{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "L30JbHSkiVZx" }, "source": [ "##### Copyright 2021 The TensorFlow Authors." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "cellView": "form", "execution": { "iopub.execute_input": "2022-08-30T23:58:59.271551Z", "iopub.status.busy": "2022-08-30T23:58:59.271210Z", "iopub.status.idle": "2022-08-30T23:58:59.275755Z", "shell.execute_reply": "2022-08-30T23:58:59.275142Z" }, "id": "ZtimvKLdili0" }, "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": "QXdiroR-Ue-Z" }, "source": [ "# 基于 MoveNet 和 TensorFlow Lite 的人体姿势分类\n", "\n", "本笔记本将教您如何使用 MoveNet 和 TensorFlow Lite 训练姿势分类模型。结果是一个新的 TensorFlow Lite 模型,该模型接受来自 MoveNet 模型的输出作为其输入,并输出姿势分类,例如瑜伽姿势的名称。\n", "\n", "本笔记本中的流程由 3 个部分组成:\n", "\n", "- 第 1 部分:将姿势分类训练数据预处理为 CSV 文件,该文件指定 MoveNet 模型检测到的特征点(身体关键点)以及基准真相姿势标签。\n", "- 第 2 部分:构建和训练姿势分类模型,该模型将 CSV 文件中的特征点坐标作为输入,并输出预测的标签。\n", "- 第 3 部分:将姿势分类模型转换为 TFLite。\n", "\n", "默认情况下,此笔记本使用一个带有瑜伽姿势标签的图像数据集,但我们在第 1 部分中也包括了一个部分,在那里你可以上传您自己的姿势图像数据集。\n", "\n", "
![]() | \n",
" ![]() | \n",
" ![]() | \n",
" ![]() | \n",
" ![]() | \n",
"