Skip to content

Instantly share code, notes, and snippets.

@AvantiShri

AvantiShri/eoinkennymodelloadtest.ipynb Secret

Created January 11, 2019 17:21
Show Gist options
  • Save AvantiShri/e77ace62219846746537f88ce50388d2 to your computer and use it in GitHub Desktop.
Save AvantiShri/e77ace62219846746537f88ce50388d2 to your computer and use it in GitHub Desktop.
Download ZIP
EoinKennyModelLoadTest.ipynb
Display the source blob
Display the rendered blob
Raw
eoinkennymodelloadtest.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "EoinKennyModelLoadTest.ipynb",
"version": "0.3.2",
"provenance": [],
"collapsed_sections": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/AvantiShri/e77ace62219846746537f88ce50388d2/eoinkennymodelloadtest.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"metadata": {
"id": "naSX9st37JMS",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 173
},
"outputId": "91a3d4b0-cc81-408f-bddd-0afe86b8d0a4"
},
"cell_type": "code",
"source": [
"!pip install deeplift"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"text": [
"Collecting deeplift\n",
" Downloading https://files.pythonhosted.org/packages/54/23/938b1c8cdfaf2babc5b87f1c37099644d312e10e98a283f33dd88c4ce557/deeplift-0.6.8.1.tar.gz\n",
"Requirement already satisfied: numpy>=1.9 in /usr/local/lib/python3.6/dist-packages (from deeplift) (1.14.6)\n",
"Building wheels for collected packages: deeplift\n",
" Running setup.py bdist_wheel for deeplift ... \u001b[?25l-\b \bdone\n",
"\u001b[?25h Stored in directory: /root/.cache/pip/wheels/c0/32/2d/141e8cc6b98bc392a6a41025672b57e623c4a49cdb96c8ca47\n",
"Successfully built deeplift\n",
"Installing collected packages: deeplift\n",
"Successfully installed deeplift-0.6.8.1\n"
],
"name": "stdout"
}
]
},
{
"metadata": {
"id": "HFA8AqfD7RI6",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 314
},
"outputId": "2facae7d-4186-4114-973d-ea71e4052a6c"
},
"cell_type": "code",
"source": [
"!wget https://github.com/kundajelab/deeplift/files/2750526/NN.h5.zip"
],
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"text": [
"--2019-01-11 17:19:44-- https://github.com/kundajelab/deeplift/files/2750526/NN.h5.zip\n",
"Resolving github.com (github.com)... 192.30.255.112, 192.30.255.113\n",
"Connecting to github.com (github.com)|192.30.255.112|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://github-production-repository-file-5c1aeb.s3.amazonaws.com/60138482/2750526?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAIWNJYAX4CSVEH53A%2F20190111%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20190111T171944Z&X-Amz-Expires=300&X-Amz-Signature=c84b8f7ef134f72ce3379e8578153282c1d7d359c9aac3d07c1e306b0bfd5bec&X-Amz-SignedHeaders=host&actor_id=0&response-content-disposition=attachment%3Bfilename%3DNN.h5.zip&response-content-type=application%2Fzip [following]\n",
"--2019-01-11 17:19:44-- https://github-production-repository-file-5c1aeb.s3.amazonaws.com/60138482/2750526?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAIWNJYAX4CSVEH53A%2F20190111%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20190111T171944Z&X-Amz-Expires=300&X-Amz-Signature=c84b8f7ef134f72ce3379e8578153282c1d7d359c9aac3d07c1e306b0bfd5bec&X-Amz-SignedHeaders=host&actor_id=0&response-content-disposition=attachment%3Bfilename%3DNN.h5.zip&response-content-type=application%2Fzip\n",
"Resolving github-production-repository-file-5c1aeb.s3.amazonaws.com (github-production-repository-file-5c1aeb.s3.amazonaws.com)... 52.216.169.67\n",
"Connecting to github-production-repository-file-5c1aeb.s3.amazonaws.com (github-production-repository-file-5c1aeb.s3.amazonaws.com)|52.216.169.67|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 3893268 (3.7M) [application/zip]\n",
"Saving to: ‘NN.h5.zip’\n",
"\n",
"NN.h5.zip 100%[===================>] 3.71M 7.21MB/s in 0.5s \n",
"\n",
"2019-01-11 17:19:45 (7.21 MB/s) - ‘NN.h5.zip’ saved [3893268/3893268]\n",
"\n"
],
"name": "stdout"
}
]
},
{
"metadata": {
"id": "tD7gKJU17TnT",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 52
},
"outputId": "6ec7858c-5cad-450a-dbb5-50d9ce1798ab"
},
"cell_type": "code",
"source": [
"!unzip NN.h5.zip"
],
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"text": [
"Archive: NN.h5.zip\n",
" inflating: NN.h5 \n"
],
"name": "stdout"
}
]
},
{
"metadata": {
"id": "3IgaFZiJ7Ww6",
"colab_type": "code",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 312
},
"outputId": "75d5219b-2b58-47ef-85ac-36f12310e9a2"
},
"cell_type": "code",
"source": [
"from deeplift.conversion import kerasapi_conversion as kc\n",
"kc.convert_model_from_saved_files(\"NN.h5\")"
],
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"text": [
"nonlinear_mxts_mode is set to: DeepLIFT_GenomicsDefault\n",
"For layer 1 the preceding linear layer is 0 of type Conv2D;\n",
"In accordance with nonlinear_mxts_mode=DeepLIFT_GenomicsDefault we are setting the NonlinearMxtsMode to Rescale\n",
"Heads-up: current implementation assumes maxpool layer is followed by a linear transformation (conv/dense layer)\n",
"For layer 5 the preceding linear layer is 4 of type Conv2D;\n",
"In accordance with nonlinear_mxts_mode=DeepLIFT_GenomicsDefault we are setting the NonlinearMxtsMode to Rescale\n",
"Heads-up: current implementation assumes maxpool layer is followed by a linear transformation (conv/dense layer)\n",
"For layer 9 the preceding linear layer is 8 of type Conv2D;\n",
"In accordance with nonlinear_mxts_mode=DeepLIFT_GenomicsDefault we are setting the NonlinearMxtsMode to Rescale\n",
"For layer 13 the preceding linear layer is 12 of type Dense;\n",
"In accordance with nonlinear_mxts_modeDeepLIFT_GenomicsDefault we are setting the NonlinearMxtsMode to RevealCancel\n",
"For layer 16 the preceding linear layer is 15 of type Dense;\n",
"In accordance with nonlinear_mxts_modeDeepLIFT_GenomicsDefault we are setting the NonlinearMxtsMode to RevealCancel\n",
"Heads-up: I assume softmax is the output layer, not an intermediate one; if it's an intermediate layer, please let me know and I will prioritise that use-case\n",
"For layer 19 the preceding linear layer is 18 of type Dense;\n",
"In accordance with nonlinear_mxts_modeDeepLIFT_GenomicsDefault we are setting the NonlinearMxtsMode to RevealCancel\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<deeplift.models.SequentialModel at 0x7fad34026da0>"
]
},
"metadata": {
"tags": []
},
"execution_count": 5
}
]
},
{
"metadata": {
"id": "u7AN2tj27eQB",
"colab_type": "code",
"colab": {}
},
"cell_type": "code",
"source": [
""
],
"execution_count": 0,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment