TensorFlow深度学习框架模型推理Pipeline进行人像抠图推理

2024-03-26码农

概述

为了使ModelScope的用户能够快速、方便的使用平台提供的各类模型，提供了一套功能完备的 Python library ，其中包含了ModelScope官方模型的实现，以及使用这些模型进行推理，finetune等任务所需的数据预处理，后处理，效果评估等功能相关的代码，同时也提供了简单易用的API，以及丰富的使用样例。通过调用library，用户可以只写短短的几行代码，就可以完成模型的推理、训练和评估等任务，也可以在此基础上快速进行二次开发，实现自己的创新想法。

目前library提供的算法模型，涵盖了图像，自然语言处理，语音，多模态，科学5个主要的AI领域，数十个应用场景任务，具体任务可参考文档：任务的介绍。

深度学习框架

ModelScope Library 当前支持的深度学习框架包括 Pytorch 和 Tensorflow ，后续将持续更新拓展，敬请期待！当前的官方模型均支持使用 ModelScope Library 进行模型推理，部分支持使用该库进行训练和评估，具体可参看相应模型的模型卡片，了解完整使用信息。

模型推理Pipeline

模型的推理

推理在深度学习中表示模型的预测过程。ModelScope的推理会使用pipeline来执行所需要的操作。一个完整的pipeline一般包括了 数据的前处理 、 模型的前向推理 、 数据的后处理 三个过程。

Pipeline介绍

pipeline() 方法是ModelScope框架上最基础的用户方法之一，可对多领域的多种模型进行快速推理。通过pipeline()方法，用户可以只需要一行代码即可完成对特定任务的模型推理。

Pipeline的使用

本文简单介绍如何使用 pipeline 方法加载模型进行推理。 pipeline 方法支持按照任务类型、模型名称从模型仓库拉取模型进行进行推理，包含以下几个方面：

环境准备

重要参数

Pipeline基本用法

指定预处理、模型进行推理

不同场景任务推理pipeline使用示例

Pipeline基本用法

中文分词

pipeline 函数支持指定特定任务名称，加载任务默认模型，创建对应pipeline对象。

Python代码

from modelscope.pipelines import pipeline word_segmentation = pipeline('word-segmentation') input_str = '开源技术小栈作者是Tinywan，你知道不？' print(word_segmentation(input_str))

PHP 代码

<?php $operator = PyCore::import("operator"); $builtins = PyCore::import("builtins"); $pipeline = PyCore::import('modelscope.pipelines')->pipeline; $word_segmentation = $pipeline("word-segmentation"); $input_str = "开源技术小栈作者是Tinywan，你知道不？"; PyCore::print($word_segmentation($input_str));

在线转换工具：https://www.swoole.com/py2php/

输出结果

/usr/local/php-8.2.14/bin/php demo.php 2024-03-25 21:41:42,434 - modelscope - INFO - PyTorch version 2.2.1 Found. 2024-03-25 21:41:42,434 - modelscope - INFO - Loading ast index from /home/www/.cache/modelscope/ast_indexer 2024-03-25 21:41:42,577 - modelscope - INFO - Loading done! Current index file version is 1.13.0, with md5 f54e9d2dceb89a6c989540d66db83a65 and a total number of 972 components indexed 2024-03-25 21:41:44,661 - modelscope - WARNING - Model revision not specified, use revision: v1.0.3 2024-03-25 21:41:44,879 - modelscope - INFO - initiate model from /home/www/.cache/modelscope/hub/damo/nlp_structbert_word-segmentation_chinese-base 2024-03-25 21:41:44,879 - modelscope - INFO - initiate model from location /home/www/.cache/modelscope/hub/damo/nlp_structbert_word-segmentation_chinese-base. 2024-03-25 21:41:44,880 - modelscope - INFO - initialize model from /home/www/.cache/modelscope/hub/damo/nlp_structbert_word-segmentation_chinese-base You are using a model of type bert to instantiate a model of type structbert. This is not supported for all configurations of models and can yield errors. 2024-03-25 21:41:48,633 - modelscope - WARNING - No preprocessor field found in cfg. 2024-03-25 21:41:48,633 - modelscope - WARNING - No val key and type key found in preprocessor domain of configuration.json file. 2024-03-25 21:41:48,633 - modelscope - WARNING - Cannot find available config to build preprocessor at mode inference, current config: {'model_dir': '/home/www/.cache/modelscope/hub/damo/nlp_structbert_word-segmentation_chinese-base'}. trying to build by task and model information. 2024-03-25 21:41:48,639 - modelscope - INFO - cuda is not available, using cpu instead. 2024-03-25 21:41:48,640 - modelscope - WARNING - No preprocessor field found in cfg. 2024-03-25 21:41:48,640 - modelscope - WARNING - No val key and type key found in preprocessor domain of configuration.json file. 2024-03-25 21:41:48,640 - modelscope - WARNING - Cannot find available config to build preprocessor at mode inference, current config: {'model_dir': '/home/www/.cache/modelscope/hub/damo/nlp_structbert_word-segmentation_chinese-base', 'sequence_length': 512}. trying to build by task and model information. /home/www/anaconda3/envs/tinywan-modelscope/lib/python3.10/site-packages/transformers/modeling_utils.py:962: FutureWarning: The `device` argument is deprecated and will be removed in v5 of Transformers. warnings.warn( {'output': ['开源', '技术', '小', '栈', '作者', '是', 'Tinywan', '，', '你', '知道', '不', '？']}

输入多条样本

pipeline 对象也支持传入多个样本列表输入，返回对应输出列表，每个元素对应输入样本的返回结果。多条文本的推理方式是输入data在 pipeline 内部用迭代器单条处理后 append 到同一个返回 List 中。

Python代码

from modelscope.pipelines import pipeline word_segmentation = pipeline('word-segmentation') inputs = ['开源技术小栈作者是Tinywan，你知道不？','webman这个框架不错，建议你看看'] print(word_segmentation(inputs))

PHP 代码

<?php $operator = PyCore::import("operator"); $builtins = PyCore::import("builtins"); $pipeline = PyCore::import('modelscope.pipelines')->pipeline; $word_segmentation = $pipeline("word-segmentation"); $inputs = new PyList(["开源技术小栈作者是Tinywan，你知道不？", "webman这个框架不错，建议你看看"]); PyCore::print($word_segmentation($inputs));

输出

[{'output': ['开源', '技术', '小', '栈', '作者', '是', 'Tinywan', '，', '你', '知道', '不', '？']}, {'output': ['webman', '这个', '框架', '不错', '，', '建议', '你', '看看']}]

批量推理

pipeline对于批量推理的支持类似于上面的「输入多条文本」，区别在于会在用户指定的batch_size尺度上，在模型forward过程实现批量前向推理。

inputs = ['今天天气不错，适合出去游玩','这本书很好，建议你看看'] # 指定batch_size参数来支持批量推理 print(word_segmentation(inputs, batch_size=2)) # 输出 [{'output': ['今天', '天气', '不错', '，', '适合', '出去', '游玩']}, {'output': ['这', '本', '书', '很', '好', '，', '建议', '你', '看看']}]

输入一个数据集

from modelscope.msdatasets import MsDataset from modelscope.pipelines import pipeline inputs = ['今天天气不错，适合出去游玩', '这本书很好，建议你看看'] dataset = MsDataset.load(inputs, target='sentence') word_segmentation = pipeline('word-segmentation') outputs = word_segmentation(dataset) for o in outputs: print(o) # 输出 {'output': ['今天', '天气', '不错', '，', '适合', '出去', '游玩']} {'output': ['这', '本', '书', '很', '好', '，', '建议', '你', '看看']}

指定预处理、模型进行推理

pipeline函数支持传入实例化的预处理对象、模型对象，从而支持用户在推理过程中定制化预处理、模型。

创建模型对象进行推理

Python代码

from modelscope.models import Model from modelscope.pipelines import pipeline model = Model.from_pretrained('damo/nlp_structbert_word-segmentation_chinese-base') word_segmentation = pipeline('word-segmentation', model=model) inputs = ['开源技术小栈作者是Tinywan，你知道不？','webman这个框架不错，建议你看看'] print(word_segmentation(inputs))

PHP 代码

<?php $operator = PyCore::import("operator"); $builtins = PyCore::import("builtins"); $Model = PyCore::import('modelscope.models')->Model; $pipeline = PyCore::import('modelscope.pipelines')->pipeline; $model = $Model->from_pretrained("damo/nlp_structbert_word-segmentation_chinese-base"); $word_segmentation = $pipeline("word-segmentation", model: $model); $inputs = new PyList(["开源技术小栈作者是Tinywan，你知道不？", "webman这个框架不错，建议你看看"]); PyCore::print($word_segmentation($inputs));

输出

创建预处理器和模型对象进行推理

from modelscope.models import Model from modelscope.pipelines import pipeline from modelscope.preprocessors import Preprocessor, Token classificationTransformersPreprocessor model = Model.from_pretrained('damo/nlp_structbert_word-segmentation_chinese-base') tokenizer = Preprocessor.from_pretrained(model.model_dir) # Or call the constructor directly: # tokenizer = Token classificationTransformersPreprocessor(model.model_dir) word_segmentation = pipeline('word-segmentation', model=model, preprocessor=tokenizer) inputs = ['开源技术小栈作者是Tinywan，你知道不？','webman这个框架不错，建议你看看'] print(word_segmentation(inputs)) [{'output': ['开源', '技术', '小', '栈', '作者', '是', 'Tinywan', '，', '你', '知道', '不', '？']}, {'output': ['webman', '这个', '框架', '不错', '，', '建议', '你', '看看']}]

图像

注意：

确保你已经安装了OpenCV库。如果没有安装，你可以通过 pip 安装

pip install opencv-python

没有安装会提示： PHP Fatal error: Uncaught PyError: No module named 'cv2' in /home/www/build/ai/demo3.php:4

确保你已经安装深度学习框架包 TensorFlow 库

否则提示 modelscope.pipelines.cv.image_matting_pipeline requires the TensorFlow library but it was not found in your environment. Checkout the instructions on the installation page: https://www.tensorflow.org/install and follow the ones that match your environment. 。

报错信息表明，你正在尝试使用一个名为 modelscope.pipelines.cv.image_matting_pipeline 的模块，该模块依赖于 TensorFlow 库。然而，该模块无法正常工作，因为缺少必要的 TensorFlow 依赖。

可以使用以下命令安装最新版本的 TensorFlow

pip install tensorflow

人像抠图（'portrait-matting'）

输入图片

Python 代码

import cv2 from modelscope.pipelines import pipeline portrait_matting = pipeline('portrait-matting') result = portrait_matting('https://modelscope.oss-cn-beijing.aliyuncs.com/test/images/image_matting.png') cv2.imwrite('result.png', result['output_img'])

PHP 代码 tinywan-images.php

<?php $operator = PyCore::import("operator"); $builtins = PyCore::import("builtins"); $cv2 = PyCore::import('cv2'); $pipeline = PyCore::import('modelscope.pipelines')->pipeline; $portrait_matting = $pipeline("portrait-matting"); $result = $portrait_matting("https://modelscope.oss-cn-beijing.aliyuncs.com/test/images/image_matting.png"); $cv2->imwrite("tinywan_result.png", $result->__getitem__("output_img"));

加载本地文件图片 $result = $portrait_matting("./tinywan.png");

执行结果

/usr/local/php-8.2.14/bin/php tinywan-images.php 2024-03-2522:17:25,630 - modelscope - INFO - PyTorch version 2.2.1 Found. 2024-03-2522:17:25,631 - modelscope - INFO - TensorFlow version 2.16.1 Found. 2024-03-2522:17:25,631 - modelscope - INFO - Loading ast index from /home/www/.cache/modelscope/ast_indexer 2024-03-2522:17:25,668 - modelscope - INFO - Loading done! Current index file version is 1.13.0, with md5 f54e9d2dceb89a6c989540d66db83a65 and a total number of 972 components indexed 2024-03-2522:17:26,990 - modelscope - WARNING - Model revision not specified, use revision: v1.0.0 2024-03-2522:17:27.623085: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2024-03-2522:17:27.678592: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-03-2522:17:28.551510: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT 2024-03-2522:17:29,206 - modelscope - INFO - initiate model from /home/www/.cache/modelscope/hub/damo/cv_unet_image-matting 2024-03-2522:17:29,206 - modelscope - INFO - initiate model from location /home/www/.cache/modelscope/hub/damo/cv_unet_image-matting. 2024-03-2522:17:29,209 - modelscope - WARNING - No preprocessor field found in cfg. 2024-03-2522:17:29,210 - modelscope - WARNING - No val key and type key found in preprocessor domain of configuration.json file. 2024-03-2522:17:29,210 - modelscope - WARNING - Cannot find available config to build preprocessor at mode inference, current config: {'model_dir': '/home/www/.cache/modelscope/hub/damo/cv_unet_image-matting'}. trying to build by task and model information. 2024-03-2522:17:29,210 - modelscope - WARNING - Find task: portrait-matting, model type: None. Insufficient information to build preprocessor, skip building preprocessor WARNING:tensorflow:From /home/www/anaconda3/envs/tinywan-modelscope/lib/python3.10/site-packages/modelscope/utils/device.py:60: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.config.list_physical_devices('GPU')` instead. 2024-03-2522:17:29,213 - modelscope - INFO - loading model from /home/www/.cache/modelscope/hub/damo/cv_unet_image-matting/tf_graph.pb WARNING:tensorflow:From /home/www/anaconda3/envs/tinywan-modelscope/lib/python3.10/site-packages/modelscope/pipelines/cv/image_matting_pipeline.py:45: FastGFile.__init__ (from tensorflow.python.platform.gfile) is deprecated and will be removed in a future version. Instructions for updating: Use tf.gfile.GFile. 2024-03-2522:17:29,745 - modelscope - INFO - load model done

输出图片