PaddleOCR转RKNN并在RK3588上运行

一、Ubuntu20.04PC端1.创建环境conda create -n deploy python3.6 conda activate deploy2.安装环境链接: https://pan.baidu.com/s/18KoIYMkCUS5-PNb3DCRTHA?pwd5ix5 提取码: 5ix5pip install rknn_toolkit2-1.4.2b30bdd72ff-cp36-cp36m-linux_x86_64.whl pip install paddle2onnx3.PaddleOCR转换3.1 下载PP-OCRv3文字检测模型、文字方向分类器模型、PP-OCRv3文字识别模型wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar tar -xvf ch_PP-OCRv3_det_infer.tar wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar tar -xvf ch_PP-OCRv3_rec_infer.tar3.2 转换成ONNX并将ONNX固定输入shapepaddle2onnx --model_dir ch_PP-OCRv3_det_infer \ --model_filename inference.pdmodel \ --params_filename inference.pdiparams \ --opset_version 11 \ --save_file det3.onnx \ --enable_dev_version True paddle2onnx --model_dir ch_ppocr_mobile_v2.0_cls_infer \ --model_filename inference.pdmodel \ --params_filename inference.pdiparams \ --opset_version 11 \ --save_file cls2.onnx \ --enable_dev_version True paddle2onnx --model_dir ch_PP-OCRv3_rec_infer \ --model_filename inference.pdmodel \ --params_filename inference.pdiparams \ --opset_version 11 \ --save_file rec3.onnx \ --enable_dev_version True python -m paddle2onnx.optimize --input_model det3.onnx \ --output_model det3_shape.onnx \ --input_shape_dict {x:[1,3,960,960]} python -m paddle2onnx.optimize --input_model cls2.onnx \ --output_model cls2_shape.onnx \ --input_shape_dict {x:[1,3,48,192]} python -m paddle2onnx.optimize --input_model rec3.onnx \ --output_model rec3_shape.onnx \ --input_shape_dict {x:[1,3,48,320]}3.3 转换成RKNN# 下载FastDeploy1.1.0版本除了可以python调用也支持C # 下载解压后先修改该目录下rknpu2_tools/config中三个yaml更换onnx路径和rknn输出路径后开始转换 git clone https://github.com/PaddlePaddle/FastDeploy.git cd FastDeploy-release-1.1.0/examples/vision/ocr/PP-OCR/rockchip/rknpu2_tools python rknpu2_tools/export.py --config_path rknpu2_tools/config/ppocrv3_det.yaml --target_platform rk3588 python rknpu2_tools/export.py --config_path rknpu2_tools/config/ppocrv3_rec.yaml --target_platform rk3588 python rknpu2_tools/export.py --config_path rknpu2_tools/config/ppocrv3_cls.yaml --target_platform rk3588得到三个RKNN文件拷贝至RK3588版端二、RK3588板端1.搭建环境先下载rknn-toolkit-lite2链接: https://pan.baidu.com/s/1mb8XmoTSVz2ZsO9HnKvr8Q?pwd5ax6 提取码: 5ax6conda create -n deploy python3.8 conda activate fastdeploy pip install packages/rknn_toolkit_lite2-2.0.0b1-cp38-cp38-linux_aarch64.whl