diff --git a/doc/doc_ch/algorithm_rec_can.md b/doc/doc_ch/algorithm_rec_can.md index 2cc5a72bf1767fd2a90278c7b91662c922e2697e..13e868e505262c1c353ec58981e609f1b0091c1d 100644 --- a/doc/doc_ch/algorithm_rec_can.md +++ b/doc/doc_ch/algorithm_rec_can.md @@ -57,24 +57,22 @@ python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs **注意：** - 我们提供的数据集，即[`CROHME数据集`](https://paddleocr.bj.bcebos.com/dataset/CROHME.tar)将手写公式存储为黑底白字的格式，若您自行准备的数据集与之相反，即以白底黑字模式存储，请在训练时做出如下修改 ``` -python3 tools/train.py -c configs/rec/rec_d28_can.yml --o Train.dataset.transforms.GrayImageChannelFormat.inverse=False +python3 tools/train.py -c configs/rec/rec_d28_can.yml -o Train.dataset.transforms.GrayImageChannelFormat.inverse=False ``` - 默认每训练1个epoch（1105次iteration）进行1次评估，若您更改训练的batch_size，或更换数据集，请在训练时作出如下修改 ``` -python3 tools/train.py -c configs/rec/rec_d28_can.yml --o Global.eval_batch_step=[0, {length_of_dataset//batch_size}] +python3 tools/train.py -c configs/rec/rec_d28_can.yml -o Global.eval_batch_step=[0, {length_of_dataset//batch_size}] ``` # ### 3.2 评估 -可下载已训练完成的[模型文件](https://paddleocr.bj.bcebos.com/contribution/can_train.tar)，使用如下命令进行评估： +可下载已训练完成的[模型文件](https://paddleocr.bj.bcebos.com/contribution/rec_d28_can_train.tar)，使用如下命令进行评估： ```shell # 注意将pretrained_model的路径设置为本地路径。若使用自行训练保存的模型，请注意修改路径和文件名为{path/to/weights}/{model_name}。 -python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_d28_can.yml -o Global.pretrained_model=./rec_d28_can_train/CAN +python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_d28_can.yml -o Global.pretrained_model=./rec_d28_can_train/best_accuracy.pdparams ``` @@ -83,7 +81,7 @@ python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec 使用如下命令进行单张图片预测： ```shell # 注意将pretrained_model的路径设置为本地路径。 -python3 tools/infer_rec.py -c configs/rec/rec_d28_can.yml -o Architecture.Head.attdecoder.is_train=False Global.infer_img='./doc/datasets/crohme_demo/hme_00.jpg' Global.pretrained_model=./rec_d28_can_train/CAN +python3 tools/infer_rec.py -c configs/rec/rec_d28_can.yml -o Architecture.Head.attdecoder.is_train=False Global.infer_img='./doc/datasets/crohme_demo/hme_00.jpg' Global.pretrained_model=./rec_d28_can_train/best_accuracy.pdparams # 预测文件夹下所有图像时，可修改infer_img为文件夹，如 Global.infer_img='./doc/datasets/crohme_demo/'。 ``` @@ -94,11 +92,11 @@ python3 tools/infer_rec.py -c configs/rec/rec_d28_can.yml -o Architecture.Head.a ### 4.1 Python推理 -首先将训练得到best模型，转换成inference model。这里以训练完成的模型为例（[模型下载地址](https://paddleocr.bj.bcebos.com/contribution/can_train.tar) )，可以使用如下命令进行转换： +首先将训练得到best模型，转换成inference model。这里以训练完成的模型为例（[模型下载地址](https://paddleocr.bj.bcebos.com/contribution/rec_d28_can_train.tar) )，可以使用如下命令进行转换： ```shell # 注意将pretrained_model的路径设置为本地路径。 -python3 tools/export_model.py -c configs/rec/rec_d28_can.yml -o Global.pretrained_model=./rec_d28_can_train/CAN Global.save_inference_dir=./inference/rec_d28_can/ Architecture.Head.attdecoder.is_train=False +python3 tools/export_model.py -c configs/rec/rec_d28_can.yml -o Global.pretrained_model=./rec_d28_can_train/best_accuracy.pdparams Global.save_inference_dir=./inference/rec_d28_can/ Architecture.Head.attdecoder.is_train=False # 目前的静态图模型默认的输出长度最大为36，如果您需要预测更长的序列，请在导出模型时指定其输出序列为合适的值，例如 Architecture.Head.max_text_length=72 ``` diff --git a/doc/doc_en/algorithm_rec_can_en.md b/doc/doc_en/algorithm_rec_can_en.md index 5cc7038f668e394c48169e46a83a3f0e1a62a0e1..ef114990a8cc50d04a12acd65c477509e4b0ca42 100644 --- a/doc/doc_en/algorithm_rec_can_en.md +++ b/doc/doc_en/algorithm_rec_can_en.md @@ -53,14 +53,14 @@ Evaluation: ``` # GPU evaluation -python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_d28_can.yml -o Global.pretrained_model=./rec_d28_can_train/CAN +python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_d28_can.yml -o Global.pretrained_model=./rec_d28_can_train/best_accuracy.pdparams ``` Prediction: ``` # The configuration file used for prediction must match the training -python3 tools/infer_rec.py -c configs/rec/rec_d28_can.yml -o Architecture.Head.attdecoder.is_train=False Global.infer_img='./doc/crohme_demo/hme_00.jpg' Global.pretrained_model=./rec_d28_can_train/CAN +python3 tools/infer_rec.py -c configs/rec/rec_d28_can.yml -o Architecture.Head.attdecoder.is_train=False Global.infer_img='./doc/crohme_demo/hme_00.jpg' Global.pretrained_model=./rec_d28_can_train/best_accuracy.pdparams ``` @@ -71,7 +71,7 @@ python3 tools/infer_rec.py -c configs/rec/rec_d28_can.yml -o Architecture.Head.a First, the model saved during the CAN handwritten mathematical expression recognition training process is converted into an inference model. you can use the following command to convert: ``` -python3 tools/export_model.py -c configs/rec/rec_d28_can.yml -o Global.save_inference_dir=./inference/rec_d28_can/ Architecture.Head.attdecoder.is_train=False +python3 tools/export_model.py -c configs/rec/rec_d28_can.yml -o Global.pretrained_model=./rec_d28_can_train/best_accuracy.pdparams Global.save_inference_dir=./inference/rec_d28_can/ Architecture.Head.attdecoder.is_train=False # The default output max length of the model is 36. If you need to predict a longer sequence, please specify its output sequence as an appropriate value when exporting the model, as: Architecture.Head.max_ text_ length=72 ``` @@ -79,7 +79,7 @@ python3 tools/export_model.py -c configs/rec/rec_d28_can.yml -o Global.save_infe For CAN handwritten mathematical expression recognition model inference, the following commands can be executed: ``` -python3 tools/infer/predict_rec.py --image_dir="./doc/crohme_demo/hme_00.jpg" --rec_algorithm="CAN" --rec_batch_num=1 --rec_model_dir="./inference/rec_d28_can/" --rec_char_dict_path="./ppocr/utils/dict/latex_symbol_dict.txt" +python3 tools/infer/predict_rec.py --image_dir="./doc/datasets/crohme_demo/hme_00.jpg" --rec_algorithm="CAN" --rec_batch_num=1 --rec_model_dir="./inference/rec_d28_can/" --rec_char_dict_path="./ppocr/utils/dict/latex_symbol_dict.txt" # If you need to predict on a picture with black characters on a white background, please set: -- rec_ image_ inverse=False ``` diff --git a/test_tipc/configs/sr_telescope/sr_telescope.yml b/test_tipc/configs/sr_telescope/sr_telescope.yml index d3c10448e423ff0305950ea39664379e60f8a113..c78a42d0efb7bbcdd182861a6474d87c9f68b3d4 100644 --- a/test_tipc/configs/sr_telescope/sr_telescope.yml +++ b/test_tipc/configs/sr_telescope/sr_telescope.yml @@ -51,7 +51,7 @@ Metric: Train: dataset: name: LMDBDataSetSR - data_dir: ./train_data/TextZoom/train + data_dir: ./train_data/TextZoom/test transforms: - SRResize: imgH: 32 diff --git a/test_tipc/configs/sr_telescope/train_infer_python.txt b/test_tipc/configs/sr_telescope/train_infer_python.txt index 4dcfa29ee146b3b2662122966d859142bb0ed0c5..7235f07e8c72411f6ae979e666e624c32de935b9 100644 --- a/test_tipc/configs/sr_telescope/train_infer_python.txt +++ b/test_tipc/configs/sr_telescope/train_infer_python.txt @@ -4,12 +4,12 @@ python:python3.7 gpu_list:0|0,1 Global.use_gpu:True|True Global.auto_cast:null -Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300 +Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=300 Global.save_model_dir:./output/ Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=16 Global.pretrained_model:null train_model_name:latest -train_infer_img_dir:./inference/sr_inference +train_infer_img_dir:./inference/rec_inference null:null ## trainer:norm_train @@ -21,7 +21,7 @@ null:null null:null ## ===========================eval_params=========================== -eval:tools/eval.py -c test_tipc/configs/sr_telescope/sr_telescope.yml -o +eval:null null:null ## ===========================infer_params=========================== @@ -44,8 +44,8 @@ inference:tools/infer/predict_sr.py --sr_image_shape="1,32,128" --rec_algorithm= --rec_batch_num:1 --use_tensorrt:False --precision:fp32 ---rec_model_dir: ---image_dir:./inference/sr_inference +--sr_model_dir: +--image_dir:./inference/rec_inference --save_log_path:./test/output/ --benchmark:True null:null diff --git a/test_tipc/prepare.sh b/test_tipc/prepare.sh index 452ec31c48f2b5bd807a3a0a7c6bd0d95b520e28..02ee8a24d241195d1330ea42fc05ed35dd7a87b7 100644 --- a/test_tipc/prepare.sh +++ b/test_tipc/prepare.sh @@ -150,6 +150,7 @@ if [ ${MODE} = "lite_train_lite_infer" ];then # pretrain lite train data wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams --no-check-certificate wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar --no-check-certificate + cd ./pretrain_models/ && tar xf det_mv3_db_v2.0_train.tar && cd ../ if [[ ${model_name} =~ "ch_PP-OCRv2_det" ]];then wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar --no-check-certificate cd ./pretrain_models/ && tar xf ch_PP-OCRv2_det_distill_train.tar && cd ../ @@ -179,7 +180,6 @@ if [ ${MODE} = "lite_train_lite_infer" ];then wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/ppstructure/models/tablemaster/table_structure_tablemaster_train.tar --no-check-certificate cd ./pretrain_models/ && tar xf table_structure_tablemaster_train.tar && cd ../ fi - cd ./pretrain_models/ && tar xf det_mv3_db_v2.0_train.tar && cd ../ rm -rf ./train_data/icdar2015 rm -rf ./train_data/ic15_data rm -rf ./train_data/pubtabnet