{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "d6p8EySq1zXZ" }, "source": [ "##### Copyright 2019 The TensorFlow Authors." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "cellView": "form", "execution": { "iopub.execute_input": "2022-12-15T02:45:16.985527Z", "iopub.status.busy": "2022-12-15T02:45:16.985244Z", "iopub.status.idle": "2022-12-15T02:45:16.989596Z", "shell.execute_reply": "2022-12-15T02:45:16.988975Z" }, "id": "KsOkK8O69PyT" }, "outputs": [], "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." ] }, { "cell_type": "markdown", "metadata": { "id": "F1xIRPtY0E1w" }, "source": [ "# Keras モデルから Estimator を作成する" ] }, { "cell_type": "markdown", "metadata": { "id": "r61fkA2i9Y3_" }, "source": [ "\n", " \n", " \n", " \n", " \n", "
TensorFlow.org で表示Google Colab で実行GitHub でソースを表示ノートブックをダウンロード
" ] }, { "cell_type": "markdown", "metadata": { "id": "Dhcq8Ds4mCtm" }, "source": [ "> 警告: 新しいコードには Estimators は推奨されません。Estimators は `v1.Session` スタイルのコードを実行しますが、これは正しく記述するのはより難しく、特に TF 2 コードと組み合わせると予期しない動作をする可能性があります。Estimators は、[互換性保証](https://tensorflow.org/guide/versions)の対象となりますが、セキュリティの脆弱性以外の修正は行われません。詳細については、[移行ガイド](https://tensorflow.org/guide/migrate)を参照してください。" ] }, { "cell_type": "markdown", "metadata": { "id": "ZaGcclVLwqDS" }, "source": [ "## 概要\n", "\n", "TensorFlow Estimator は、TensorFlow でサポートされており、新規または既存の `tf.keras` モデルから作成することができます。このチュートリアルには、このプロセスの完全な最小限の例が含まれます。\n", "\n", "注意: Keras モデルがある場合は、Estimator に変換せずに、直接 [`tf.distribute` ストラテジー](https://tensorflow.org/guide/migrate/guide/distributed_training)で使用することができます。したがって、`model_to_estimator` は推奨されなくなりました。" ] }, { "cell_type": "markdown", "metadata": { "id": "epgfaZmO2vF0" }, "source": [ "## セットアップ" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "execution": { "iopub.execute_input": "2022-12-15T02:45:16.993541Z", "iopub.status.busy": "2022-12-15T02:45:16.993018Z", "iopub.status.idle": "2022-12-15T02:45:19.780857Z", "shell.execute_reply": "2022-12-15T02:45:19.779956Z" }, "id": "Qmq4FzaztASN" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2022-12-15 02:45:18.105988: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory\n", "2022-12-15 02:45:18.106099: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory\n", "2022-12-15 02:45:18.106110: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n" ] } ], "source": [ "import tensorflow as tf\n", "\n", "import numpy as np\n", "import tensorflow_datasets as tfds" ] }, { "cell_type": "markdown", "metadata": { "id": "9ZUATGJGtQIU" }, "source": [ "### 単純な Keras モデルを作成する。" ] }, { "cell_type": "markdown", "metadata": { "id": "rR-zPidHyzcb" }, "source": [ "Keras では、*レイヤー*を組み合わせて*モデル*を構築します。モデルは（通常）レイヤーのグラフです。最も一般的なモデルのタイプはレイヤーのスタックである `tf.keras.Sequential` モデルです。\n", "\n", "単純で完全に接続されたネットワーク（多層パーセプトロン）を構築するには、以下を実行します。" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "execution": { "iopub.execute_input": "2022-12-15T02:45:19.785977Z", "iopub.status.busy": "2022-12-15T02:45:19.785430Z", "iopub.status.idle": "2022-12-15T02:45:23.643738Z", "shell.execute_reply": "2022-12-15T02:45:23.642819Z" }, "id": "p5NSx38itD1a" }, "outputs": [], "source": [ "model = tf.keras.models.Sequential([\n", " tf.keras.layers.Dense(16, activation='relu', input_shape=(4,)),\n", " tf.keras.layers.Dropout(0.2),\n", " tf.keras.layers.Dense(3)\n", "])" ] }, { "cell_type": "markdown", "metadata": { "id": "ABgo9-8BtYNs" }, "source": [ "モデルをコンパイルして要約を取得します。" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "execution": { "iopub.execute_input": "2022-12-15T02:45:23.648450Z", "iopub.status.busy": "2022-12-15T02:45:23.647809Z", "iopub.status.idle": "2022-12-15T02:45:23.672837Z", "shell.execute_reply": "2022-12-15T02:45:23.672049Z" }, "id": "nViACuBDtVEC" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model: \"sequential\"\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "_________________________________________________________________\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " Layer (type) Output Shape Param # \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "=================================================================\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " dense (Dense) (None, 16) 80 \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " dropout (Dropout) (None, 16) 0 \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " dense_1 (Dense) (None, 3) 51 \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ " \n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "=================================================================\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Total params: 131\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Trainable params: 131\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Non-trainable params: 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "_________________________________________________________________\n" ] } ], "source": [ "model.compile(loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n", " optimizer='adam')\n", "model.summary()" ] }, { "cell_type": "markdown", "metadata": { "id": "pM3Cx5Fm_sHI" }, "source": [ "### 入力関数を作成する\n", "\n", "[Datasets API](../../guide/data.md) を使用して、大規模なデータセットまたはマルチデバイストレーニングにスケーリングします。\n", "\n", "Estimator には、いつどのように入力パイプラインが構築されるのかを制御する必要があります。これを行えるようにするには、\"入力関数\" または `input_fn` が必要です。`Estimator` は引数なしでこの関数を呼び出します。`input_fn` は、`tf.data.Dataset` を返す必要があります。" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2022-12-15T02:45:23.680506Z", "iopub.status.busy": "2022-12-15T02:45:23.679829Z", "iopub.status.idle": "2022-12-15T02:45:23.684430Z", "shell.execute_reply": "2022-12-15T02:45:23.683718Z" }, "id": "H0DpLEop_x0o" }, "outputs": [], "source": [ "def input_fn():\n", " split = tfds.Split.TRAIN\n", " dataset = tfds.load('iris', split=split, as_supervised=True)\n", " dataset = dataset.map(lambda features, labels: ({'dense_input':features}, labels))\n", " dataset = dataset.batch(32).repeat()\n", " return dataset" ] }, { "cell_type": "markdown", "metadata": { "id": "UR1vRw1bBFjo" }, "source": [ "`input_fn` をテストします。" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "execution": { "iopub.execute_input": "2022-12-15T02:45:23.687910Z", "iopub.status.busy": "2022-12-15T02:45:23.687388Z", "iopub.status.idle": "2022-12-15T02:45:24.832153Z", "shell.execute_reply": "2022-12-15T02:45:24.831281Z" }, "id": "WO94bGYKBKRv" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.9/site-packages/tensorflow/python/autograph/pyct/static_analysis/liveness.py:83: Analyzer.lamba_check (from tensorflow.python.autograph.pyct.static_analysis.liveness) is deprecated and will be removed after 2023-09-23.\n", "Instructions for updating:\n", "Lambda fuctions will be no more assumed to be used in the statement where they are used, or at least in the same block. https://github.com/tensorflow/tensorflow/issues/56089\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.9/site-packages/tensorflow/python/autograph/pyct/static_analysis/liveness.py:83: Analyzer.lamba_check (from tensorflow.python.autograph.pyct.static_analysis.liveness) is deprecated and will be removed after 2023-09-23.\n", "Instructions for updating:\n", "Lambda fuctions will be no more assumed to be used in the statement where they are used, or at least in the same block. https://github.com/tensorflow/tensorflow/issues/56089\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'dense_input': }\n", "tf.Tensor([0 2 1 2 0 1 1 1 0 2 1 0 2 0 0 0 0 0 2 2 2 2 2 0 2 0 2 1 1 1 1 1], shape=(32,), dtype=int64)\n" ] } ], "source": [ "for features_batch, labels_batch in input_fn().take(1):\n", " print(features_batch)\n", " print(labels_batch)" ] }, { "cell_type": "markdown", "metadata": { "id": "svdhkQ4Otcv0" }, "source": [ "### tf.keras モデルから Estimator を作成する。\n", "\n", "`tf.keras.Model` は、`tf.estimator` API を使って、`tf.keras.estimator.model_to_estimator` を持つ `tf.estimator.Estimator` オブジェクトにモデルを変換することで、トレーニングすることができます。" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "execution": { "iopub.execute_input": "2022-12-15T02:45:24.836162Z", "iopub.status.busy": "2022-12-15T02:45:24.835433Z", "iopub.status.idle": "2022-12-15T02:45:25.183714Z", "shell.execute_reply": "2022-12-15T02:45:25.182739Z" }, "id": "roChngg8t7il" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Using default config.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Using default config.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Using the Keras model provided.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Using the Keras model provided.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "WARNING:absl:You are using `tf.keras.optimizers.experimental.Optimizer` in TF estimator, which only supports `tf.keras.optimizers.legacy.Optimizer`. Automatically converting your optimizer to `tf.keras.optimizers.legacy.Optimizer`.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/tmpfs/src/tf_docs_env/lib/python3.9/site-packages/keras/backend.py:451: UserWarning: `tf.keras.backend.set_learning_phase` is deprecated and will be removed after 2020-10-11. To update it, simply pass a True/False value to the `training` argument of the `__call__` method of your layer or model.\n", " warnings.warn(\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Using config: {'_model_dir': '/tmpfs/tmp/tmp9h0gesw0', '_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, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_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" ] }, { "name": "stderr", "output_type": "stream", "text": [ "2022-12-15 02:45:25.103464: W tensorflow/c/c_api.cc:291] Operation '{name:'training/Adam/dense_1/bias/v/Assign' id:218 op device:{requested: '', assigned: ''} def:{{{node training/Adam/dense_1/bias/v/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](training/Adam/dense_1/bias/v, training/Adam/dense_1/bias/v/Initializer/zeros)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session.\n", "INFO:tensorflow:Using config: {'_model_dir': '/tmpfs/tmp/tmp9h0gesw0', '_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, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_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" ] } ], "source": [ "import tempfile\n", "model_dir = tempfile.mkdtemp()\n", "keras_estimator = tf.keras.estimator.model_to_estimator(\n", " keras_model=model, model_dir=model_dir)" ] }, { "cell_type": "markdown", "metadata": { "id": "U-8ekW5It_2w" }, "source": [ "Estimator をトレーニングして評価します。" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "execution": { "iopub.execute_input": "2022-12-15T02:45:25.187938Z", "iopub.status.busy": "2022-12-15T02:45:25.187248Z", "iopub.status.idle": "2022-12-15T02:45:39.238826Z", "shell.execute_reply": "2022-12-15T02:45:39.238050Z" }, "id": "ouIkVtp9uAg5" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.9/site-packages/tensorflow/python/training/training_util.py:396: 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" ] }, { "name": "stderr", "output_type": "stream", "text": [ "WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.9/site-packages/tensorflow/python/training/training_util.py:396: 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" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Calling model_fn.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Calling model_fn.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Done calling model_fn.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Done calling model_fn.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Warm-starting with WarmStartSettings: WarmStartSettings(ckpt_to_initialize_from='/tmpfs/tmp/tmp9h0gesw0/keras/keras_model.ckpt', vars_to_warm_start='.*', var_name_to_vocab_info={}, var_name_to_prev_var_name={})\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Warm-starting with WarmStartSettings: WarmStartSettings(ckpt_to_initialize_from='/tmpfs/tmp/tmp9h0gesw0/keras/keras_model.ckpt', vars_to_warm_start='.*', var_name_to_vocab_info={}, var_name_to_prev_var_name={})\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Warm-starting from: /tmpfs/tmp/tmp9h0gesw0/keras/keras_model.ckpt\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Warm-starting from: /tmpfs/tmp/tmp9h0gesw0/keras/keras_model.ckpt\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Warm-starting variables only in TRAINABLE_VARIABLES.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Warm-starting variables only in TRAINABLE_VARIABLES.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Warm-started 4 variables.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Warm-started 4 variables.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Create CheckpointSaverHook.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Create CheckpointSaverHook.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Graph was finalized.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Graph was finalized.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Running local_init_op.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Running local_init_op.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Done running local_init_op.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Done running local_init_op.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0...\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0...\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Saving checkpoints for 0 into /tmpfs/tmp/tmp9h0gesw0/model.ckpt.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Saving checkpoints for 0 into /tmpfs/tmp/tmp9h0gesw0/model.ckpt.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 2.432807, step = 0\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 2.432807, step = 0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:global_step/sec: 44.6531\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:global_step/sec: 44.6531\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 1.0671942, step = 100 (2.241 sec)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 1.0671942, step = 100 (2.241 sec)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:global_step/sec: 46.4651\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:global_step/sec: 46.4651\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 0.82943535, step = 200 (2.152 sec)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 0.82943535, step = 200 (2.152 sec)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:global_step/sec: 46.1527\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:global_step/sec: 46.1527\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 0.6606032, step = 300 (2.167 sec)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 0.6606032, step = 300 (2.167 sec)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:global_step/sec: 46.4966\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:global_step/sec: 46.4966\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 0.56208, step = 400 (2.151 sec)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:loss = 0.56208, step = 400 (2.151 sec)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 500...\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 500...\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Saving checkpoints for 500 into /tmpfs/tmp/tmp9h0gesw0/model.ckpt.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Saving checkpoints for 500 into /tmpfs/tmp/tmp9h0gesw0/model.ckpt.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 500...\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 500...\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Loss for final step: 0.5922533.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Loss for final step: 0.5922533.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Calling model_fn.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Calling model_fn.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Done calling model_fn.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/tmpfs/src/tf_docs_env/lib/python3.9/site-packages/keras/engine/training_v1.py:2333: UserWarning: `Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically.\n", " updates = self.state_updates\n", "INFO:tensorflow:Done calling model_fn.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Starting evaluation at 2022-12-15T02:45:38\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Starting evaluation at 2022-12-15T02:45:38\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Graph was finalized.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Graph was finalized.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Restoring parameters from /tmpfs/tmp/tmp9h0gesw0/model.ckpt-500\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Restoring parameters from /tmpfs/tmp/tmp9h0gesw0/model.ckpt-500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Running local_init_op.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Running local_init_op.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Done running local_init_op.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Done running local_init_op.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [1/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [1/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [2/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [2/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [3/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [3/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [4/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [4/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [5/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [5/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [6/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [6/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [7/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [7/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [8/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [8/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [9/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [9/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [10/10]\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Evaluation [10/10]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Inference Time : 0.50137s\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Inference Time : 0.50137s\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Finished evaluation at 2022-12-15-02:45:39\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Finished evaluation at 2022-12-15-02:45:39\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Saving dict for global step 500: global_step = 500, loss = 0.5014641\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Saving dict for global step 500: global_step = 500, loss = 0.5014641\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 500: /tmpfs/tmp/tmp9h0gesw0/model.ckpt-500\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "INFO:tensorflow:Saving 'checkpoint_path' summary for global step 500: /tmpfs/tmp/tmp9h0gesw0/model.ckpt-500\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Eval result: {'loss': 0.5014641, 'global_step': 500}\n" ] } ], "source": [ "keras_estimator.train(input_fn=input_fn, steps=500)\n", "eval_result = keras_estimator.evaluate(input_fn=input_fn, steps=10)\n", "print('Eval result: {}'.format(eval_result))" ] } ], "metadata": { "colab": { "collapsed_sections": [], "name": "keras_model_to_estimator.ipynb", "toc_visible": true }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.16" } }, "nbformat": 4, "nbformat_minor": 0 }