH not found in checkpoint\n",
"\n",
"During handling of the above exception, another exception occurred:\n",
"\n",
"Traceback (most recent call last):\n",
" File \"./object_detection/model_main.py\", line 109, in <module>\n",
" tf.app.run()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/platform/app.py\", line 40, in run\n",
" _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)\n",
" File \"/usr/local/lib/python3.6/dist-packages/absl/app.py\", line 299, in run\n",
" _run_main(main, args)\n",
" File \"/usr/local/lib/python3.6/dist-packages/absl/app.py\", line 250, in _run_main\n",
" sys.exit(main(argv))\n",
" File \"./object_detection/model_main.py\", line 105, in main\n",
" tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0])\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 473, in train_and_evaluate\n",
" return executor.run()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 613, in run\n",
" return self.run_local()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 714, in run_local\n",
" saving_listeners=saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 370, in train\n",
" loss = self._train_model(input_fn, hooks, saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1161, in _train_model\n",
" return self._train_model_default(input_fn, hooks, saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1195, in _train_model_default\n",
" saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1494, in _train_with_estimator_spec\n",
" _, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 754, in run\n",
" run_metadata=run_metadata)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1259, in run\n",
" run_metadata=run_metadata)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1360, in run\n",
" raise six.reraise(*original_exc_info)\n",
" File \"/usr/local/lib/python3.6/dist-packages/six.py\", line 693, in reraise\n",
" raise value\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1345, in run\n",
" return self._sess.run(*args, **kwargs)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1426, in run\n",
" run_metadata=run_metadata))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/basic_session_run_hooks.py\", line 594, in after_run\n",
" if self._save(run_context.session, global_step):\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/basic_session_run_hooks.py\", line 619, in _save\n",
" if l.after_save(session, step):\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 519, in after_save\n",
" self._evaluate(global_step_value) # updates self.eval_result\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 539, in _evaluate\n",
" self._evaluator.evaluate_and_export())\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 920, in evaluate_and_export\n",
" hooks=self._eval_spec.hooks)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 480, in evaluate\n",
" name=name)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 522, in _actual_eval\n",
" return _evaluate()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 511, in _evaluate\n",
" output_dir=self.eval_dir(name))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1619, in _evaluate_run\n",
" config=self._session_config)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/evaluation.py\", line 269, in _evaluate_once\n",
" session_creator=session_creator, hooks=hooks) as session:\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1014, in __init__\n",
" stop_grace_period_secs=stop_grace_period_secs)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 725, in __init__\n",
" self._sess = _RecoverableSession(self._coordinated_creator)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1207, in __init__\n",
" _WrappedSession.__init__(self, self._create_session())\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1212, in _create_session\n",
" return self._sess_creator.create_session()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 878, in create_session\n",
" self.tf_sess = self._session_creator.create_session()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 647, in create_session\n",
" init_fn=self._scaffold.init_fn)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/session_manager.py\", line 290, in prepare_session\n",
" config=config)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/session_manager.py\", line 204, in _restore_checkpoint\n",
" saver.restore(sess, checkpoint_filename_with_path)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 1306, in restore\n",
" err, \"a Variable name or other graph key that is missing\")\n",
"tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:\n",
"\n",
"2 root error(s) found.\n",
" (0) Not found: Key FeatureExtractor/MobilenetV3/Conv/conv_quant/max not found in checkpoint\n",
"\t [[node save/RestoreV2 (defined at /tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py:1748) ]]\n",
" (1) Not found: Key FeatureExtractor/MobilenetV3/Conv/conv_quant/max not found in checkpoint\n",
"\t [[node save/RestoreV2 (defined at /tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py:1748) ]]\n",
"\t [[save/RestoreV2/_301]]\n",
"0 successful operations.\n",
"0 derived errors ignored.\n",
"\n",
"Original stack trace for 'save/RestoreV2':\n",
" File \"./object_detection/model_main.py\", line 109, in <module>\n",
" tf.app.run()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/platform/app.py\", line 40, in run\n",
" _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)\n",
" File \"/usr/local/lib/python3.6/dist-packages/absl/app.py\", line 299, in run\n",
" _run_main(main, args)\n",
" File \"/usr/local/lib/python3.6/dist-packages/absl/app.py\", line 250, in _run_main\n",
" sys.exit(main(argv))\n",
" File \"./object_detection/model_main.py\", line 105, in main\n",
" tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0])\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 473, in train_and_evaluate\n",
" return executor.run()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 613, in run\n",
" return self.run_local()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 714, in run_local\n",
" saving_listeners=saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 370, in train\n",
" loss = self._train_model(input_fn, hooks, saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1161, in _train_model\n",
" return self._train_model_default(input_fn, hooks, saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1195, in _train_model_default\n",
" saving_listeners)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1494, in _train_with_estimator_spec\n",
" _, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 754, in run\n",
" run_metadata=run_metadata)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1259, in run\n",
" run_metadata=run_metadata)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1345, in run\n",
" return self._sess.run(*args, **kwargs)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/monitored_session.py\", line 1426, in run\n",
" run_metadata=run_metadata))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/basic_session_run_hooks.py\", line 594, in after_run\n",
" if self._save(run_context.session, global_step):\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/basic_session_run_hooks.py\", line 619, in _save\n",
" if l.after_save(session, step):\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 519, in after_save\n",
" self._evaluate(global_step_value) # updates self.eval_result\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 539, in _evaluate\n",
" self._evaluator.evaluate_and_export())\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/training.py\", line 920, in evaluate_and_export\n",
" hooks=self._eval_spec.hooks)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 480, in evaluate\n",
" name=name)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 522, in _actual_eval\n",
" return _evaluate()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 504, in _evaluate\n",
" self._evaluate_build_graph(input_fn, hooks, checkpoint_path))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1511, in _evaluate_build_graph\n",
" self._call_model_fn_eval(input_fn, self.config))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1547, in _call_model_fn_eval\n",
" features, labels, ModeKeys.EVAL, config)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_estimator/python/estimator/estimator.py\", line 1149, in _call_model_fn\n",
" model_fn_results = self._model_fn(features=features, **kwargs)\n",
" File \"/content/models/research/object_detection/model_lib.py\", line 518, in model_fn\n",
" save_relative_paths=True)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 828, in __init__\n",
" self.build()\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 840, in build\n",
" self._build(self._filename, build_save=True, build_restore=True)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 878, in _build\n",
" build_restore=build_restore)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 502, in _build_internal\n",
" restore_sequentially, reshape)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 381, in _AddShardedRestoreOps\n",
" name=\"restore_shard\"))\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 328, in _AddRestoreOps\n",
" restore_sequentially)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/training/saver.py\", line 575, in bulk_restore\n",
" return io_ops.restore_v2(filename_tensor, names, slices, dtypes)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/ops/gen_io_ops.py\", line 1696, in restore_v2\n",
" name=name)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/op_def_library.py\", line 794, in _apply_op_helper\n",
" op_def=op_def)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/util/deprecation.py\", line 507, in new_func\n",
" return func(*args, **kwargs)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py\", line 3357, in create_op\n",
" attrs, op_def, compute_device)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py\", line 3426, in _create_op_internal\n",
" op_def=op_def)\n",
" File \"/tensorflow-1.15.0/python3.6/tensorflow_core/python/framework/ops.py\", line 1748, in __init__\n",
" self._traceback = tf_stack.extract_stack()\n",
"\n"
],
"name": "stdout"
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment