From 09187228d6e5f046182310f3adb8122ffac72900 Mon Sep 17 00:00:00 2001 From: andyjpaddle <87074272+andyjpaddle@users.noreply.github.com> Date: Wed, 11 May 2022 16:14:49 +0800 Subject: [PATCH] [CP] update doc for v3 det quant (#6250) * update cpp serving for v3 * update doc for v3 det quant * update doc for v3 infer --- deploy/slim/quantization/README.md | 4 ++-- deploy/slim/quantization/README_en.md | 4 ++-- doc/doc_ch/inference_ppocr.md | 12 ++++++------ doc/doc_en/inference_ppocr_en.md | 11 +++++------ 4 files changed, 15 insertions(+), 16 deletions(-) diff --git a/deploy/slim/quantization/README.md b/deploy/slim/quantization/README.md index 894a29be..4c1d784b 100644 --- a/deploy/slim/quantization/README.md +++ b/deploy/slim/quantization/README.md @@ -47,9 +47,9 @@ python deploy/slim/quantization/quant.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3 ``` # 下载检测预训练模型： wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar -tar xf https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar +tar xf ch_PP-OCRv3_det_distill_train.tar -python deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv3_det/ch_PP-OCRv3_det_cml.yml -o Global.pretrained_model='./ch_PP-OCRv3_det_distill_train/best_accuracy' Global.save_model_dir=./output/quant_model_distill/ +python deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o Global.pretrained_model='./ch_PP-OCRv3_det_distill_train/best_accuracy' Global.save_model_dir=./output/quant_model_distill/ ``` 如果要训练识别模型的量化，修改配置文件和加载的模型参数即可。 diff --git a/deploy/slim/quantization/README_en.md b/deploy/slim/quantization/README_en.md index ea77cb38..33b2c478 100644 --- a/deploy/slim/quantization/README_en.md +++ b/deploy/slim/quantization/README_en.md @@ -54,9 +54,9 @@ Model distillation and model quantization can be used at the same time, taking t ``` # download provided model wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar -tar xf https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar +tar xf ch_PP-OCRv3_det_distill_train.tar -python deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv3_det/ch_PP-OCRv3_det_cml.yml -o Global.pretrained_model='./ch_PP-OCRv3_det_distill_train/best_accuracy' Global.save_model_dir=./output/quant_model_distill/ +python deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o Global.pretrained_model='./ch_PP-OCRv3_det_distill_train/best_accuracy' Global.save_model_dir=./output/quant_model_distill/ ``` If you want to quantify the text recognition model, you can modify the configuration file and loaded model parameters. diff --git a/doc/doc_ch/inference_ppocr.md b/doc/doc_ch/inference_ppocr.md index 94630755..472c0003 100644 --- a/doc/doc_ch/inference_ppocr.md +++ b/doc/doc_ch/inference_ppocr.md @@ -59,7 +59,7 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_di ### 2.1 超轻量中文识别模型推理 -**注意** `PP-OCRv3`的识别模型使用的输入shape为`3,48,320`, 需要添加参数`--rec_image_shape=3,48,320`，如果不使用`PP-OCRv3`的识别模型，则无需设置该参数。 +**注意** `PP-OCRv3`的识别模型使用的输入shape为`3,48,320`, 如果使用其他识别模型，则需根据模型设置参数`--rec_image_shape`。此外，`PP-OCRv3`的识别模型默认使用的`rec_algorithm`为`SVTR_LCNet`，注意和原始`SVTR`的区别。 超轻量中文识别模型推理，可以执行如下命令： @@ -67,7 +67,7 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_di # 下载超轻量中文识别模型： wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar tar xf ch_PP-OCRv3_rec_infer.tar -python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --rec_image_shape=3,48,320 +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" ``` ![](../imgs_words/ch/word_4.jpg) @@ -121,17 +121,17 @@ Predicts of ./doc/imgs_words/ch/word_4.jpg:['0', 0.9999982] ## 4. 文本检测、方向分类和文字识别串联推理 -**注意** `PP-OCRv3`的识别模型使用的输入shape为`3,48,320`, 需要添加参数`--rec_image_shape=3,48,320`，如果不使用`PP-OCRv3`的识别模型，则无需设置该参数。 +**注意** `PP-OCRv3`的识别模型使用的输入shape为`3,48,320`, 如果使用其他识别模型，则需根据模型设置参数`--rec_image_shape`。此外，`PP-OCRv3`的识别模型默认使用的`rec_algorithm`为`SVTR_LCNet`，注意和原始`SVTR`的区别。 以超轻量中文OCR模型推理为例，在执行预测时，需要通过参数`image_dir`指定单张图像或者图像集合的路径、参数`det_model_dir`,`cls_model_dir`和`rec_model_dir`分别指定检测，方向分类和识别的inference模型路径。参数`use_angle_cls`用于控制是否启用方向分类模型。`use_mp`表示是否使用多进程。`total_process_num`表示在使用多进程时的进程数。可视化识别结果默认保存到 ./inference_results 文件夹里面。 ```shell # 使用方向分类器 -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --cls_model_dir="./cls/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=true --rec_image_shape=3,48,320 +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --cls_model_dir="./cls/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=true # 不使用方向分类器 -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=false --rec_image_shape=3,48,320 +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=false # 使用多进程 -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=false --use_mp=True --total_process_num=6 --rec_image_shape=3,48,320 +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=false --use_mp=True --total_process_num=6 ``` 执行命令后，识别结果图像如下： diff --git a/doc/doc_en/inference_ppocr_en.md b/doc/doc_en/inference_ppocr_en.md index dcfb738e..935f92f5 100755 --- a/doc/doc_en/inference_ppocr_en.md +++ b/doc/doc_en/inference_ppocr_en.md @@ -56,7 +56,7 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_di ### 1. Lightweight Chinese Recognition Model Inference -**Note**: The input shape used by the recognition model of `PP-OCRv3` is `3,48,320`, and the parameter `--rec_image_shape=3,48,320` needs to be added. If the recognition model of `PP-OCRv3` is not used, this parameter does not need to be set. +**Note**: The input shape used by the recognition model of `PP-OCRv3` is `3, 48, 320`. If you use other recognition models, you need to set the parameter `--rec_image_shape` according to the model. In addition, the `rec_algorithm` used by the recognition model of `PP-OCRv3` is `SVTR_LCNet` by default. Note the difference from the original `SVTR`. For lightweight Chinese recognition model inference, you can execute the following commands: @@ -120,19 +120,18 @@ After executing the command, the prediction results (classification angle and sc ## Text Detection Angle Classification and Recognition Inference Concatenation -**Note**: The input shape used by the recognition model of `PP-OCRv3` is `3,48,320`, and the parameter `--rec_image_shape=3,48,320` needs to be added. If the recognition model of `PP-OCRv3` is not used, this parameter does not need to be set. +**Note**: The input shape used by the recognition model of `PP-OCRv3` is `3, 48, 320`. If you use other recognition models, you need to set the parameter `--rec_image_shape` according to the model. In addition, the `rec_algorithm` used by the recognition model of `PP-OCRv3` is `SVTR_LCNet` by default. Note the difference from the original `SVTR`. When performing prediction, you need to specify the path of a single image or a folder of images through the parameter `image_dir`, the parameter `det_model_dir` specifies the path to detect the inference model, the parameter `cls_model_dir` specifies the path to angle classification inference model and the parameter `rec_model_dir` specifies the path to identify the inference model. The parameter `use_angle_cls` is used to control whether to enable the angle classification model. The parameter `use_mp` specifies whether to use multi-process to infer `total_process_num` specifies process number when using multi-process. The parameter . The visualized recognition results are saved to the `./inference_results` folder by default. ```shell # use direction classifier -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --cls_model_dir="./cls/" --rec_model_dir="./ch_PP-OCRv2_rec_infer/" --use_angle_cls=true --rec_image_shape=3,48,320 +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --cls_model_dir="./cls/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=true # not use use direction classifier -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv2_det_infer/" --rec_model_dir="./ch_PP-OCRv2_rec_infer/" --use_angle_cls=false --rec_image_shape=3,48,320 - +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=false # use multi-process -python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv2_det_infer/" --rec_model_dir="./ch_PP-OCRv2_rec_infer/" --use_angle_cls=false --use_mp=True --total_process_num=6 --rec_image_shape=3,48,320 +python3 tools/infer/predict_system.py --image_dir="./doc/imgs/00018069.jpg" --det_model_dir="./ch_PP-OCRv3_det_infer/" --rec_model_dir="./ch_PP-OCRv3_rec_infer/" --use_angle_cls=false --use_mp=True --total_process_num=6 ``` -- GitLab