From 4561ec9798ca0df69da78e00f58c910851acb0f8 Mon Sep 17 00:00:00 2001 From: WenmuZhou Date: Thu, 10 Dec 2020 17:15:05 +0800 Subject: [PATCH] update doc --- doc/doc_ch/inference.md | 66 ++++++++++++++++++------------------ doc/doc_en/inference_en.md | 68 ++++++++++++++++++-------------------- 2 files changed, 66 insertions(+), 68 deletions(-) diff --git a/doc/doc_ch/inference.md b/doc/doc_ch/inference.md index bab54bf9..dfd84ccc 100644 --- a/doc/doc_ch/inference.md +++ b/doc/doc_ch/inference.md @@ -41,14 +41,17 @@ inference 模型（`paddle.jit.save`保存的模型） 下载超轻量级中文检测模型： ``` -wget -P ./ch_lite/ {link} && tar xf ./ch_lite/{file} -C ./ch_lite/ +wget -P ./ch_lite/ {link} && tar xf ./ch_lite/ch_ppocr_mobile_v2.0_det_train.tar -C ./ch_lite/ ``` 上述模型是以MobileNetV3为backbone训练的DB算法，将训练好的模型转换成inference模型只需要运行如下命令： ``` -# -c 后面设置训练算法的yml配置文件，需设置 `Global.load_static_weights=False`, 并将待转换的训练模型地址写入配置文件里的 `Global.pretrained_model` 字段下，不用添加文件后缀.pdmodel，.pdopt或.pdparams。 -# -o 后面设置转换的模型将保存的地址。 +# -c 后面设置训练算法的yml配置文件 +# -o 配置可选参数 +# Global.pretrained_model 参数设置待转换的训练模型地址，不用添加文件后缀 .pdmodel，.pdopt或.pdparams。 +# Global.load_static_weights 参数需要设置为 False。 +# Global.save_inference_dir参数设置转换的模型将保存的地址。 -python3 tools/export_model.py -c configs/det/det_mv3_db_v1.1.yml -o ./inference/det_db/ +python3 tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o Global.checkpoints=./ch_lite/ch_ppocr_mobile_v2.0_det_train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_db/ ``` 转inference模型时，使用的配置文件和训练时使用的配置文件相同。另外，还需要设置配置文件中的`Global.checkpoints`参数，其指向训练中保存的模型参数文件。 转换成功后，在模型保存目录下有三个文件： @@ -64,14 +67,18 @@ inference/det_db/ 下载超轻量中文识别模型： ``` -wget -P ./ch_lite/ {link} && tar xf ./ch_lite/{file} -C ./ch_lite/ +wget -P ./ch_lite/ {link} && tar xf ./ch_lite/ch_ppocr_mobile_v2.0_rec_train.tar -C ./ch_lite/ ``` 识别模型转inference模型与检测的方式相同，如下： ``` -# -c 后面设置训练算法的yml配置文件，需设置 `Global.load_static_weights=False`, 并将待转换的训练模型地址写入配置文件里的 `Global.pretrained_model` 字段下，不用添加文件后缀.pdmodel，.pdopt或.pdparams。 -# -o 后面设置转换的模型将保存的地址。 -python3 tools/export_model.py -c configs/rec/ch_ppocr_v1.1/rec_chinese_lite_train_v1.1.yml -o ./inference/rec_crnn/ +# -c 后面设置训练算法的yml配置文件 +# -o 配置可选参数 +# Global.pretrained_model 参数设置待转换的训练模型地址，不用添加文件后缀 .pdmodel，.pdopt或.pdparams。 +# Global.load_static_weights 参数需要设置为 False。 +# Global.save_inference_dir参数设置转换的模型将保存的地址。 + +python3 tools/export_model.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints=./ch_lite/ch_ppocr_mobile_v2.0_rec_train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/rec_crnn/ ``` **注意：**如果您是在自己的数据集上训练的模型，并且调整了中文字符的字典文件，请注意修改配置文件中的`character_dict_path`是否是所需要的字典文件。 @@ -89,15 +96,18 @@ python3 tools/export_model.py -c configs/rec/ch_ppocr_v1.1/rec_chinese_lite_trai 下载方向分类模型： ``` -wget -P ./ch_lite/ {link} && tar xf ./ch_lite/{file} -C ./ch_lite/ +wget -P ./ch_lite/ {link} && tar xf ./ch_lite/ch_ppocr_mobile_v2.0_cls_train.tar -C ./ch_lite/ ``` 方向分类模型转inference模型与检测的方式相同，如下： ``` -# -c 后面设置训练算法的yml配置文件，需设置 `Global.load_static_weights=False`, 并将待转换的训练模型地址写入配置文件里的 `Global.pretrained_model` 字段下，不用添加文件后缀.pdmodel，.pdopt或.pdparams。 -# -o 后面设置转换的模型将保存的地址。 +# -c 后面设置训练算法的yml配置文件 +# -o 配置可选参数 +# Global.pretrained_model 参数设置待转换的训练模型地址，不用添加文件后缀 .pdmodel，.pdopt或.pdparams。 +# Global.load_static_weights 参数需要设置为 False。 +# Global.save_inference_dir参数设置转换的模型将保存的地址。 -python3 tools/export_model.py -c configs/cls/cls_mv3.yml -o ./inference/cls/ +python3 tools/export_model.py -c configs/cls/cls_mv3.yml -o Global.checkpoints=./ch_lite/ch_ppocr_mobile_v2.0_cls_train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/cls/ ``` 转换成功后，在目录下有三个文件： @@ -145,10 +155,7 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs/2.jpg" --det_model_di 首先将DB文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在ICDAR2015英文数据集训练的模型为例（[模型下载地址](link))，可以使用如下命令进行转换： ``` -# -c 后面设置训练算法的yml配置文件，需设置 `Global.load_static_weights=False`, 并将待转换的训练模型地址写入配置文件里的 `Global.pretrained_model` 字段下，不用添加文件后缀.pdmodel，.pdopt或.pdparams。 -# -o 后面设置转换的模型将保存的地址。 - -python3 tools/export_model.py -c configs/det/det_r50_vd_db.yml -o "./inference/det_db" +python3 tools/export_model.py -c configs/det/det_r50_vd_db.yml -o Global.checkpoints=./det_r50_vd_db_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_db ``` DB文本检测模型推理，可以执行如下命令： @@ -169,10 +176,7 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs_en/img_10.jpg" --det_ 首先将EAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在ICDAR2015英文数据集训练的模型为例（[模型下载地址](link))，可以使用如下命令进行转换： ``` -# -c 后面设置训练算法的yml配置文件，需设置 `Global.load_static_weights=False`, 并将待转换的训练模型地址写入配置文件里的 `Global.pretrained_model` 字段下，不用添加文件后缀.pdmodel，.pdopt或.pdparams。 -# -o 后面设置转换的模型将保存的地址。 - -python3 tools/export_model.py -c configs/det/det_r50_vd_east.yml -o Global.checkpoints="./models/det_r50_vd_east/best_accuracy" Global.save_inference_dir="./inference/det_east" +python3 tools/export_model.py -c configs/det/det_r50_vd_east.yml -o Global.checkpoints=./det_r50_vd_east_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_east ``` **EAST文本检测模型推理，需要设置参数`--det_algorithm="EAST"`**，可以执行如下命令： @@ -192,10 +196,8 @@ python3 tools/infer/predict_det.py --det_algorithm="EAST" --image_dir="./doc/img #### (1). 四边形文本检测模型（ICDAR2015） 首先将SAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在ICDAR2015英文数据集训练的模型为例([模型下载地址](link))，可以使用如下命令进行转换： ``` -# -c 后面设置训练算法的yml配置文件，需设置 `Global.load_static_weights=False`, 并将待转换的训练模型地址写入配置文件里的 `Global.pretrained_model` 字段下，不用添加文件后缀.pdmodel，.pdopt或.pdparams。 -# -o 后面设置转换的模型将保存的地址。 +python3 tools/export_model.py -c configs/det/det_r50_vd_sast_icdar15.yml -o Global.checkpoints=./det_r50_vd_sast_icdar15_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_sast_ic15 -python3 tools/export_model.py -c configs/det/det_r50_vd_sast_icdar15.yml -o "./inference/det_sast_ic15" ``` **SAST文本检测模型推理，需要设置参数`--det_algorithm="SAST"`**，可以执行如下命令： ``` @@ -209,10 +211,8 @@ python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/img 首先将SAST文本检测训练过程中保存的模型，转换成inference model。以基于Resnet50_vd骨干网络，在Total-Text英文数据集训练的模型为例（[模型下载地址](link))，可以使用如下命令进行转换： ``` -# -c 后面设置训练算法的yml配置文件，需设置 `Global.load_static_weights=False`, 并将待转换的训练模型地址写入配置文件里的 `Global.pretrained_model` 字段下，不用添加文件后缀.pdmodel，.pdopt或.pdparams。 -# -o 后面设置转换的模型将保存的地址。 +python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Global.checkpoints=./det_r50_vd_sast_totaltext_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_sast_tt -python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o "./inference/det_sast_tt" ``` **SAST文本检测模型推理，需要设置参数`--det_algorithm="SAST"`，同时，还需要增加参数`--det_sast_polygon=True`，**可以执行如下命令： @@ -251,30 +251,30 @@ Predicts of ./doc/imgs_words/ch/word_4.jpg:['实力活力', 0.89552695] ### 2. 基于CTC损失的识别模型推理 -我们以STAR-Net为例，介绍基于CTC损失的识别模型推理。 CRNN和Rosetta使用方式类似，不用设置识别算法参数rec_algorithm。 +我们以 CRNN 为例，介绍基于CTC损失的识别模型推理。 Rosetta 使用方式类似，不用设置识别算法参数rec_algorithm。 -首先将STAR-Net文本识别训练过程中保存的模型，转换成inference model。以基于Resnet34_vd骨干网络，使用MJSynth和SynthText两个英文文本识别合成数据集训练 +首先将 Rosetta 文本识别训练过程中保存的模型，转换成inference model。以基于Resnet34_vd骨干网络，使用MJSynth和SynthText两个英文文本识别合成数据集训练 的模型为例（[模型下载地址](link))，可以使用如下命令进行转换： ``` -# -c 后面设置训练算法的yml配置文件，需设置 `Global.load_static_weights=False`, 并将待转换的训练模型地址写入配置文件里的 `Global.pretrained_model` 字段下，不用添加文件后缀.pdmodel，.pdopt或.pdparams。 -# -o 后面设置转换的模型将保存的地址。 +python3 tools/export_model.py -c configs/det/rec_r34_vd_none_bilstm_ctc.yml -o Global.checkpoints=./rec_r34_vd_none_bilstm_ctc_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/rec_crnn -python3 tools/export_model.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml -o "./inference/starnet" ``` STAR-Net文本识别模型推理，可以执行如下命令： ``` -python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_type="en" +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rec_crnn/" --rec_image_shape="3, 32, 100" --rec_char_type="en" ``` ### 3. 基于Attention损失的识别模型推理 +基于Attention损失的识别模型与ctc不同，需要额外设置识别算法参数 --rec_algorithm="RARE" RARE 文本识别模型推理，可以执行如下命令： ``` -python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rare/" --rec_image_shape="3, 32, 100" --rec_char_type="en" +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rare/" --rec_image_shape="3, 32, 100" --rec_char_type="en" --rec_algorithm="RARE" + ``` ![](../imgs_words_en/word_336.png) diff --git a/doc/doc_en/inference_en.md b/doc/doc_en/inference_en.md index 40ac3d8c..ac1b634d 100644 --- a/doc/doc_en/inference_en.md +++ b/doc/doc_en/inference_en.md @@ -43,15 +43,18 @@ Next, we first introduce how to convert a trained model into an inference model, Download the lightweight Chinese detection model: ``` -wget -P ./ch_lite/ {link} && tar xf ./ch_lite/{file} -C ./ch_lite/ +wget -P ./ch_lite/ {link} && tar xf ./ch_lite/ch_ppocr_mobile_v2.0_det_train.tar -C ./ch_lite/ ``` The above model is a DB algorithm trained with MobileNetV3 as the backbone. To convert the trained model into an inference model, just run the following command: ``` --c Set the yml configuration file of the algorithm, you need to set `Global.load_static_weights=False`, and write the path of the training model to be converted under the `Global.pretrained_model` parameter in the configuration file, without adding the file suffix .pdmodel, .pdopt or .pdparams. -# -o Set the address where the converted model will be saved. +# -c Set the training algorithm yml configuration file +# -o Set optional parameters +# Global.checkpoints parameter Set the training model address to be converted without adding the file suffix .pdmodel, .pdopt or .pdparams. +# Global.load_static_weights needs to be set to False +# Global.save_inference_dir Set the address where the converted model will be saved. -python3 tools/export_model.py -c configs/det/det_mv3_db_v1.1.yml -o ./inference/det_db/ +python3 tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o Global.checkpoints=./ch_lite/ch_ppocr_mobile_v2.0_det_train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_db/ ``` When converting to an inference model, the configuration file used is the same as the configuration file used during training. In addition, you also need to set the `Global.checkpoints` parameter in the configuration file. @@ -68,15 +71,18 @@ inference/det_db/ Download the lightweight Chinese recognition model: ``` -wget -P ./ch_lite/ {link} && tar xf ./ch_lite/{file} -C ./ch_lite/ +wget -P ./ch_lite/ {link} && tar xf ./ch_lite/ch_ppocr_mobile_v2.0_rec_train.tar -C ./ch_lite/ ``` The recognition model is converted to the inference model in the same way as the detection, as follows: ``` --c Set the yml configuration file of the algorithm, you need to set `Global.load_static_weights=False`, and write the path of the training model to be converted under the `Global.pretrained_model` parameter in the configuration file, without adding the file suffix .pdmodel, .pdopt or .pdparams. -# -o Set the address where the converted model will be saved. +# -c Set the training algorithm yml configuration file +# -o Set optional parameters +# Global.checkpoints parameter Set the training model address to be converted without adding the file suffix .pdmodel, .pdopt or .pdparams. +# Global.load_static_weights needs to be set to False +# Global.save_inference_dir Set the address where the converted model will be saved. -python3 tools/export_model.py -c configs/cls/cls_mv3.yml -o ./inference/cls/ +python3 tools/export_model.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints=./ch_lite/ch_ppocr_mobile_v2.0_rec_train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/rec_crnn/ ``` If you have a model trained on your own dataset with a different dictionary file, please make sure that you modify the `character_dict_path` in the configuration file to your dictionary file path. @@ -94,15 +100,18 @@ inference/det_db/ Download the angle classification model: ``` -wget -P ./ch_lite/ {link} && tar xf ./ch_lite/{file} -C ./ch_lite/ +wget -P ./ch_lite/ {link} && tar xf ./ch_lite/ch_ppocr_mobile_v2.0_cls_train.tar -C ./ch_lite/ ``` The angle classification model is converted to the inference model in the same way as the detection, as follows: ``` --c Set the yml configuration file of the algorithm, you need to set `Global.load_static_weights=False`, and write the path of the training model to be converted under the `Global.pretrained_model` parameter in the configuration file, without adding the file suffix .pdmodel, .pdopt or .pdparams. -# -o Set the address where the converted model will be saved. +# -c Set the training algorithm yml configuration file +# -o Set optional parameters +# Global.checkpoints parameter Set the training model address to be converted without adding the file suffix .pdmodel, .pdopt or .pdparams. +# Global.load_static_weights needs to be set to False +# Global.save_inference_dir Set the address where the converted model will be saved. -python3 tools/export_model.py -c configs/cls/cls_mv3.yml -o ./inference/cls/ +python3 tools/export_model.py -c configs/cls/cls_mv3.yml -o Global.checkpoints=./ch_lite/ch_ppocr_mobile_v2.0_cls_train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/cls/ ``` After the conversion is successful, there are two files in the directory: @@ -152,10 +161,7 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs/2.jpg" --det_model_di First, convert the model saved in the DB text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as an example ([model download link](link)), you can use the following command to convert: ``` --c Set the yml configuration file of the algorithm, you need to set `Global.load_static_weights=False`, and write the path of the training model to be converted under the `Global.pretrained_model` parameter in the configuration file, without adding the file suffix .pdmodel, .pdopt or .pdparams. -# -o Set the address where the converted model will be saved. - -python3 tools/export_model.py -c configs/det/det_r50_vd_db.yml -o "./inference/det_db" +python3 tools/export_model.py -c configs/det/det_r50_vd_db.yml -o Global.checkpoints=./det_r50_vd_db_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_db ``` DB text detection model inference, you can execute the following command: @@ -176,10 +182,7 @@ The visualized text detection results are saved to the `./inference_results` fol First, convert the model saved in the EAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as an example ([model download link](link)), you can use the following command to convert: ``` --c Set the yml configuration file of the algorithm, you need to set `Global.load_static_weights=False`, and write the path of the training model to be converted under the `Global.pretrained_model` parameter in the configuration file, without adding the file suffix .pdmodel, .pdopt or .pdparams. -# -o Set the address where the converted model will be saved. - -python3 tools/export_model.py -c configs/det/det_r50_vd_east.yml -o Global.checkpoints="./models/det_r50_vd_east/best_accuracy" Global.save_inference_dir="./inference/det_east" +python3 tools/export_model.py -c configs/det/det_r50_vd_east.yml -o Global.checkpoints=./det_r50_vd_east_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_east ``` **For EAST text detection model inference, you need to set the parameter ``--det_algorithm="EAST"``**, run the following command: @@ -200,10 +203,7 @@ The visualized text detection results are saved to the `./inference_results` fol First, convert the model saved in the SAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the ICDAR2015 English dataset as an example ([model download link](link)), you can use the following command to convert: ``` --c Set the yml configuration file of the algorithm, you need to set `Global.load_static_weights=False`, and write the path of the training model to be converted under the `Global.pretrained_model` parameter in the configuration file, without adding the file suffix .pdmodel, .pdopt or .pdparams. -# -o Set the address where the converted model will be saved. - -python3 tools/export_model.py -c configs/det/det_r50_vd_sast_icdar15.yml -o "./inference/det_sast_ic15" +python3 tools/export_model.py -c configs/det/det_r50_vd_sast_icdar15.yml -o Global.checkpoints=./det_r50_vd_sast_icdar15_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_sast_ic15 ``` **For SAST quadrangle text detection model inference, you need to set the parameter `--det_algorithm="SAST"`**, run the following command: @@ -220,10 +220,7 @@ The visualized text detection results are saved to the `./inference_results` fol First, convert the model saved in the SAST text detection training process into an inference model. Taking the model based on the Resnet50_vd backbone network and trained on the Total-Text English dataset as an example ([model download link](https://paddleocr.bj.bcebos.com/SAST/sast_r50_vd_total_text.tar)), you can use the following command to convert: ``` --c Set the yml configuration file of the algorithm, you need to set `Global.load_static_weights=False`, and write the path of the training model to be converted under the `Global.pretrained_model` parameter in the configuration file, without adding the file suffix .pdmodel, .pdopt or .pdparams. -# -o Set the address where the converted model will be saved. - -python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Global.checkpoints="./models/sast_r50_vd_total_text/best_accuracy" Global.save_inference_dir="./inference/det_sast_tt" +python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Global.checkpoints=./det_r50_vd_sast_totaltext_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/det_sast_tt ``` **For SAST curved text detection model inference, you need to set the parameter `--det_algorithm="SAST"` and `--det_sast_polygon=True`**, run the following command: @@ -263,18 +260,15 @@ Predicts of ./doc/imgs_words/ch/word_4.jpg:['实力活力', 0.89552695] ### 2. CTC-BASED TEXT RECOGNITION MODEL INFERENCE -Taking STAR-Net as an example, we introduce the recognition model inference based on CTC loss. CRNN and Rosetta are used in a similar way, by setting the recognition algorithm parameter `rec_algorithm`. +Taking CRNN as an example, we introduce the recognition model inference based on CTC loss. Rosetta and Star-Net are used in a similar way, No need to set the recognition algorithm parameter rec_algorithm. -First, convert the model saved in the STAR-Net text recognition training process into an inference model. Taking the model based on Resnet34_vd backbone network, using MJSynth and SynthText (two English text recognition synthetic datasets) for training, as an example ([model download address](link)). It can be converted as follow: +First, convert the model saved in the CRNN text recognition training process into an inference model. Taking the model based on Resnet34_vd backbone network, using MJSynth and SynthText (two English text recognition synthetic datasets) for training, as an example ([model download address](link)). It can be converted as follow: ``` --c Set the yml configuration file of the algorithm, you need to set `Global.load_static_weights=False`, and write the path of the training model to be converted under the `Global.pretrained_model` parameter in the configuration file, without adding the file suffix .pdmodel, .pdopt or .pdparams. -# -o Set the address where the converted model will be saved. - -python3 tools/export_model.py -c configs/rec/rec_r34_vd_tps_bilstm_ctc.yml -o "./inference/starnet" +python3 tools/export_model.py -c configs/det/rec_r34_vd_none_bilstm_ctc.yml -o Global.checkpoints=./rec_r34_vd_none_bilstm_ctc_v2.0.train/best_accuracy Global.load_static_weights=False Global.save_inference_dir=./inference/rec_crnn ``` -For STAR-Net text recognition model inference, execute the following commands: +For CRNN text recognition model inference, execute the following commands: ``` python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/starnet/" --rec_image_shape="3, 32, 100" --rec_char_type="en" @@ -284,7 +278,11 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png ### 3. ATTENTION-BASED TEXT RECOGNITION MODEL INFERENCE ![](../imgs_words_en/word_336.png) +The recognition model based on Attention loss is different from ctc, and additional recognition algorithm parameters need to be set --rec_algorithm="RARE" After executing the command, the recognition result of the above image is as follows: +```bash +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./inference/rare/" --rec_image_shape="3, 32, 100" --rec_char_type="en" --rec_algorithm="RARE" +``` Predicts of ./doc/imgs_words_en/word_336.png:['super', 0.9999555] -- GitLab