Skip to content

Instantly share code, notes, and snippets.

@tve

tve/model-maker-object-detection-tutorial.ipynb

Created July 26, 2021 19:13
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save tve/615f4b51fa88dc643358176c86d6537e to your computer and use it in GitHub Desktop.
Save tve/615f4b51fa88dc643358176c86d6537e to your computer and use it in GitHub Desktop.
Download ZIP
Model Maker Object Detection Tutorial
Display the source blob
Display the rendered blob
Raw
model-maker-object-detection-tutorial.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"accelerator": "TPU",
"colab": {
"name": "Model Maker Object Detection Tutorial",
"provenance": [],
"collapsed_sections": [],
"include_colab_link": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/tve/615f4b51fa88dc643358176c86d6537e/model-maker-object-detection-tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "h2q27gKz1H20"
},
"source": [
"##### Copyright 2021 The TensorFlow Authors."
]
},
{
"cell_type": "code",
"metadata": {
"cellView": "form",
"id": "TUfAcER1oUS6"
},
"source": [
"#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n",
"# you may not use this file except in compliance with the License.\n",
"# You may obtain a copy of the License at\n",
"#\n",
"# https://www.apache.org/licenses/LICENSE-2.0\n",
"#\n",
"# Unless required by applicable law or agreed to in writing, software\n",
"# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
"# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
"# See the License for the specific language governing permissions and\n",
"# limitations under the License."
],
"execution_count": 1,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "Gb7qyhNL1yWt"
},
"source": [
"# Object Detection with TensorFlow Lite Model Maker"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Fw5Y7snSuG51"
},
"source": [
"<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://www.tensorflow.org/lite/tutorials/model_maker_object_detection\"><img src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" />View on TensorFlow.org</a>\n",
" </td>\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/g3doc/tutorials/model_maker_object_detection.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
" </td>\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/g3doc/tutorials/model_maker_object_detection.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
" </td>\n",
" <td>\n",
" <a href=\"https://storage.googleapis.com/tensorflow_docs/tensorflow/tensorflow/lite/g3doc/tutorials/model_maker_object_detection.ipynb\"><img src=\"https://www.tensorflow.org/images/download_logo_32px.png\" />Download notebook</a>\n",
" </td>\n",
"</table>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "sr3q-gvm3cI8"
},
"source": [
"In this colab notebook, you'll learn how to use the [TensorFlow Lite Model Maker](https://www.tensorflow.org/lite/guide/model_maker) library to train a custom object detection model capable of detecting salads within images on a mobile device.\n",
"\n",
"The Model Maker library uses *transfer learning* to simplify the process of training a TensorFlow Lite model using a custom dataset. Retraining a TensorFlow Lite model with your own custom dataset reduces the amount of training data required and will shorten the training time.\n",
"\n",
"You'll use the publicly available *Salads* dataset, which was created from the [Open Images Dataset V4](https://storage.googleapis.com/openimages/web/index.html).\n",
"\n",
"Each image in the dataset \bcontains objects labeled as one of the following classes:\n",
"* Baked Good\n",
"* Cheese\n",
"* Salad\n",
"* Seafood\n",
"* Tomato\n",
"\n",
"The dataset contains the bounding-boxes specifying where each object locates, together with the object's label.\n",
"\n",
"Here is an example image from the dataset:\n",
"\n",
"<br/>\n",
"\n",
"<img src=\"https://cloud.google.com/vision/automl/object-detection/docs/images/quickstart-preparing_a_dataset.png\" width=\"400\" hspace=\"0\">\n",
"\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "bcLF2PKkSbV3"
},
"source": [
"## Prerequisites\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "2vvAObmTqglq"
},
"source": [
"### Install the required packages\n",
"Start by installing the required packages, including the Model Maker package from the [GitHub repo](https://github.com/tensorflow/examples/tree/master/tensorflow_examples/lite/model_maker) and the pycocotools library you'll use for evaluation."
]
},
{
"cell_type": "code",
"metadata": {
"id": "qhl8lqVamEty",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "7fcd92c4-eff4-4c89-f49e-10005d11347f"
},
"source": [
"!pip install -q tflite-model-maker\n",
"!pip install -q pycocotools"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"text": [
"\u001b[K |████████████████████████████████| 591 kB 5.5 MB/s \n",
"\u001b[K |████████████████████████████████| 211 kB 9.7 MB/s \n",
"\u001b[K |████████████████████████████████| 6.3 MB 10.7 MB/s \n",
"\u001b[K |████████████████████████████████| 103 kB 54.4 MB/s \n",
"\u001b[K |████████████████████████████████| 1.2 MB 41.8 MB/s \n",
"\u001b[K |████████████████████████████████| 840 kB 52.8 MB/s \n",
"\u001b[K |████████████████████████████████| 87 kB 5.9 MB/s \n",
"\u001b[K |████████████████████████████████| 636 kB 53.5 MB/s \n",
"\u001b[K |████████████████████████████████| 64 kB 2.3 MB/s \n",
"\u001b[K |████████████████████████████████| 120 kB 56.9 MB/s \n",
"\u001b[K |████████████████████████████████| 679 kB 46.6 MB/s \n",
"\u001b[K |████████████████████████████████| 1.1 MB 42.4 MB/s \n",
"\u001b[K |████████████████████████████████| 37.1 MB 1.1 MB/s \n",
"\u001b[K |████████████████████████████████| 99 kB 7.7 MB/s \n",
"\u001b[K |████████████████████████████████| 352 kB 52.2 MB/s \n",
"\u001b[K |████████████████████████████████| 199 kB 54.2 MB/s \n",
"\u001b[?25h Building wheel for fire (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Building wheel for py-cpuinfo (setup.py) ... \u001b[?25l\u001b[?25hdone\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "l6lRhVK9Q_0U"
},
"source": [
"Import the required packages."
]
},
{
"cell_type": "code",
"metadata": {
"id": "XtxiUeZEiXpt"
},
"source": [
"import numpy as np\n",
"import os\n",
"\n",
"from tflite_model_maker.config import ExportFormat\n",
"from tflite_model_maker import model_spec\n",
"from tflite_model_maker import object_detector\n",
"\n",
"import tensorflow as tf\n",
"assert tf.__version__.startswith('2')\n",
"\n",
"tf.get_logger().setLevel('ERROR')\n",
"from absl import logging\n",
"logging.set_verbosity(logging.ERROR)"
],
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "b0Daxa1CHc0P"
},
"source": [
"tpu = tf.distribute.cluster_resolver.TPUClusterResolver()"
],
"execution_count": 3,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "BRd13bfetO7B"
},
"source": [
"### Prepare the dataset\n",
"\n",
"Here you'll use the same dataset as the AutoML [quickstart](https://cloud.google.com/vision/automl/object-detection/docs/edge-quickstart#preparing_a_dataset).\n",
"\n",
"The *Salads* dataset is available at:\n",
" `gs://cloud-ml-data/img/openimage/csv/salads_ml_use.csv`.\n",
"\n",
"It contains 175 images for training, 25 images for validation, and 25 images for testing. The dataset has five classes: `Salad`, `Seafood`, `Tomato`, `Baked goods`, `Cheese`.\n",
"\n",
"<br/>\n",
"\n",
"The dataset is provided in CSV format:\n",
"```\n",
"TRAINING,gs://cloud-ml-data/img/openimage/3/2520/3916261642_0a504acd60_o.jpg,Salad,0.0,0.0954,,,0.977,0.957,,\n",
"VALIDATION,gs://cloud-ml-data/img/openimage/3/2520/3916261642_0a504acd60_o.jpg,Seafood,0.0154,0.1538,,,1.0,0.802,,\n",
"TEST,gs://cloud-ml-data/img/openimage/3/2520/3916261642_0a504acd60_o.jpg,Tomato,0.0,0.655,,,0.231,0.839,,\n",
"```\n",
"\n",
"* Each row corresponds to an object localized inside a larger image, with each object specifically designated as test, train, or validation data. You'll learn more about what that means in a later stage in this notebook.\n",
"* The three lines included here indicate **three distinct objects located inside the same image** available at `gs://cloud-ml-data/img/openimage/3/2520/3916261642_0a504acd60_o.jpg`.\n",
"* Each row has a different label: `Salad`, `Seafood`, `Tomato`, etc.\n",
"* Bounding boxes are specified for each image using the top left and bottom right vertices.\n",
"\n",
"Here is a visualzation of these three lines:\n",
"\n",
"<br>\n",
"\n",
"<img src=\"https://cloud.google.com/vision/automl/object-detection/docs/images/quickstart-preparing_a_dataset.png\" width=\"400\" hspace=\"100\">\n",
"\n",
"If you want to know more about how to prepare your own CSV file and the minimum requirements for creating a valid dataset, see the [Preparing your training data](https://cloud.google.com/vision/automl/object-detection/docs/prepare) guide for more details.\n",
"\n",
"If you are new to Google Cloud, you may wonder what the `gs://` URL means. They are URLs of files stored on [Google Cloud Storage](https://cloud.google.com/storage) (GCS). If you make your files on GCS public or [authenticate your client](https://cloud.google.com/storage/docs/authentication#libauth), Model Maker can read those files similarly to your local files.\n",
"\n",
"However, you don't need to keep your images on Google Cloud to use Model Maker. You can use a local path in your CSV file and Model Maker will just work."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "xushUyZXqP59"
},
"source": [
"## Quickstart"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vn61LJ9QbOPi"
},
"source": [
"There are six steps to training an object detection model:\n",
"\n",
"**Step 1. Choose an object detection model archiecture.**\n",
"\n",
"This tutorial uses the EfficientDet-Lite0 model. EfficientDet-Lite[0-4] are a family of mobile/IoT-friendly object detection models derived from the [EfficientDet](https://arxiv.org/abs/1911.09070) architecture.\n",
"\n",
"Here is the performance of each EfficientDet-Lite models compared to each others.\n",
"\n",
"| Model architecture | Size(MB)* | Latency(ms)** | Average Precision*** |\n",
"|--------------------|-----------|---------------|----------------------|\n",
"| EfficientDet-Lite0 | 4.4 | 37 | 25.69% |\n",
"| EfficientDet-Lite1 | 5.8 | 49 | 30.55% |\n",
"| EfficientDet-Lite2 | 7.2 | 69 | 33.97% |\n",
"| EfficientDet-Lite3 | 11.4 | 116 | 37.70% |\n",
"| EfficientDet-Lite4 | 19.9 | 260 | 41.96% |\n",
"\n",
"<i> * Size of the integer quantized models. <br/>\n",
"** Latency measured on Pixel 4 using 4 threads on CPU. <br/>\n",
"*** Average Precision is the mAP (mean Average Precision) on the COCO 2017 validation dataset.\n",
"</i>\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "CtdZ-JDwMimd",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "775bff0f-bad4-4a26-a795-8f952afeeb10"
},
"source": [
"#spec = model_spec.get('efficientdet_lite0', strategy='tpu', tpu=tpu.master(), debug=True)\n",
"from tensorflow_examples.lite.model_maker.core.task.model_spec import object_detector_spec\n",
"spec = object_detector_spec.efficientdet_lite0_spec(strategy='tpu', tpu=tpu.master(), debug=True)\n",
"print(spec)"
],
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"text": [
"INFO:absl:Entering into master device scope: /job:worker/replica:0/task:0/device:CPU:0\n",
"INFO:absl:All devices: [LogicalDevice(name='/job:worker/replica:0/task:0/device:TPU:4', device_type='TPU'), LogicalDevice(name='/job:worker/replica:0/task:0/device:TPU:3', device_type='TPU'), LogicalDevice(name='/job:worker/replica:0/task:0/device:TPU:6', device_type='TPU'), LogicalDevice(name='/job:worker/replica:0/task:0/device:TPU:5', device_type='TPU'), LogicalDevice(name='/job:worker/replica:0/task:0/device:TPU:7', device_type='TPU'), LogicalDevice(name='/job:worker/replica:0/task:0/device:TPU:0', device_type='TPU'), LogicalDevice(name='/job:worker/replica:0/task:0/device:TPU:1', device_type='TPU'), LogicalDevice(name='/job:worker/replica:0/task:0/device:TPU:2', device_type='TPU')]\n"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"<tensorflow_examples.lite.model_maker.core.task.model_spec.object_detector_spec.EfficientDetModelSpec object at 0x7f2ae2cc89d0>\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "s5U-A3tw6Y27"
},
"source": [
"**Step 2. Load the dataset.**\n",
"\n",
"Model Maker will take input data in the CSV format. Use the `object_detector.DataLoader.from_csv` method to load the dataset and split them into the training, validation and test images.\n",
"\n",
"* Training images: These images are used to train the object detection model to recognize salad ingredients.\n",
"* Validation images: These are images that the model didn't see during the training process. You'll use them to decide when you should stop the training, to avoid [overfitting](https://en.wikipedia.org/wiki/Overfitting).\n",
"* Test images: These images are used to evaluate the final model performance.\n",
"\n",
"You can load the CSV file directly from Google Cloud Storage, but you don't need to keep your images on Google Cloud to use Model Maker. You can specify a local CSV file on your computer, and Model Maker will work just fine."
]
},
{
"cell_type": "code",
"metadata": {
"id": "HD5BvzWe6YKa"
},
"source": [
"train_data, validation_data, test_data = object_detector.DataLoader.from_csv('gs://cloud-ml-data/img/openimage/csv/salads_ml_use.csv')"
],
"execution_count": 8,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "2uZkLR6N6gDR"
},
"source": [
"**Step 3. Train the TensorFlow model with the training data.**\n",
"\n",
"* The EfficientDet-Lite0 model uses `epochs = 50` by default, which means it will go through the training dataset 50 times. You can look at the validation accuracy during training and stop early to avoid overfitting.\n",
"* Set `batch_size = 8` here so you will see that it takes 21 steps to go through the 175 images in the training dataset.\n",
"* Set `train_whole_model=True` to fine-tune the whole model instead of just training the head layer to improve accuracy. The trade-off is that it may take longer to train the model."
]
},
{
"cell_type": "code",
"metadata": {
"id": "kwlYdTcg63xy",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 426
},
"outputId": "f11a87db-0a8f-4ce5-a7ea-699c5ca806fc"
},
"source": [
"model = object_detector.create(train_data, model_spec=spec, batch_size=8, epochs=4, train_whole_model=True, validation_data=validation_data)"
],
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"text": [
"INFO:absl:Using /tmp/tfhub_modules to cache modules.\n",
"INFO:absl:Downloading TF-Hub Module 'https://tfhub.dev/tensorflow/efficientdet/lite0/feature-vector/1'.\n",
"INFO:absl:Downloaded https://tfhub.dev/tensorflow/efficientdet/lite0/feature-vector/1, Total size: 29.61MB\n",
"INFO:absl:Downloaded TF-Hub Module 'https://tfhub.dev/tensorflow/efficientdet/lite0/feature-vector/1'.\n"
],
"name": "stderr"
},
{
"output_type": "error",
"ename": "InvalidArgumentError",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mInvalidArgumentError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-9-fb7d2e23be2c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mobject_detector\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel_spec\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mspec\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m8\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m4\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrain_whole_model\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mvalidation_data\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow_examples/lite/model_maker/core/task/object_detector.py\u001b[0m in \u001b[0;36mcreate\u001b[0;34m(cls, train_data, model_spec, validation_data, epochs, batch_size, train_whole_model, do_train)\u001b[0m\n\u001b[1;32m 285\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mdo_train\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 286\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompat\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mv1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlogging\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minfo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Retraining the models...'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 287\u001b[0;31m \u001b[0mobject_detector\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrain_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 288\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 289\u001b[0m \u001b[0mobject_detector\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow_examples/lite/model_maker/core/task/object_detector.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, train_data, validation_data, epochs, batch_size)\u001b[0m\n\u001b[1;32m 149\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 150\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodel_spec\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mds_strategy\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscope\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 151\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 152\u001b[0m train_ds, steps_per_epoch, _ = self._get_dataset_and_steps(\n\u001b[1;32m 153\u001b[0m train_data, batch_size, is_training=True)\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow_examples/lite/model_maker/core/task/object_detector.py\u001b[0m in \u001b[0;36mcreate_model\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 105\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 106\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mcreate_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mModel\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 107\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodel_spec\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate_model\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 108\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmodel\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 109\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow_examples/lite/model_maker/core/task/model_spec/object_detector_spec.py\u001b[0m in \u001b[0;36mcreate_model\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 237\u001b[0m \u001b[0;34m\"\"\"Creates the EfficientDet model.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 238\u001b[0m return train_lib.EfficientDetNetTrainHub(\n\u001b[0;32m--> 239\u001b[0;31m config=self.config, hub_module_url=self.uri)\n\u001b[0m\u001b[1;32m 240\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 241\u001b[0m def train(self,\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow_examples/lite/model_maker/third_party/efficientdet/keras/train_lib.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, config, hub_module_url, name)\u001b[0m\n\u001b[1;32m 860\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconfig\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconfig\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 861\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhub_module_url\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mhub_module_url\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 862\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbase_model\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mhub\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mKerasLayer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhub_module_url\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtrainable\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 863\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 864\u001b[0m \u001b[0;31m# class/box output prediction network.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow_hub/keras_layer.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, handle, trainable, arguments, _sentinel, tags, signature, signature_outputs_as_dict, output_key, output_shape, load_options, **kwargs)\u001b[0m\n\u001b[1;32m 158\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 159\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_load_options\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_options\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 160\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_func\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_module\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtags\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_load_options\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 161\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_has_training_argument\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunc_has_training_argument\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_func\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 162\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_is_hub_module_v1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_func\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"_is_hub_module_v1\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow_hub/keras_layer.py\u001b[0m in \u001b[0;36mload_module\u001b[0;34m(handle, tags, load_options)\u001b[0m\n\u001b[1;32m 427\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mImportError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 428\u001b[0m \u001b[0mset_load_options\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_options\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 429\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mmodule_v2\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtags\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtags\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptions\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mset_load_options\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 430\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 431\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow_hub/module_v2.py\u001b[0m in \u001b[0;36mload\u001b[0;34m(handle, tags, options)\u001b[0m\n\u001b[1;32m 112\u001b[0m module_path, tags=tags, options=options)\n\u001b[1;32m 113\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 114\u001b[0;31m \u001b[0mobj\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_v1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msaved_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload_v2\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodule_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtags\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtags\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 115\u001b[0m \u001b[0mobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_is_hub_module_v1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mis_hub_module_v1\u001b[0m \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 116\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mobj\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/saved_model/load.py\u001b[0m in \u001b[0;36mload\u001b[0;34m(export_dir, tags, options)\u001b[0m\n\u001b[1;32m 867\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mIf\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m`\u001b[0m\u001b[0mtags\u001b[0m\u001b[0;31m`\u001b[0m \u001b[0mdon\u001b[0m\u001b[0;31m'\u001b[0m\u001b[0mt\u001b[0m \u001b[0mmatch\u001b[0m \u001b[0ma\u001b[0m \u001b[0mMetaGraph\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mSavedModel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 868\u001b[0m \"\"\"\n\u001b[0;32m--> 869\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mload_internal\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexport_dir\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtags\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"root\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 870\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 871\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/saved_model/load.py\u001b[0m in \u001b[0;36mload_internal\u001b[0;34m(export_dir, tags, options, loader_cls, filters)\u001b[0m\n\u001b[1;32m 904\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 905\u001b[0m loader = loader_cls(object_graph_proto, saved_model_proto, export_dir,\n\u001b[0;32m--> 906\u001b[0;31m ckpt_options, filters)\n\u001b[0m\u001b[1;32m 907\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0merrors\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mNotFoundError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 908\u001b[0m raise FileNotFoundError(\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/saved_model/load.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, object_graph_proto, saved_model_proto, export_dir, ckpt_options, filters)\u001b[0m\n\u001b[1;32m 161\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 162\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_load_all\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 163\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_restore_checkpoint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 164\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 165\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mnode\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_nodes\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/saved_model/load.py\u001b[0m in \u001b[0;36m_restore_checkpoint\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 487\u001b[0m self._checkpoint_options).expect_partial()\n\u001b[1;32m 488\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 489\u001b[0;31m \u001b[0mload_status\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msaver\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrestore\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvariables_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_checkpoint_options\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 490\u001b[0m \u001b[0mload_status\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0massert_existing_objects_matched\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 491\u001b[0m \u001b[0mcheckpoint\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_status\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_checkpoint\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/util.py\u001b[0m in \u001b[0;36mrestore\u001b[0;34m(self, save_path, options)\u001b[0m\n\u001b[1;32m 1337\u001b[0m options=options)\n\u001b[1;32m 1338\u001b[0m base.CheckpointPosition(\n\u001b[0;32m-> 1339\u001b[0;31m checkpoint=checkpoint, proto_id=0).restore(self._graph_view.root)\n\u001b[0m\u001b[1;32m 1340\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1341\u001b[0m \u001b[0;31m# Attached dependencies are not attached to the root, so should be restored\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py\u001b[0m in \u001b[0;36mrestore\u001b[0;34m(self, trackable)\u001b[0m\n\u001b[1;32m 256\u001b[0m \u001b[0;31m# This object's correspondence with a checkpointed object is new, so\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 257\u001b[0m \u001b[0;31m# process deferred restorations for it and its dependencies.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 258\u001b[0;31m \u001b[0mrestore_ops\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrackable\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_restore_from_checkpoint_position\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 259\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mrestore_ops\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 260\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_checkpoint\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnew_restore_ops\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrestore_ops\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py\u001b[0m in \u001b[0;36m_restore_from_checkpoint_position\u001b[0;34m(self, checkpoint_position)\u001b[0m\n\u001b[1;32m 976\u001b[0m restore_ops.extend(\n\u001b[1;32m 977\u001b[0m current_position.checkpoint.restore_saveables(\n\u001b[0;32m--> 978\u001b[0;31m tensor_saveables, python_saveables))\n\u001b[0m\u001b[1;32m 979\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mrestore_ops\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 980\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/util.py\u001b[0m in \u001b[0;36mrestore_saveables\u001b[0;34m(self, tensor_saveables, python_saveables)\u001b[0m\n\u001b[1;32m 307\u001b[0m \"expecting %s\") % (tensor_saveables.keys(), validated_names))\n\u001b[1;32m 308\u001b[0m new_restore_ops = functional_saver.MultiDeviceSaver(\n\u001b[0;32m--> 309\u001b[0;31m validated_saveables).restore(self.save_path_tensor, self.options)\n\u001b[0m\u001b[1;32m 310\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecuting_eagerly\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 311\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrestore_op\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msorted\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnew_restore_ops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saving/functional_saver.py\u001b[0m in \u001b[0;36mrestore\u001b[0;34m(self, file_prefix, options)\u001b[0m\n\u001b[1;32m 337\u001b[0m \u001b[0mrestore_ops\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_function_restore\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 338\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 339\u001b[0;31m \u001b[0mrestore_ops\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrestore_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 340\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 341\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mcallback\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_after_restore_callbacks\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saving/functional_saver.py\u001b[0m in \u001b[0;36mrestore_fn\u001b[0;34m()\u001b[0m\n\u001b[1;32m 321\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mdevice\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msaver\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msorted\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_single_device_savers\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mitems\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 322\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 323\u001b[0;31m \u001b[0mrestore_ops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msaver\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrestore\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfile_prefix\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 324\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 325\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mrestore_ops\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saving/functional_saver.py\u001b[0m in \u001b[0;36mrestore\u001b[0;34m(self, file_prefix, options)\u001b[0m\n\u001b[1;32m 114\u001b[0m structured_restored_tensors):\n\u001b[1;32m 115\u001b[0m restore_ops[saveable.name] = saveable.restore(\n\u001b[0;32m--> 116\u001b[0;31m restored_tensors, restored_shapes=None)\n\u001b[0m\u001b[1;32m 117\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mrestore_ops\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 118\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/values.py\u001b[0m in \u001b[0;36mrestore\u001b[0;34m(self, restored_tensors, restored_shapes)\u001b[0m\n\u001b[1;32m 1060\u001b[0m \u001b[0mtensor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrestored_tensors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1061\u001b[0m return self._distributed_variable._policy.get_restore_ops( # pylint: disable=protected-access\n\u001b[0;32m-> 1062\u001b[0;31m self._distributed_variable, tensor)\n\u001b[0m\u001b[1;32m 1063\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1064\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/values.py\u001b[0m in \u001b[0;36mget_restore_ops\u001b[0;34m(self, var, tensor)\u001b[0m\n\u001b[1;32m 1637\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1638\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mget_restore_ops\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvar\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1639\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mvalues_util\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_on_write_restore_ops\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvar\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1640\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1641\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_write_object_proto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvar\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mproto\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/values_util.py\u001b[0m in \u001b[0;36mget_on_write_restore_ops\u001b[0;34m(var, tensor)\u001b[0m\n\u001b[1;32m 90\u001b[0m tuple(\n\u001b[1;32m 91\u001b[0m \u001b[0massign_on_device\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0md\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpacked_var\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 92\u001b[0;31m for d in packed_var.devices))\n\u001b[0m\u001b[1;32m 93\u001b[0m return control_flow_ops.group(\n\u001b[1;32m 94\u001b[0m tuple(\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/values_util.py\u001b[0m in \u001b[0;36m<genexpr>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 90\u001b[0m tuple(\n\u001b[1;32m 91\u001b[0m \u001b[0massign_on_device\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0md\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpacked_var\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 92\u001b[0;31m for d in packed_var.devices))\n\u001b[0m\u001b[1;32m 93\u001b[0m return control_flow_ops.group(\n\u001b[1;32m 94\u001b[0m tuple(\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/values_util.py\u001b[0m in \u001b[0;36massign_on_device\u001b[0;34m(device, variable, tensor)\u001b[0m\n\u001b[1;32m 300\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0massign_on_device\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvariable\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 301\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 302\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mvariable\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0massign\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 303\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 304\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/packed_distributed_variable.py\u001b[0m in \u001b[0;36massign\u001b[0;34m(self, value, use_locking, name, read_value)\u001b[0m\n\u001b[1;32m 174\u001b[0m \u001b[0muse_locking\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0muse_locking\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 175\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 176\u001b[0;31m read_value=read_value)\n\u001b[0m\u001b[1;32m 177\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 178\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mscatter_sub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msparse_delta\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0muse_locking\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/packed_distributed_variable.py\u001b[0m in \u001b[0;36m_update\u001b[0;34m(self, update_fn, value, **kwargs)\u001b[0m\n\u001b[1;32m 145\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_update\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mupdate_fn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 146\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexecuting_eagerly\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 147\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mupdate_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_var_on_current_device\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 148\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 149\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mupdate_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mPackedDistributedVariable\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/packed_distributed_variable.py\u001b[0m in \u001b[0;36m<lambda>\u001b[0;34m(var, *a, **kw)\u001b[0m\n\u001b[1;32m 168\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 169\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0massign\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0muse_locking\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mread_value\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 170\u001b[0;31m \u001b[0massign_fn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mlambda\u001b[0m \u001b[0mvar\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkw\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mvar\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0massign\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkw\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 171\u001b[0m return self._update(\n\u001b[1;32m 172\u001b[0m \u001b[0mupdate_fn\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0massign_fn\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/resource_variable_ops.py\u001b[0m in \u001b[0;36massign\u001b[0;34m(self, value, use_locking, name, read_value)\u001b[0m\n\u001b[1;32m 891\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0m_handle_graph\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhandle\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 892\u001b[0m \u001b[0mvalue_tensor\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconvert_to_tensor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 893\u001b[0;31m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_shape\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_compatible_with\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue_tensor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 894\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mname\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 895\u001b[0m \u001b[0mtensor_name\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36mshape\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 1196\u001b[0m \u001b[0;31m# `_tensor_shape` is declared and defined in the definition of\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1197\u001b[0m \u001b[0;31m# `EagerTensor`, in C.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1198\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_tensor_shape\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtensor_shape\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTensorShape\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_shape_tuple\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1199\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_NotOkStatusException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1200\u001b[0m \u001b[0msix\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mraise_from\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_status_to_exception\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcode\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mInvalidArgumentError\u001b[0m: Unsuccessful TensorSliceReader constructor: Failed to get matching files on /tmp/tfhub_modules/0771ebbebbfa831cd20c20680920ec4ad9deb2bd/variables/variables: Unimplemented: File system scheme '[local]' not implemented (file: '/tmp/tfhub_modules/0771ebbebbfa831cd20c20680920ec4ad9deb2bd/variables/variables')"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "-BzCHLWJ6h7q"
},
"source": [
"**Step 4. Evaluate the model with the test data.**\n",
"\n",
"After training the object detection model using the images in the training dataset, use the remaining 25 images in the test dataset to evaluate how the model performs against new data it has never seen before.\n",
"\n",
"As the default batch size is 64, it will take 1 step to go through the 25 images in the test dataset.\n",
"\n",
"The evaluation metrics are same as [COCO](https://cocodataset.org/#detection-eval)."
]
},
{
"cell_type": "code",
"metadata": {
"id": "8xmnl6Yy7ARn"
},
"source": [
"model.evaluate(test_data)"
],
"execution_count": null,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment