From 73d4b41ab03171c0b2782edc3a1e0bf029e45e4a Mon Sep 17 00:00:00 2001 From: WenmuZhou Date: Fri, 18 Dec 2020 22:36:04 +0800 Subject: [PATCH 1/2] update inference doc --- doc/doc_ch/inference.md | 11 ++++++++--- doc/doc_en/inference_en.md | 16 ++++++++++++---- 2 files changed, 20 insertions(+), 7 deletions(-) diff --git a/doc/doc_ch/inference.md b/doc/doc_ch/inference.md index 09303e93..c69c127a 100755 --- a/doc/doc_ch/inference.md +++ b/doc/doc_ch/inference.md @@ -245,7 +245,10 @@ python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/img 超轻量中文识别模型推理，可以执行如下命令： ``` -python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./inference/rec_crnn/" +# 下载超轻量中文识别模型： +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar +tar xf ch_ppocr_mobile_v2.0_rec_infer.tar +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="ch_ppocr_mobile_v2.0_rec_infer" ``` ![](../imgs_words/ch/word_4.jpg) @@ -266,7 +269,6 @@ Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.98458153) ``` python3 tools/export_model.py -c configs/rec/rec_r34_vd_none_bilstm_ctc.yml -o Global.pretrained_model=./rec_r34_vd_none_bilstm_ctc_v2.0_train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/rec_crnn - ``` CRNN 文本识别模型推理，可以执行如下命令： @@ -327,7 +329,10 @@ Predicts of ./doc/imgs_words/korean/1.jpg:('바탕으로', 0.9948904) 方向分类模型推理，可以执行如下命令： ``` -python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --cls_model_dir="./inference/cls/" +# 下载超轻量中文方向分类器模型： +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar +tar xf ch_ppocr_mobile_v2.0_cls_infer.tar +python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --cls_model_dir="ch_ppocr_mobile_v2.0_cls_infer" ``` ![](../imgs_words/ch/word_1.jpg) diff --git a/doc/doc_en/inference_en.md b/doc/doc_en/inference_en.md index 3fcd36c0..8742b7ce 100755 --- a/doc/doc_en/inference_en.md +++ b/doc/doc_en/inference_en.md @@ -255,15 +255,18 @@ The following will introduce the lightweight Chinese recognition model inference For lightweight Chinese recognition model inference, you can execute the following commands: ``` -python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./inference/rec_crnn/" +# download CRNN text recognition inference model +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar +tar xf ch_ppocr_mobile_v2.0_rec_infer.tar +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_10.png" --rec_model_dir="ch_ppocr_mobile_v2.0_rec_infer" ``` -![](../imgs_words/ch/word_4.jpg) +![](../imgs_words_en/word_10.png) After executing the command, the prediction results (recognized text and score) of the above image will be printed on the screen. ```bash -Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.98458153) +Predicts of ./doc/imgs_words_en/word_10.png:('PAIN', 0.9897658) ``` @@ -339,7 +342,12 @@ For angle classification model inference, you can execute the following commands ``` python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words_en/word_10.png" --cls_model_dir="./inference/cls/" ``` - +``` +# download text angle class inference model： +wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar +tar xf ch_ppocr_mobile_v2.0_cls_infer.tar +python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words_en/word_10.png" --cls_model_dir="ch_ppocr_mobile_v2.0_cls_infer" +``` ![](../imgs_words_en/word_10.png) After executing the command, the prediction results (classification angle and score) of the above image will be printed on the screen. From b615f6704d9b7e7e58c90fc246ec002d7485adac Mon Sep 17 00:00:00 2001 From: WenmuZhou Date: Fri, 18 Dec 2020 23:00:16 +0800 Subject: [PATCH 2/2] load model by pretrained_model --- doc/doc_ch/angle_class.md | 2 +- doc/doc_ch/detection.md | 6 +++--- doc/doc_ch/recognition.md | 5 ++--- doc/doc_en/angle_class_en.md | 2 +- doc/doc_en/detection_en.md | 6 +++--- doc/doc_en/recognition_en.md | 8 ++++---- 6 files changed, 14 insertions(+), 15 deletions(-) diff --git a/doc/doc_ch/angle_class.md b/doc/doc_ch/angle_class.md index 3f2027b9..846be15f 100644 --- a/doc/doc_ch/angle_class.md +++ b/doc/doc_ch/angle_class.md @@ -117,7 +117,7 @@ python3 tools/eval.py -c configs/cls/cls_mv3.yml -o Global.checkpoints={path/to/ ``` # 预测分类结果 -python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/ch/word_1.jpg +python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/ch/word_1.jpg ``` 预测图片： diff --git a/doc/doc_ch/detection.md b/doc/doc_ch/detection.md index 08b94a9c..8f0f6979 100644 --- a/doc/doc_ch/detection.md +++ b/doc/doc_ch/detection.md @@ -120,16 +120,16 @@ python3 tools/eval.py -c configs/det/det_mv3_db.yml -o Global.checkpoints="{pat 测试单张图像的检测效果 ```shell -python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy" +python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false ``` 测试DB模型时，调整后处理阈值， ```shell -python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy" PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5 +python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5 ``` 测试文件夹下所有图像的检测效果 ```shell -python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.checkpoints="./output/det_db/best_accuracy" +python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false ``` diff --git a/doc/doc_ch/recognition.md b/doc/doc_ch/recognition.md index dc06365c..b473f3ac 100644 --- a/doc/doc_ch/recognition.md +++ b/doc/doc_ch/recognition.md @@ -324,7 +324,6 @@ Eval: 评估数据集可以通过 `configs/rec/rec_icdar15_train.yml` 修改Eval中的 `label_file_path` 设置。 -*注意* 评估时必须确保配置文件中 infer_img 字段为空 ``` # GPU 评估， Global.checkpoints 为待测权重 python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy @@ -342,7 +341,7 @@ python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec ``` # 预测英文结果 -python3 tools/infer_rec.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/en/word_1.png +python3 tools/infer_rec.py -c configs/rec/rec_icdar15_train.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/en/word_1.png ``` 预测图片： @@ -361,7 +360,7 @@ infer_img: doc/imgs_words/en/word_1.png ``` # 预测中文结果 -python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words/ch/word_1.jpg +python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/ch/word_1.jpg ``` 预测图片： diff --git a/doc/doc_en/angle_class_en.md b/doc/doc_en/angle_class_en.md index 4c479e7b..e6157d16 100644 --- a/doc/doc_en/angle_class_en.md +++ b/doc/doc_en/angle_class_en.md @@ -119,7 +119,7 @@ Use `Global.infer_img` to specify the path of the predicted picture or folder, a ``` # Predict English results -python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words_en/word_10.png +python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words_en/word_10.png ``` Input image: diff --git a/doc/doc_en/detection_en.md b/doc/doc_en/detection_en.md index 7638315a..5c4a63e2 100644 --- a/doc/doc_en/detection_en.md +++ b/doc/doc_en/detection_en.md @@ -113,16 +113,16 @@ python3 tools/eval.py -c configs/det/det_mv3_db.yml -o Global.checkpoints="{pat Test the detection result on a single image: ```shell -python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy" +python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false ``` When testing the DB model, adjust the post-processing threshold: ```shell -python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy" PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5 +python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5 ``` Test the detection result on all images in the folder: ```shell -python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.checkpoints="./output/det_db/best_accuracy" +python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false ``` diff --git a/doc/doc_en/recognition_en.md b/doc/doc_en/recognition_en.md index bc8faa0f..7723d20b 100644 --- a/doc/doc_en/recognition_en.md +++ b/doc/doc_en/recognition_en.md @@ -317,11 +317,11 @@ Eval: ### EVALUATION -The evaluation data set can be modified via `configs/rec/rec_icdar15_reader.yml` setting of `label_file_path` in EvalReader. +The evaluation dataset can be set by modifying the `Eval.dataset.label_file_list` field in the `configs/rec/rec_icdar15_train.yml` file. ``` # GPU evaluation, Global.checkpoints is the weight to be tested -python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_reader.yml -o Global.checkpoints={path/to/weights}/best_accuracy +python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy ``` @@ -336,7 +336,7 @@ The default prediction picture is stored in `infer_img`, and the weight is speci ``` # Predict English results -python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints={path/to/weights}/best_accuracy TestReader.infer_img=doc/imgs_words/en/word_1.jpg +python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/en/word_1.jpg ``` Input image: @@ -354,7 +354,7 @@ The configuration file used for prediction must be consistent with the training. ``` # Predict Chinese results -python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints={path/to/weights}/best_accuracy TestReader.infer_img=doc/imgs_words/ch/word_1.jpg +python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/ch/word_1.jpg ``` Input image: