{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "6bYaCABobL5q"
      },
      "outputs": [],
      "source": [
        "##### Copyright 2018 The TensorFlow Authors."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "cellView": "form",
        "id": "FlUw7tSKbtg4"
      },
      "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": "xc1srSc51n_4"
      },
      "source": [
        "# 使用 SavedModel 格式"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-nBUqG2rchGH"
      },
      "source": [
        "<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
        "  <td><a target=\"_blank\" href=\"https://tensorflow.google.cn/guide/saved_model\" class=\"\"><img src=\"https://tensorflow.google.cn/images/tf_logo_32px.png\" class=\"\">在 TensorFlow.org 上查看</a></td>\n",
        "  <td><a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/docs-l10n/blob/master/site/zh-cn/guide/saved_model.ipynb\"><img src=\"https://tensorflow.google.cn/images/colab_logo_32px.png\">在 Google Colab 中运行</a></td>\n",
        "  <td>     <a target=\"_blank\" href=\"https://github.com/tensorflow/docs-l10n/blob/master/site/zh-cn/guide/saved_model.ipynb\"><img src=\"https://tensorflow.google.cn/images/GitHub-Mark-32px.png\">在 Github 上查看源代码</a>\n",
        "</td>\n",
        "  <td><a href=\"https://storage.googleapis.com/tensorflow_docs/docs-l10n/site/zh-cn/guide/saved_model.ipynb\" class=\"\"><img src=\"https://tensorflow.google.cn/images/download_logo_32px.png\" class=\"\">下载笔记本</a></td>\n",
        "</table>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CPE-fshLTsXU"
      },
      "source": [
        "SavedModel 包含一个完整的 TensorFlow 程序，包括训练的参数（即 `tf.Variable`）和计算。它不需要原始模型构建代码就可以运行，因此，对于使用 [TFLite](https://tensorflow.org/lite)、[TensorFlow.js](https://js.tensorflow.org/)、[TensorFlow Serving](https://tensorflow.google.cn/tfx/serving/tutorials/Serving_REST_simple) 或 [TensorFlow Hub](https://tensorflow.org/hub) 共享或部署非常有用。\n",
        "\n",
        "您可以使用以下 API 以 SavedModel 格式保存和加载模型：\n",
        "\n",
        "- 低级 `tf.saved_model` API。本文档将详细介绍如何使用此 API。\n",
        "    - 保存：`tf.saved_model.save(model, path_to_dir)`\n",
        "    - 加载：`model = tf.saved_model.load(path_to_dir)`\n",
        "- 高级`tf.keras.Model` API。请参阅 [Keras 保存和序列化指南](https://tensorflow.google.cn/guide/keras/save_and_serialize)。\n",
        "- 如果您只是想在训练中保存/加载权重，请参阅[检查点指南](./checkpoint.ipynb)。\n",
        "\n",
        "小心：TensorFlow 模型是代码，对于不受信任的代码，一定要小心。请参阅[安全使用 TensorFlow](https://github.com/tensorflow/tensorflow/blob/master/SECURITY.md) 以了解详情。\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9SuIC7FiI9g8"
      },
      "source": [
        "## 从 Keras 创建 SavedModel"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "AtSmftAvhJvE"
      },
      "source": [
        "已弃用：对于 Keras 对象，建议使用新的高级 `.keras` 格式和 `tf.keras.Model.export`，如[此处](https://tensorflow.google.cn/guide/keras/save_and_serialize)的指南所示。对于现有代码，继续支持低级 SavedModel 格式。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {},
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "/media/pc/data/lxw/ai/d2py/doc/libs/tf-chaos/guide\n"
          ]
        }
      ],
      "source": [
        "%cd ..\n",
        "from set_env import temp_dir"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eLSOptpYhJvE"
      },
      "source": [
        "为便于简单介绍，本部分将导出一个预训练 Keras 模型来处理图像分类请求。本指南的其他部分将详细介绍和讨论创建 SavedModel 的其他方式。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "id": "Le5OB-fBHHW7"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "import tempfile\n",
        "\n",
        "from matplotlib import pyplot as plt\n",
        "import numpy as np\n",
        "import tensorflow as tf\n",
        "\n",
        "tmpdir = tempfile.mkdtemp(str(temp_dir))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "id": "wlho4HEWoHUT"
      },
      "outputs": [],
      "source": [
        "physical_devices = tf.config.list_physical_devices('GPU')\n",
        "for device in physical_devices:\n",
        "  tf.config.experimental.set_memory_growth(device, True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "id": "SofdPKo0G8Lb"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "file = tf.keras.utils.get_file(\n",
        "    \"grace_hopper.jpg\",\n",
        "    \"https://storage.googleapis.com/download.tensorflow.org/example_images/grace_hopper.jpg\")\n",
        "img = tf.keras.utils.load_img(file, target_size=[224, 224])\n",
        "plt.imshow(img)\n",
        "plt.axis('off')\n",
        "x = tf.keras.utils.img_to_array(img)\n",
        "x = tf.keras.applications.mobilenet.preprocess_input(\n",
        "    x[tf.newaxis,...])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "sqVcFL10JkF0"
      },
      "source": [
        "我们会使用 Grace Hopper 的一张照片作为运行示例，并使用一个预先训练的 Keras 图像分类模型，因为它简单易用。您也可以使用自定义模型，后文会作详细介绍。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "id": "JhVecdzJTsKE"
      },
      "outputs": [],
      "source": [
        "labels_path = tf.keras.utils.get_file(\n",
        "    'ImageNetLabels.txt',\n",
        "    'https://storage.googleapis.com/download.tensorflow.org/data/ImageNetLabels.txt')\n",
        "imagenet_labels = np.array(open(labels_path).read().splitlines())"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "id": "aEHSYjW6JZHV"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
            "W0000 00:00:1729855602.693493 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.717962 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.718418 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.740024 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.740479 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.740971 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.751292 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.751747 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.753143 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.754849 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.756429 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.780397 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.847167 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.847600 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.848029 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.849851 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.851702 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.853514 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.854053 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.855672 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.856109 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.856525 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.858495 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.860658 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.861229 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.861682 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.862271 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n",
            "W0000 00:00:1729855602.863987 4125101 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced\n"
          ]
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Result before saving:\n",
            " ['military uniform' 'bow tie' 'suit' 'bearskin' 'pickelhaube']\n"
          ]
        }
      ],
      "source": [
        "pretrained_model = tf.keras.applications.MobileNet()\n",
        "result_before_save = pretrained_model(x)\n",
        "\n",
        "decoded = imagenet_labels[np.argsort(result_before_save)[0,::-1][:5]+1]\n",
        "\n",
        "print(\"Result before saving:\\n\", decoded)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "r4KIsQDZJ5PS"
      },
      "source": [
        "对此图像的热门预测是“军服”。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "id": "8nfznDmHCW6F"
      },
      "outputs": [
        {
          "ename": "TypeError",
          "evalue": "this __dict__ descriptor does not support '_DictWrapper' objects",
          "output_type": "error",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
            "Cell \u001b[0;32mIn[9], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m mobilenet_save_path \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(tmpdir, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmobilenet/1/\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 2\u001b[0m tf\u001b[38;5;241m.\u001b[39msaved_model\u001b[38;5;241m.\u001b[39msave(pretrained_model, mobilenet_save_path)\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/saved_model/save.py:1432\u001b[0m, in \u001b[0;36msave\u001b[0;34m(obj, export_dir, signatures, options)\u001b[0m\n\u001b[1;32m   1430\u001b[0m \u001b[38;5;66;03m# pylint: enable=line-too-long\u001b[39;00m\n\u001b[1;32m   1431\u001b[0m metrics\u001b[38;5;241m.\u001b[39mIncrementWriteApi(_SAVE_V2_LABEL)\n\u001b[0;32m-> 1432\u001b[0m save_and_return_nodes(obj, export_dir, signatures, options)\n\u001b[1;32m   1434\u001b[0m metrics\u001b[38;5;241m.\u001b[39mIncrementWrite(write_version\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m2\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/saved_model/save.py:1467\u001b[0m, in \u001b[0;36msave_and_return_nodes\u001b[0;34m(obj, export_dir, signatures, options, experimental_skip_checkpoint)\u001b[0m\n\u001b[1;32m   1463\u001b[0m saved_model \u001b[38;5;241m=\u001b[39m saved_model_pb2\u001b[38;5;241m.\u001b[39mSavedModel()\n\u001b[1;32m   1464\u001b[0m meta_graph_def \u001b[38;5;241m=\u001b[39m saved_model\u001b[38;5;241m.\u001b[39mmeta_graphs\u001b[38;5;241m.\u001b[39madd()\n\u001b[1;32m   1466\u001b[0m _, exported_graph, object_saver, asset_info, saved_nodes, node_paths \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m-> 1467\u001b[0m     _build_meta_graph(obj, signatures, options, meta_graph_def))\n\u001b[1;32m   1468\u001b[0m saved_model\u001b[38;5;241m.\u001b[39msaved_model_schema_version \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m   1469\u001b[0m     constants\u001b[38;5;241m.\u001b[39mSAVED_MODEL_SCHEMA_VERSION)\n\u001b[1;32m   1471\u001b[0m \u001b[38;5;66;03m# Write the checkpoint, copy assets into the assets directory, and write out\u001b[39;00m\n\u001b[1;32m   1472\u001b[0m \u001b[38;5;66;03m# the SavedModel proto itself.\u001b[39;00m\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/saved_model/save.py:1682\u001b[0m, in \u001b[0;36m_build_meta_graph\u001b[0;34m(obj, signatures, options, meta_graph_def)\u001b[0m\n\u001b[1;32m   1655\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Creates a MetaGraph under a save context.\u001b[39;00m\n\u001b[1;32m   1656\u001b[0m \n\u001b[1;32m   1657\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1678\u001b[0m \u001b[38;5;124;03m  saveable_view.node_paths: _SaveableView paths.\u001b[39;00m\n\u001b[1;32m   1679\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m   1681\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m save_context\u001b[38;5;241m.\u001b[39msave_context(options):\n\u001b[0;32m-> 1682\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m _build_meta_graph_impl(obj, signatures, options, meta_graph_def)\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/saved_model/save.py:1604\u001b[0m, in \u001b[0;36m_build_meta_graph_impl\u001b[0;34m(obj, signatures, options, meta_graph_def)\u001b[0m\n\u001b[1;32m   1601\u001b[0m augmented_graph_view\u001b[38;5;241m.\u001b[39mset_signature(signature_map, wrapped_functions)\n\u001b[1;32m   1603\u001b[0m \u001b[38;5;66;03m# Use _SaveableView to provide a frozen listing of properties and functions.\u001b[39;00m\n\u001b[0;32m-> 1604\u001b[0m saveable_view \u001b[38;5;241m=\u001b[39m _SaveableView(augmented_graph_view, options)\n\u001b[1;32m   1605\u001b[0m object_saver \u001b[38;5;241m=\u001b[39m checkpoint\u001b[38;5;241m.\u001b[39mTrackableSaver(augmented_graph_view)\n\u001b[1;32m   1606\u001b[0m asset_info, exported_graph \u001b[38;5;241m=\u001b[39m _fill_meta_graph_def(\n\u001b[1;32m   1607\u001b[0m     meta_graph_def\u001b[38;5;241m=\u001b[39mmeta_graph_def,\n\u001b[1;32m   1608\u001b[0m     saveable_view\u001b[38;5;241m=\u001b[39msaveable_view,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1614\u001b[0m     defaults\u001b[38;5;241m=\u001b[39mdefaults,\n\u001b[1;32m   1615\u001b[0m )\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/saved_model/save.py:285\u001b[0m, in \u001b[0;36m_SaveableView.__init__\u001b[0;34m(self, augmented_graph_view, options)\u001b[0m\n\u001b[1;32m    280\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maugmented_graph_view \u001b[38;5;241m=\u001b[39m augmented_graph_view\n\u001b[1;32m    281\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions \u001b[38;5;241m=\u001b[39m options\n\u001b[1;32m    283\u001b[0m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_trackable_objects, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnode_paths, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnode_ids,\n\u001b[1;32m    284\u001b[0m  \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_slot_variables, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mobject_names) \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 285\u001b[0m      checkpoint_util\u001b[38;5;241m.\u001b[39mobjects_ids_and_slot_variables_and_paths(\n\u001b[1;32m    286\u001b[0m          \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maugmented_graph_view))\n\u001b[1;32m    288\u001b[0m untraced_functions \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maugmented_graph_view\u001b[38;5;241m.\u001b[39muntraced_functions\n\u001b[1;32m    289\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m untraced_functions:\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/checkpoint/util.py:160\u001b[0m, in \u001b[0;36mobjects_ids_and_slot_variables_and_paths\u001b[0;34m(graph_view, skip_slot_variables)\u001b[0m\n\u001b[1;32m    142\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mobjects_ids_and_slot_variables_and_paths\u001b[39m(graph_view,\n\u001b[1;32m    143\u001b[0m                                              skip_slot_variables\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[1;32m    144\u001b[0m \u001b[38;5;250m  \u001b[39m\u001b[38;5;124;03m\"\"\"Traverse the object graph and list all accessible objects.\u001b[39;00m\n\u001b[1;32m    145\u001b[0m \n\u001b[1;32m    146\u001b[0m \u001b[38;5;124;03m  Looks for `Trackable` objects which are dependencies of\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    158\u001b[0m \u001b[38;5;124;03m                object -> node id, slot variables, object_names)\u001b[39;00m\n\u001b[1;32m    159\u001b[0m \u001b[38;5;124;03m  \"\"\"\u001b[39;00m\n\u001b[0;32m--> 160\u001b[0m   trackable_objects, node_paths \u001b[38;5;241m=\u001b[39m graph_view\u001b[38;5;241m.\u001b[39mbreadth_first_traversal()\n\u001b[1;32m    161\u001b[0m   object_names \u001b[38;5;241m=\u001b[39m object_identity\u001b[38;5;241m.\u001b[39mObjectIdentityDictionary()\n\u001b[1;32m    162\u001b[0m   \u001b[38;5;28;01mfor\u001b[39;00m obj, path \u001b[38;5;129;01min\u001b[39;00m node_paths\u001b[38;5;241m.\u001b[39mitems():\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/checkpoint/graph_view.py:124\u001b[0m, in \u001b[0;36mObjectGraphView.breadth_first_traversal\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    123\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mbreadth_first_traversal\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[0;32m--> 124\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_breadth_first_traversal()\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/saved_model/save.py:156\u001b[0m, in \u001b[0;36m_AugmentedGraphView._breadth_first_traversal\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    151\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Returns all trackable objects in the SavedObjectGraph.\"\"\"\u001b[39;00m\n\u001b[1;32m    152\u001b[0m \u001b[38;5;66;03m# This method is overriden to merge all equivalent constant tensors and\u001b[39;00m\n\u001b[1;32m    153\u001b[0m \u001b[38;5;66;03m# Assets in the object graph.\u001b[39;00m\n\u001b[1;32m    155\u001b[0m trackable_objects, _ \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 156\u001b[0m     \u001b[38;5;28msuper\u001b[39m(_AugmentedGraphView, \u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39m_breadth_first_traversal())\n\u001b[1;32m    158\u001b[0m asset_paths \u001b[38;5;241m=\u001b[39m object_identity\u001b[38;5;241m.\u001b[39mObjectIdentityDictionary()\n\u001b[1;32m    159\u001b[0m constant_captures \u001b[38;5;241m=\u001b[39m object_identity\u001b[38;5;241m.\u001b[39mObjectIdentityDictionary()\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/checkpoint/graph_view.py:128\u001b[0m, in \u001b[0;36mObjectGraphView._breadth_first_traversal\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    126\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_breadth_first_traversal\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m    127\u001b[0m \u001b[38;5;250m  \u001b[39m\u001b[38;5;124;03m\"\"\"Find shortest paths to all dependencies of self.root.\"\"\"\u001b[39;00m\n\u001b[0;32m--> 128\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m(ObjectGraphView, \u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39m_descendants_with_paths()\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/checkpoint/trackable_view.py:111\u001b[0m, in \u001b[0;36mTrackableView._descendants_with_paths\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    109\u001b[0m current_trackable \u001b[38;5;241m=\u001b[39m to_visit\u001b[38;5;241m.\u001b[39mpopleft()\n\u001b[1;32m    110\u001b[0m bfs_sorted\u001b[38;5;241m.\u001b[39mappend(current_trackable)\n\u001b[0;32m--> 111\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m name, dependency \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mchildren(current_trackable)\u001b[38;5;241m.\u001b[39mitems():\n\u001b[1;32m    112\u001b[0m   \u001b[38;5;28;01mif\u001b[39;00m dependency \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m node_paths:\n\u001b[1;32m    113\u001b[0m     node_paths[dependency] \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    114\u001b[0m         node_paths[current_trackable] \u001b[38;5;241m+\u001b[39m\n\u001b[1;32m    115\u001b[0m         (base\u001b[38;5;241m.\u001b[39mTrackableReference(name, dependency),))\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/checkpoint/graph_view.py:97\u001b[0m, in \u001b[0;36mObjectGraphView.children\u001b[0;34m(self, obj, save_type, **kwargs)\u001b[0m\n\u001b[1;32m     86\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Returns all child trackables attached to obj.\u001b[39;00m\n\u001b[1;32m     87\u001b[0m \n\u001b[1;32m     88\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     94\u001b[0m \u001b[38;5;124;03m  Dictionary of all children attached to the object with name to trackable.\u001b[39;00m\n\u001b[1;32m     95\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m     96\u001b[0m children \u001b[38;5;241m=\u001b[39m {}\n\u001b[0;32m---> 97\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m name, ref \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlist_children(obj, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m     98\u001b[0m   children[name] \u001b[38;5;241m=\u001b[39m ref\n\u001b[1;32m     99\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m children\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/saved_model/save.py:190\u001b[0m, in \u001b[0;36m_AugmentedGraphView.list_children\u001b[0;34m(self, obj)\u001b[0m\n\u001b[1;32m    187\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m obj \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_children_cache:\n\u001b[1;32m    188\u001b[0m   children \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_children_cache[obj] \u001b[38;5;241m=\u001b[39m {}\n\u001b[0;32m--> 190\u001b[0m   \u001b[38;5;28;01mfor\u001b[39;00m name, child \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28msuper\u001b[39m(_AugmentedGraphView, \u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39mlist_children(\n\u001b[1;32m    191\u001b[0m       obj,\n\u001b[1;32m    192\u001b[0m       save_type\u001b[38;5;241m=\u001b[39mbase\u001b[38;5;241m.\u001b[39mSaveType\u001b[38;5;241m.\u001b[39mSAVEDMODEL,\n\u001b[1;32m    193\u001b[0m       cache\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_serialization_cache):\n\u001b[1;32m    194\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(child, defun\u001b[38;5;241m.\u001b[39mConcreteFunction):\n\u001b[1;32m    195\u001b[0m       child \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_maybe_uncache_variable_captures(child)\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/checkpoint/graph_view.py:75\u001b[0m, in \u001b[0;36mObjectGraphView.list_children\u001b[0;34m(self, obj, save_type, **kwargs)\u001b[0m\n\u001b[1;32m     64\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Returns list of all child trackables attached to obj.\u001b[39;00m\n\u001b[1;32m     65\u001b[0m \n\u001b[1;32m     66\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     72\u001b[0m \u001b[38;5;124;03m  List of all children attached to the object.\u001b[39;00m\n\u001b[1;32m     73\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m     74\u001b[0m children \u001b[38;5;241m=\u001b[39m []\n\u001b[0;32m---> 75\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m name, ref \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28msuper\u001b[39m(ObjectGraphView,\n\u001b[1;32m     76\u001b[0m                        \u001b[38;5;28mself\u001b[39m)\u001b[38;5;241m.\u001b[39mchildren(obj, save_type, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\u001b[38;5;241m.\u001b[39mitems():\n\u001b[1;32m     77\u001b[0m   children\u001b[38;5;241m.\u001b[39mappend(base\u001b[38;5;241m.\u001b[39mTrackableReference(name, ref))\n\u001b[1;32m     79\u001b[0m \u001b[38;5;66;03m# GraphView objects may define children of the root object that are not\u001b[39;00m\n\u001b[1;32m     80\u001b[0m \u001b[38;5;66;03m# actually attached, e.g. a Checkpoint object's save_counter.\u001b[39;00m\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/checkpoint/trackable_view.py:85\u001b[0m, in \u001b[0;36mTrackableView.children\u001b[0;34m(cls, obj, save_type, **kwargs)\u001b[0m\n\u001b[1;32m     83\u001b[0m children \u001b[38;5;241m=\u001b[39m {}\n\u001b[1;32m     84\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m name, ref \u001b[38;5;129;01min\u001b[39;00m obj\u001b[38;5;241m.\u001b[39m_trackable_children(save_type, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\u001b[38;5;241m.\u001b[39mitems():\n\u001b[0;32m---> 85\u001b[0m   ref \u001b[38;5;241m=\u001b[39m converter\u001b[38;5;241m.\u001b[39mconvert_to_trackable(ref, parent\u001b[38;5;241m=\u001b[39mobj)\n\u001b[1;32m     86\u001b[0m   children[name] \u001b[38;5;241m=\u001b[39m ref\n\u001b[1;32m     87\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m children\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/trackable/converter.py:31\u001b[0m, in \u001b[0;36mconvert_to_trackable\u001b[0;34m(obj, parent)\u001b[0m\n\u001b[1;32m     29\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m obj\n\u001b[1;32m     30\u001b[0m obj \u001b[38;5;241m=\u001b[39m data_structures\u001b[38;5;241m.\u001b[39mwrap_or_unwrap(obj)\n\u001b[0;32m---> 31\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (tensor_util\u001b[38;5;241m.\u001b[39mis_tf_type(obj) \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[1;32m     32\u001b[0m     obj\u001b[38;5;241m.\u001b[39mdtype \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m (dtypes\u001b[38;5;241m.\u001b[39mvariant, dtypes\u001b[38;5;241m.\u001b[39mresource) \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[1;32m     33\u001b[0m     \u001b[38;5;129;01mnot\u001b[39;00m resource_variable_ops\u001b[38;5;241m.\u001b[39mis_resource_variable(obj)):\n\u001b[1;32m     34\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m saved_model_utils\u001b[38;5;241m.\u001b[39mTrackableConstant(obj, parent)\n\u001b[1;32m     35\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(obj, base\u001b[38;5;241m.\u001b[39mTrackable):\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/site-packages/tensorflow/python/framework/tensor_util.py:1156\u001b[0m, in \u001b[0;36mis_tf_type\u001b[0;34m(x)\u001b[0m\n\u001b[1;32m   1128\u001b[0m \u001b[38;5;129m@tf_export\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mis_tensor\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m   1129\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mis_tf_type\u001b[39m(x):  \u001b[38;5;66;03m# pylint: disable=invalid-name\u001b[39;00m\n\u001b[1;32m   1130\u001b[0m \u001b[38;5;250m  \u001b[39m\u001b[38;5;124;03m\"\"\"Checks whether `x` is a TF-native type that can be passed to many TF ops.\u001b[39;00m\n\u001b[1;32m   1131\u001b[0m \n\u001b[1;32m   1132\u001b[0m \u001b[38;5;124;03m  Use `is_tensor` to differentiate types that can ingested by TensorFlow ops\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1154\u001b[0m \u001b[38;5;124;03m    `True` if `x` is a TensorFlow-native type.\u001b[39;00m\n\u001b[1;32m   1155\u001b[0m \u001b[38;5;124;03m  \"\"\"\u001b[39;00m\n\u001b[0;32m-> 1156\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(x, tf_type_classes)\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/typing.py:1871\u001b[0m, in \u001b[0;36m_ProtocolMeta.__instancecheck__\u001b[0;34m(cls, instance)\u001b[0m\n\u001b[1;32m   1869\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m attr \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m__protocol_attrs__:\n\u001b[1;32m   1870\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1871\u001b[0m         val \u001b[38;5;241m=\u001b[39m getattr_static(instance, attr)\n\u001b[1;32m   1872\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m:\n\u001b[1;32m   1873\u001b[0m         \u001b[38;5;28;01mbreak\u001b[39;00m\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/inspect.py:1839\u001b[0m, in \u001b[0;36mgetattr_static\u001b[0;34m(obj, attr, default)\u001b[0m\n\u001b[1;32m   1836\u001b[0m     dict_attr \u001b[38;5;241m=\u001b[39m _shadowed_dict(klass)\n\u001b[1;32m   1837\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m (dict_attr \u001b[38;5;129;01mis\u001b[39;00m _sentinel \u001b[38;5;129;01mor\u001b[39;00m\n\u001b[1;32m   1838\u001b[0m         \u001b[38;5;28mtype\u001b[39m(dict_attr) \u001b[38;5;129;01mis\u001b[39;00m types\u001b[38;5;241m.\u001b[39mMemberDescriptorType):\n\u001b[0;32m-> 1839\u001b[0m         instance_result \u001b[38;5;241m=\u001b[39m _check_instance(obj, attr)\n\u001b[1;32m   1840\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1841\u001b[0m     klass \u001b[38;5;241m=\u001b[39m obj\n",
            "File \u001b[0;32m/media/pc/data/lxw/envs/anaconda3x/envs/xxx/lib/python3.12/inspect.py:1793\u001b[0m, in \u001b[0;36m_check_instance\u001b[0;34m(obj, attr)\u001b[0m\n\u001b[1;32m   1791\u001b[0m instance_dict \u001b[38;5;241m=\u001b[39m {}\n\u001b[1;32m   1792\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1793\u001b[0m     instance_dict \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mobject\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__getattribute__\u001b[39m(obj, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m__dict__\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m   1794\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mAttributeError\u001b[39;00m:\n\u001b[1;32m   1795\u001b[0m     \u001b[38;5;28;01mpass\u001b[39;00m\n",
            "\u001b[0;31mTypeError\u001b[0m: this __dict__ descriptor does not support '_DictWrapper' objects"
          ]
        }
      ],
      "source": [
        "mobilenet_save_path = os.path.join(tmpdir, \"mobilenet/1/\")\n",
        "tf.saved_model.save(pretrained_model, mobilenet_save_path)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "pyX-ETE3wX63"
      },
      "source": [
        "保存路径遵循 TensorFlow Serving 使用的惯例，路径的最后一个部分（此处为 `1/`）是模型的版本号：它可以让 Tensorflow Serving 之类的工具推断相对新鲜度。\n",
        "\n",
        "您可以使用 `tf.saved_model.load` 将 SavedModel 加载回 Python，并查看 Admiral Hopper 的图像是如何分类的。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "NP2UpVFRV7N_"
      },
      "outputs": [],
      "source": [
        "loaded = tf.saved_model.load(mobilenet_save_path)\n",
        "print(list(loaded.signatures.keys()))  # [\"serving_default\"]"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "K5srGzowfWff"
      },
      "source": [
        "导入的签名总是会返回字典。要自定义签名名称和输出字典键，请参阅[在导出过程中指定签名](#specifying_signatures_during_export)。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ChFLpegYfQGR"
      },
      "outputs": [],
      "source": [
        "infer = loaded.signatures[\"serving_default\"]\n",
        "print(infer.structured_outputs)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cJYyZnptfuru"
      },
      "source": [
        "从 SavedModel 运行推断会产生与原始模型相同的结果。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "9WjGEaS3XfX7"
      },
      "outputs": [],
      "source": [
        "labeling = infer(tf.constant(x))[pretrained_model.output_names[0]]\n",
        "\n",
        "decoded = imagenet_labels[np.argsort(labeling)[0,::-1][:5]+1]\n",
        "\n",
        "print(\"Result after saving and loading:\\n\", decoded)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SJEkdXjTWbtl"
      },
      "source": [
        "## 在 TensorFlow Serving 中运行 SavedModel\n",
        "\n",
        "可以通过 Python 使用 SavedModel（下文中有详细介绍），但是，生产环境通常会使用专门服务进行推断，而不会运行 Python 代码。使用 TensorFlow Serving 时，这很容易从 SavedModel 进行设置。\n",
        "\n",
        "请参阅 [TensorFlow Serving REST 教程](https://tensorflow.google.cn/tfx/tutorials/serving/rest_simple)了解端到端 tensorflow-serving 示例。"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Bi0ILzu1XdWw"
      },
      "source": [
        "## 磁盘上的 SavedModel 格式\n",
        "\n",
        "SavedModel 是一个包含序列化签名和运行这些签名所需的状态的目录，其中包括变量值和词汇。\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "6u3YZuYZXyTO"
      },
      "outputs": [],
      "source": [
        "!ls {mobilenet_save_path}"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ple4X5utX8ue"
      },
      "source": [
        "`saved_model.pb` 文件用于存储实际 TensorFlow 程序或模型，以及一组已命名的签名，每个签名标识一个接受张量输入和产生张量输出的函数。\n",
        "\n",
        "SavedModel 可能包含模型的多个变体（多个 `v1.MetaGraphDefs`，通过 `saved_model_cli` 的 `--tag_set` 标志进行标识），但这种情况很少见。可以为模型创建多个变体的 API 包括 [`tf.Estimator.experimental_export_all_saved_models`](https://tensorflow.google.cn/api_docs/python/tf/estimator/Estimator#experimental_export_all_saved_models) 和 TensorFlow 1.x 中的 `tf.saved_model.Builder`。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Pus0dOYTYXbI"
      },
      "outputs": [],
      "source": [
        "!saved_model_cli show --dir {mobilenet_save_path} --tag_set serve"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eALHpGvRZOhk"
      },
      "source": [
        "`variables` 目录包含一个标准训练检查点（参阅[训练检查点指南](./checkpoint.ipynb)）。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "EDYqhDlNZAC2"
      },
      "outputs": [],
      "source": [
        "!ls {mobilenet_save_path}/variables"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VKmaZQpHahGh"
      },
      "source": [
        "`assets` 目录包含 TensorFlow 计算图使用的文件，例如，用于初始化词汇表的文本文件。本例中没有使用这种文件。\n",
        "\n",
        "SavedModel 可能有一个用于保存 TensorFlow 计算图未使用的任何文件的 `assets.extra` 目录，例如，为使用者提供的关于如何处理 SavedModel 的信息。TensorFlow 本身并不会使用此目录。\n",
        "\n",
        "`fingerprint.pb` 文件包含 SavedModel 的[指纹](https://en.wikipedia.org/wiki/Fingerprint_(computing))，它由几个 64 位哈希组成，以唯一的方式标识 SavedModel 的内容。指纹 API 目前处于实验阶段，但 `tf.saved_model.experimental.read_fingerprint` 可以用于将 SavedModel 指纹读取到 `tf.saved_model.experimental.Fingerprint` 对象中。"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zIceoF_CYmaF"
      },
      "source": [
        "## 保存自定义模型\n",
        "\n",
        "`tf.saved_model.save` 支持保存 `tf.Module` 对象及其子类，如 `tf.keras.Layer` 和 `tf.keras.Model`。\n",
        "\n",
        "我们来看一个保存和恢复 `tf.Module` 的示例。\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "6EPvKiqXMm3d"
      },
      "outputs": [],
      "source": [
        "class CustomModule(tf.Module):\n",
        "\n",
        "  def __init__(self):\n",
        "    super(CustomModule, self).__init__()\n",
        "    self.v = tf.Variable(1.)\n",
        "\n",
        "  @tf.function\n",
        "  def __call__(self, x):\n",
        "    print('Tracing with', x)\n",
        "    return x * self.v\n",
        "\n",
        "  @tf.function(input_signature=[tf.TensorSpec([], tf.float32)])\n",
        "  def mutate(self, new_v):\n",
        "    self.v.assign(new_v)\n",
        "\n",
        "module = CustomModule()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "J4FcP-Co3Fnw"
      },
      "source": [
        "当您保存 `tf.Module` 时，任何 `tf.Variable` 特性、`tf.function` 装饰的方法以及通过递归遍历找到的 `tf.Module` 都会得到保存。（参阅[检查点教程](./checkpoint.ipynb)，了解此递归遍历的详细信息。）但是，所有 Python 特性、函数和数据都会丢失。也就是说，当您保存 `tf.function` 时，不会保存 Python 代码。\n",
        "\n",
        "如果不保存 Python 代码，SavedModel 如何知道怎样恢复函数？\n",
        "\n",
        "简单地说，`tf.function` 的工作原理是，通过跟踪 Python 代码来生成 ConcreteFunction（一个可调用的 `tf.Graph` 封装容器）。当您保存 `tf.function` 时，实际上保存的是 `tf.function` 的 ConcreteFunction 缓存。\n",
        "\n",
        "要详细了解 `tf.function` 与 ConcreteFunction 之间的关系，请参阅 [tf.function 指南](function.ipynb)。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "85PUO9iWH7xn"
      },
      "outputs": [],
      "source": [
        "module_no_signatures_path = os.path.join(tmpdir, 'module_no_signatures')\n",
        "module(tf.constant(0.))\n",
        "print('Saving model...')\n",
        "tf.saved_model.save(module, module_no_signatures_path)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2ujwmMQg7OUo"
      },
      "source": [
        "## 加载和使用自定义模型"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "QpxQy5Eb77qJ"
      },
      "source": [
        "在 Python 中加载 SavedModel 时，所有 `tf.Variable` 特性、`tf.function` 装饰方法和 `tf.Module` 都会按照与原始保存的 `tf.Module` 相同的对象结构进行恢复。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "EMASjADPxPso"
      },
      "outputs": [],
      "source": [
        "imported = tf.saved_model.load(module_no_signatures_path)\n",
        "assert imported(tf.constant(3.)).numpy() == 3\n",
        "imported.mutate(tf.constant(2.))\n",
        "assert imported(tf.constant(3.)).numpy() == 6"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CDiauvb_99uk"
      },
      "source": [
        "由于没有保存 Python 代码，所以使用新输入签名调用 `tf.function` 会失败：\n",
        "\n",
        "```python\n",
        "imported(tf.constant([3.]))\n",
        "```\n",
        "\n",
        "<pre>ValueError: Could not find matching function to call for canonicalized inputs ((&lt;tf.Tensor 'args_0:0' shape=(1,) dtype=float32&gt;,), {}). Only existing signatures are [((TensorSpec(shape=(), dtype=tf.float32, name=u'x'),), {})].\n",
        "</pre>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4Vsva3UZ-2sf"
      },
      "source": [
        "### 基本微调\n",
        "\n",
        "可以使用变量对象，还可以通过导入的函数向后传播。对于简单情形，这足以支持 SavedModel 的微调（即重新训练）。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "PEkQNarJ-7nT"
      },
      "outputs": [],
      "source": [
        "optimizer = tf.keras.optimizers.SGD(0.05)\n",
        "\n",
        "def train_step():\n",
        "  with tf.GradientTape() as tape:\n",
        "    loss = (10. - imported(tf.constant(2.))) ** 2\n",
        "  variables = tape.watched_variables()\n",
        "  grads = tape.gradient(loss, variables)\n",
        "  optimizer.apply_gradients(zip(grads, variables))\n",
        "  return loss"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "p41NM6fF---3"
      },
      "outputs": [],
      "source": [
        "for _ in range(10):\n",
        "  # \"v\" approaches 5, \"loss\" approaches 0\n",
        "  print(\"loss={:.2f} v={:.2f}\".format(train_step(), imported.v.numpy()))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "XuXtkHSD_KSW"
      },
      "source": [
        "### 一般微调\n",
        "\n",
        "与普通 `__call__` 相比，Keras 的 SavedModel 提供了[更多详细信息](https://github.com/tensorflow/community/blob/master/rfcs/20190509-keras-saved-model.md#serialization-details)来解决更复杂的微调情形。TensorFlow Hub 建议在共享的 SavedModel 中提供以下详细信息（如果适用），以便进行微调：\n",
        "\n",
        "- 如果模型使用随机失活，或者是训练与推断之间的前向传递不同的另一种技术（如批次归一化），则 `__call__` 方法会获取一个可选的 Python 值 `training=` 参数。该参数的默认值为 `False`，但可将其设置为 `True`。\n",
        "- 对于变量的对应列表，除了 `__call__` 特性，还有 `.variable` 和 `.trainable_variable` 特性。在微调过程中，`.trainable_variables` 省略了一个变量，该变量原本可训练，但打算将其冻结。\n",
        "- 对于 Keras 等将权重正则化项表示为层或子模型特性的框架，还有一个 `.regularization_losses` 特性。它包含一个零参数函数的列表，这些函数的值应加到总损失中。\n",
        "\n",
        "回到初始 MobileNet 示例，您可以看到一些具体操作："
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Y6EUFdY8_PRD"
      },
      "outputs": [],
      "source": [
        "loaded = tf.saved_model.load(mobilenet_save_path)\n",
        "print(\"MobileNet has {} trainable variables: {}, ...\".format(\n",
        "          len(loaded.trainable_variables),\n",
        "          \", \".join([v.name for v in loaded.trainable_variables[:5]])))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "B-mQJ8iP_R0h"
      },
      "outputs": [],
      "source": [
        "trainable_variable_ids = {id(v) for v in loaded.trainable_variables}\n",
        "non_trainable_variables = [v for v in loaded.variables\n",
        "                           if id(v) not in trainable_variable_ids]\n",
        "print(\"MobileNet also has {} non-trainable variables: {}, ...\".format(\n",
        "          len(non_trainable_variables),\n",
        "          \", \".join([v.name for v in non_trainable_variables[:3]])))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qGlHlbd3_eyO"
      },
      "source": [
        "## 导出时指定签名\n",
        "\n",
        "TensorFlow Serving 之类的工具和 `saved_model_cli` 可以与 SavedModel 交互。为了帮助这些工具确定要使用的 ConcreteFunction，我们需要指定应用签名。`tf.keras.Model` 会自动指定应用签名，但是，对于自定义模块，我们必须明确声明应用签名。\n",
        "\n",
        "重要提示：除非您需要使用 Python 将模型导出到 TensorFlow 2.x 之外的环境，否则您不需要明确导出签名。如果您在寻找为特定函数强制输入签名的方式，请参阅 `tf.function` 的 [`input_signature`](https://tensorflow.google.cn/api_docs/python/tf/function#args_1) 参数。\n",
        "\n",
        "默认情况下，自定义 `tf.Module` 中不会声明签名。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "h-IB5Xa0NxLa"
      },
      "outputs": [],
      "source": [
        "assert len(imported.signatures) == 0"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "BiNtaMZSI8Tb"
      },
      "source": [
        "要声明应用签名，请使用 `signatures` 关键字参数指定 ConcreteFunction。指定单个签名时，签名键为 `'serving_default'`，并将保存为常量 `tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY`。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "_pAdgIORR2yH"
      },
      "outputs": [],
      "source": [
        "module_with_signature_path = os.path.join(tmpdir, 'module_with_signature')\n",
        "call = module.__call__.get_concrete_function(tf.TensorSpec(None, tf.float32))\n",
        "tf.saved_model.save(module, module_with_signature_path, signatures=call)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "nAzRHR0UT4hv"
      },
      "outputs": [],
      "source": [
        "imported_with_signatures = tf.saved_model.load(module_with_signature_path)\n",
        "list(imported_with_signatures.signatures.keys())\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_gH91j1IR4tq"
      },
      "source": [
        "要导出多个签名，请将签名键的字典传递给 ConcreteFunction。每个签名键对应一个 ConcreteFunction。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "6VYAiQmLUiox"
      },
      "outputs": [],
      "source": [
        "module_multiple_signatures_path = os.path.join(tmpdir, 'module_with_multiple_signatures')\n",
        "signatures = {\"serving_default\": call,\n",
        "              \"array_input\": module.__call__.get_concrete_function(tf.TensorSpec([None], tf.float32))}\n",
        "\n",
        "tf.saved_model.save(module, module_multiple_signatures_path, signatures=signatures)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "8IPx_0RWEx07"
      },
      "outputs": [],
      "source": [
        "imported_with_multiple_signatures = tf.saved_model.load(module_multiple_signatures_path)\n",
        "list(imported_with_multiple_signatures.signatures.keys())"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "43_Qv2W_DJZZ"
      },
      "source": [
        "默认情况下，输出张量名称非常通用，如 `output_0`。为了控制输出的名称，请修改 `tf.function`，以便返回将输出名称映射到输出的字典。输入的名称来自 Python 函数参数名称。"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ACKPl1X8G1gw"
      },
      "outputs": [],
      "source": [
        "class CustomModuleWithOutputName(tf.Module):\n",
        "  def __init__(self):\n",
        "    super(CustomModuleWithOutputName, self).__init__()\n",
        "    self.v = tf.Variable(1.)\n",
        "\n",
        "  @tf.function(input_signature=[tf.TensorSpec(None, tf.float32)])\n",
        "  def __call__(self, x):\n",
        "    return {'custom_output_name': x * self.v}\n",
        "\n",
        "module_output = CustomModuleWithOutputName()\n",
        "call_output = module_output.__call__.get_concrete_function(tf.TensorSpec(None, tf.float32))\n",
        "module_output_path = os.path.join(tmpdir, 'module_with_output_name')\n",
        "tf.saved_model.save(module_output, module_output_path,\n",
        "                    signatures={'serving_default': call_output})"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "1yGVy4MuH-V0"
      },
      "outputs": [],
      "source": [
        "imported_with_output_name = tf.saved_model.load(module_output_path)\n",
        "imported_with_output_name.signatures['serving_default'].structured_outputs"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Q4bCK55x1IBW"
      },
      "source": [
        "## proto 分割\n",
        "\n",
        "注：此功能将成为 TensorFlow 2.15 版本的一部分。它目前在 Nightly 版本中提供，您可以使用 `pip install tf-nightly` 进行安装。\n",
        "\n",
        "由于 protobuf 实现的限制，proto 的大小不能超过 2GB。在尝试保存非常大的模型时，这可能会导致以下错误：\n",
        "\n",
        "```\n",
        "ValueError: Message tensorflow.SavedModel exceeds maximum protobuf size of 2GB: ...\n",
        "```\n",
        "\n",
        "```\n",
        "google.protobuf.message.DecodeError: Error parsing message as the message exceeded the protobuf limit with type 'tensorflow.GraphDef'\n",
        "```\n",
        "\n",
        "如果您希望保存超过 2GB 限制的模型，则需要使用新的 proto 分割选项进行保存：\n",
        "\n",
        "```python\n",
        "tf.saved_model.save(\n",
        "  ...,\n",
        "  options=tf.saved_model.SaveOptions(experimental_image_format=True)\n",
        ")\n",
        "```\n",
        "\n",
        "更多信息，请参阅 [Proto 分割器/合并器库指南](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/tools/proto_splitter/in-depth-guide.md)。"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Co6fDbzw_UnD"
      },
      "source": [
        "## 在 C++ 中加载  SavedModel\n",
        "\n",
        "SavedModel [加载器](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/cc/saved_model/loader.h)的 C++ 版本提供了一个从路径中加载 SavedModel 的 API，同时允许使用 SessionOption 和 RunOption。您必须指定与计算图相关联的标记才能加载模型。加载的 SavedModel 版本称为 SavedModelBundle，其中包含 MetaGraphDef 以及加载该版本所处的会话。\n",
        "\n",
        "```C++\n",
        "const string export_dir = ...\n",
        "SavedModelBundle bundle;\n",
        "...\n",
        "LoadSavedModel(session_options, run_options, export_dir, {kSavedModelTagTrain},\n",
        "               &amp;bundle);\n",
        "```"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "b33KuyEuAO3Z"
      },
      "source": [
        "<a id=\"saved_model_cli\"></a>\n",
        "\n",
        "## SavedModel 命令行接口详细信息\n",
        "\n",
        "您可以使用 SavedModel 命令行接口 (CLI) 检查和执行 SavedModel。例如，您可以使用 CLI 来检查模型的 `SignatureDef`。通过 CLI，您可以快速确认与模型相符的输入张量的 dtype 和形状。此外，如果要测试模型，您可以传入各种格式的样本输入（例如，Python 表达式），然后获取输出，使用 CLI 执行健全性检查。\n",
        "\n",
        "### 安装 SavedModel CLI\n",
        "\n",
        "一般来说，通过以下两种方式都可以安装 TensorFlow：\n",
        "\n",
        "- 安装预构建的 TensorFlow 二进制文件。\n",
        "- 从源代码构建 TensorFlow。\n",
        "\n",
        "如果您是通过预构建的 TensorFlow 二进制文件安装的 TensorFlow，则 SavedModel CLI 已安装到您的系统上，路径为 `bin/saved_model_cli`。\n",
        "\n",
        "如果是从源代码构建的 TensorFlow，则还必须运行以下附加命令才能构建 `saved_model_cli`：\n",
        "\n",
        "```\n",
        "$ bazel build //tensorflow/python/tools:saved_model_cli\n",
        "```\n",
        "\n",
        "### 命令概述\n",
        "\n",
        "SavedModel CLI 支持在 SavedModel 上使用以下两个命令：\n",
        "\n",
        "- `show`：用于显示 SavedModel 中可用的计算。\n",
        "- `run`：用于从 SavedModel 运行计算。\n",
        "\n",
        "### `show` 命令\n",
        "\n",
        "SavedModel 包含一个或多个模型变体（从技术上说，为 `v1.MetaGraphDef`），这些变体通过 tag-set 进行标识。要应用模型，您可能想知道每个模型变体中使用的具体是哪一种 `SignatureDef` ，以及它们的输入和输出是什么。那么，利用 `show` 命令，您就可以按照层级顺序检查 SavedModel 的内容。具体语法如下：\n",
        "\n",
        "```\n",
        "usage: saved_model_cli show [-h] --dir DIR [--all]\n",
        "[--tag_set TAG_SET] [--signature_def SIGNATURE_DEF_KEY]\n",
        "```\n",
        "\n",
        "例如，以下命令会显示 SavedModel 中的所有可用 tag-set：\n",
        "\n",
        "```\n",
        "$ saved_model_cli show --dir /tmp/saved_model_dir\n",
        "The given SavedModel contains the following tag-sets:\n",
        "serve\n",
        "serve, gpu\n",
        "```\n",
        "\n",
        "以下命令会显示 tag-set 的所有可用 `SignatureDef` 键：\n",
        "\n",
        "```\n",
        "$ saved_model_cli show --dir /tmp/saved_model_dir --tag_set serve The given SavedModel `MetaGraphDef` contains `SignatureDefs` with the following keys: SignatureDef key: \"classify_x2_to_y3\" SignatureDef key: \"classify_x_to_y\" SignatureDef key: \"regress_x2_to_y3\" SignatureDef key: \"regress_x_to_y\" SignatureDef key: \"regress_x_to_y2\" SignatureDef key: \"serving_default\"\n",
        "```\n",
        "\n",
        "如果 tag-set 中有*多个*标记，则必须指定所有标记（标记之间用逗号分隔）。例如：\n",
        "\n",
        "<pre>$ saved_model_cli show --dir /tmp/saved_model_dir --tag_set serve,gpu</pre>\n",
        "\n",
        "要显示特定 `SignatureDef` 的所有输入和输出 TensorInfo，请将 `SignatureDef` 键传递给 `signature_def` 选项。如果您想知道输入张量的张量键值、dtype 和形状，以便随后执行计算图，这会非常有用。例如：\n",
        "\n",
        "```\n",
        "$ saved_model_cli show --dir \\ /tmp/saved_model_dir --tag_set serve --signature_def serving_default The given SavedModel SignatureDef contains the following input(s):   inputs['x'] tensor_info:       dtype: DT_FLOAT       shape: (-1, 1)       name: x:0 The given SavedModel SignatureDef contains the following output(s):   outputs['y'] tensor_info:       dtype: DT_FLOAT       shape: (-1, 1)       name: y:0 Method name is: tensorflow/serving/predict\n",
        "```\n",
        "\n",
        "要显示 SavedModel 中的所有可用信息，请使用 `--all` 选项。例如：\n",
        "\n",
        "<pre>$ saved_model_cli show --dir /tmp/saved_model_dir --all&lt;br&gt;MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:&lt;br&gt;&lt;br&gt;signature_def['classify_x2_to_y3']:&lt;br&gt;  The given SavedModel SignatureDef contains the following input(s):&lt;br&gt;    inputs['inputs'] tensor_info:&lt;br&gt;        dtype: DT_FLOAT&lt;br&gt;        shape: (-1, 1)&lt;br&gt;        name: x2:0&lt;br&gt;  The given SavedModel SignatureDef contains the following output(s):&lt;br&gt;    outputs['scores'] tensor_info:&lt;br&gt;        dtype: DT_FLOAT&lt;br&gt;        shape: (-1, 1)&lt;br&gt;        name: y3:0&lt;br&gt;  Method name is: tensorflow/serving/classify&lt;br&gt;&lt;br&gt;...&lt;br&gt;&lt;br&gt;signature_def['serving_default']:&lt;br&gt;  The given SavedModel SignatureDef contains the following input(s):&lt;br&gt;    inputs['x'] tensor_info:&lt;br&gt;        dtype: DT_FLOAT&lt;br&gt;        shape: (-1, 1)&lt;br&gt;        name: x:0&lt;br&gt;  The given SavedModel SignatureDef contains the following output(s):&lt;br&gt;    outputs['y'] tensor_info:&lt;br&gt;        dtype: DT_FLOAT&lt;br&gt;        shape: (-1, 1)&lt;br&gt;        name: y:0&lt;br&gt;  Method name is: tensorflow/serving/predict</pre>\n",
        "\n",
        "### `run` 命令\n",
        "\n",
        "调用 `run` 命令即可运行计算图计算，传递输入，然后显示输出，还可以选择保存。具体语法如下：\n",
        "\n",
        "```\n",
        "usage: saved_model_cli run [-h] --dir DIR --tag_set TAG_SET --signature_def\n",
        "                           SIGNATURE_DEF_KEY [--inputs INPUTS]\n",
        "                           [--input_exprs INPUT_EXPRS]\n",
        "                           [--input_examples INPUT_EXAMPLES] [--outdir OUTDIR]\n",
        "                           [--overwrite] [--tf_debug]\n",
        "```\n",
        "\n",
        "要将输入传递给模型，`run` 命令提供了以下三种方式：\n",
        "\n",
        "- `--inputs` 选项：可传递文件中的 NumPy ndarray。\n",
        "- `--input_exprs` 选项：可传递 Python 表达式。\n",
        "- `--input_examples` 选项：可传递 `tf.train.Example`。\n",
        "\n",
        "#### `--inputs`\n",
        "\n",
        "要传递文件中的输入数据，请指定 `--inputs` 选项，一般格式如下：\n",
        "\n",
        "```bsh\n",
        "--inputs <INPUTS>\n",
        "```\n",
        "\n",
        "其中，*INPUTS* 采用以下格式之一：\n",
        "\n",
        "- `<input_key>=<filename>`\n",
        "- `<input_key>=<filename>[<variable_name>]`\n",
        "\n",
        "您可以传递多个 *INPUTS*。如果确实要传递多个输入，请使用分号分隔每个 *INPUTS*。\n",
        "\n",
        "`saved_model_cli` 使用 `numpy.load` 来加载 *filename*。*filename* 可能为以下任何格式：\n",
        "\n",
        "- `.npy`\n",
        "- `.npz`\n",
        "- pickle 格式\n",
        "\n",
        "`.npy` 文件始终包含一个 NumPy ndarray。因此，从 `.npy` 文件加载时，会将内容直接分配给指定的输入张量。如果使用 `.npy` 文件来指定 *variable_name*，则会忽略 *variable_name*，并且会发出警告。\n",
        "\n",
        "从 `.npz` (zip) 文件加载时，您可以选择指定 *variable_name*，以便标识 zip 文件中要为输入张量键加载的变量。如果不指定 *variable_name*，SavedModel CLI 会检查 zip 文件中是否只包含一个文件。如果是，则为指定的输入张量键加载该文件。\n",
        "\n",
        "从 pickle 文件加载时，如果未在方括号中指定 `variable_name`，则会将该 pickle 文件中的任何内容全部传递给指定的输入张量键。否则，SavedModel CLI 会假设该 pickle 文件中有一个字典，并将使用与 *variable_name* 对应的值。\n",
        "\n",
        "#### `--input_exprs`\n",
        "\n",
        "要通过 Python 表达式传递输入，请指定 `--input_exprs` 选项。当您没有现成的数据文件，而又想使用与模型的 `SignatureDef` 的 dtype 和形状相符的一些简单输入来对模型进行健全性检查时，这非常有用。例如：\n",
        "\n",
        "```bsh\n",
        "`<input_key>=[[1],[2],[3]]`\n",
        "```\n",
        "\n",
        "除了 Python 表达式，您还可以传递 NumPy 函数。例如：\n",
        "\n",
        "```bsh\n",
        "`<input_key>=np.ones((32,32,3))`\n",
        "```\n",
        "\n",
        "（请注意，`numpy` 模块已作为 `np` 提供。）\n",
        "\n",
        "#### `--input_examples`\n",
        "\n",
        "要传递 `tf.train.Example` 作为输入，请指定 `--input_examples` 选项。对于每个输入键，它会获取一个字典列表，其中每个字典是 `tf.train.Example` 的一个实例。字典键就是特征，而值则是每个特征的值列表。例如：\n",
        "\n",
        "```bsh\n",
        "`<input_key>=[{\"age\":[22,24],\"education\":[\"BS\",\"MS\"]}]`\n",
        "```\n",
        "\n",
        "#### 保存输出\n",
        "\n",
        "默认情况下，SavedModel CLI 会将输出写入 stdout。如果将字典传递给 `--outdir` 选项，则会将输出保存为以给定字典下的输出张量键命名的 `.npy` 文件。\n",
        "\n",
        "使用 `--overwrite` 可重写现有输出文件。\n"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "name": "saved_model.ipynb",
      "toc_visible": true
    },
    "kernelspec": {
      "display_name": "xxx",
      "language": "python",
      "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": "3.12.2"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}