baidu-ai-search

{ "cells": [ { "cell_type": "markdown", "metadata": { "collapsed": true, "pycharm": { "name": "#%% md\n" } }, "source": [ "# 通用物体和场景识别-高级版组件\n", "\n", "## 目标\n", "使用通用物体和场景识别-高级版组件对图片上的物品或场景进行识别。\n", "\n", "## 准备工作\n", "### 平台注册\n", "1.先在appbuilder平台注册，获取token\n", "\n", "2.安装appbuilder-sdk" ] }, { "cell_type": "code", "execution_count": null, "outputs": [], "source": [ "!pip install appbuilder-sdk" ], "metadata": { "collapsed": false, "pycharm": { "name": "#%%\n" } } }, { "cell_type": "markdown", "source": [ "## 基本用法\n", "\n", "### 快速开始\n", "\n", "以下是一个简单的例子来演示如何开始使用ObjectRecognition组件：" ], "metadata": { "collapsed": false } }, { "cell_type": "code", "execution_count": null, "outputs": [], "source": [ "import os\n", "import appbuilder\n", "import requests\n", "\n", "# 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5\n", "os.environ[\"APPBUILDER_TOKEN\"] = '...'\n", "\n", "# 从BOS读取样例图片\n", "image_url = \"https://bj.bcebos.com/v1/appbuilder/object_recognize_test.png?\"\\\n", " \"authorization=bce-auth-v1%2FALTAKGa8m4qCUasgoljdEDAzLm%2F2024-01-\"\\\n", " \"11T11%3A00%3A19Z%2F-1%2Fhost%2F2c31bf29205f61e58df661dc80af31a1dc\"\\\n", " \"1ba1de0a8f072bc5a87102bd32f9e3\"\n", "raw_image = requests.get(image_url).content\n", "# 创建物体识别组件实例\n", "object_recognition = appbuilder.ObjectRecognition()\n", "# 执行识别操作并获取结果\n", "out = object_recognition.run(appbuilder.Message(content={\"raw_image\": raw_image}))\n", "print(out.content)" ], "metadata": { "collapsed": false, "pycharm": { "name": "#%%\n" } } }, { "cell_type": "markdown", "source": [ "## 参数说明\n", "\n", "### 鉴权说明\n", "使用组件之前，请首先申请并设置鉴权参数，可参考[组件使用流程](https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5)。\n", "```python\n", "# 设置环境中的TOKEN，以下示例略\n", "os.environ[\"APPBUILDER_TOKEN\"] = \"bce-YOURTOKEN\"\n", "```\n", "\n", "### 初始化参数\n", "无\n", "\n", "### 调用参数\n", "\n", "| 参数名称 | 参数类型 | 是否必须 | 描述 | 示例值 |\n", "|---------|---------|------|-----------------------------|------------------------------------------------|\n", "| message | String | 是 | 输入的消息，用于模型的主要输入内容。这是一个必需的参数 | Message(content={\"raw_image\": b\"待识别的图片字节流数据\"}) |\n", "|timeout| Float | 否 | HTTP超时时间,单位：秒 |1|\n", "| retry | Integer | 否 | HTTP重试次数 | 3 |\n", "\n", "### 响应参数\n", "| 参数名称 | 参数类型 | 描述 | 示例值 |\n", "|----------|---------|-------------|-----------------------------------------------------|\n", "| result | Array[] | 返回结果 | [{\"keyword\":\"苹果\",\"score\":0.961247,\"root\":\"植物-蔷薇科\"}] |\n", "| +keyword | String | 图片中的物体或场景名称 | \"苹果\" |\n", "| +score\t | Float | 置信度 | 0.961247 |\n", "| +root\t | String | 识别结果的上层标签 | \"植物-蔷薇科\" |\n", "\n", "\n", "### 响应示例\n", "#### 示例图片\n", "\n", "#### 识别结果\n", "```json\n", "{\n", " \"result\":[\n", " {\n", " \"keyword\":\"苹果\",\n", " \"score\":0.961247,\n", " \"root\":\"植物-蔷薇科\"\n", " },\n", " {\n", " \"keyword\":\"姬娜果\",\n", " \"score\":0.740838,\n", " \"root\":\"植物-其它\"\n", " },\n", " {\n", " \"keyword\":\"梨子\",\n", " \"score\":0.392218,\n", " \"root\":\"商品-水果\"\n", " },\n", " {\n", " \"keyword\":\"车厘子\",\n", " \"score\":0.193986,\n", " \"root\":\"植物-其它\"\n", " },\n", " {\n", " \"keyword\":\"石榴\",\n", " \"score\":0.000239,\n", " \"root\":\"植物-千屈菜科\"\n", " }\n", " ]\n", "}\n", "```\n", "\n", "\n" ], "metadata": { "collapsed": false, "pycharm": { "name": "#%% md\n" } } } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 2 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython2", "version": "2.7.6" } }, "nbformat": 4, "nbformat_minor": 0 }