diff --git a/deploy/hubserving/readme.md b/deploy/hubserving/readme.md index a39ac5a42b905b1efa73c02d7594511c8a7ea103..9351fa8d4fb8ee507d8e4f838397ecb615c20612 100755 --- a/deploy/hubserving/readme.md +++ b/deploy/hubserving/readme.md @@ -29,7 +29,7 @@ deploy/hubserving/ocr_system/ ### 1. 准备环境 ```shell # 安装paddlehub -pip3 install paddlehub==1.8.3 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple +pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple ``` ### 2. 下载推理模型 diff --git a/deploy/hubserving/readme_en.md b/deploy/hubserving/readme_en.md index 7d9a8629ef7d27e84e636f029202602a94d1d3f7..98ffcad63c822b4b03e58ae088cafd584aa824ab 100755 --- a/deploy/hubserving/readme_en.md +++ b/deploy/hubserving/readme_en.md @@ -30,7 +30,7 @@ The following steps take the 2-stage series service as an example. If only the d ### 1. Prepare the environment ```shell # Install paddlehub -pip3 install paddlehub==1.8.3 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple +pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple ``` ### 2. Download inference model diff --git a/deploy/slim/quantization/export_model.py b/deploy/slim/quantization/export_model.py index e9c1a8d31110ef20dd66be28d78b1e866fcd85ae..d94e53034a2bf67b364e6d91f83acfb9e5445b8a 100755 --- a/deploy/slim/quantization/export_model.py +++ b/deploy/slim/quantization/export_model.py @@ -101,7 +101,7 @@ def main(): quanter = QAT(config=quant_config) quanter.quantize(model) - init_model(config, model, logger) + init_model(config, model) model.eval() # build metric @@ -113,7 +113,7 @@ def main(): use_srn = config['Architecture']['algorithm'] == "SRN" model_type = config['Architecture']['model_type'] # start eval - metirc = program.eval(model, valid_dataloader, post_process_class, + metric = program.eval(model, valid_dataloader, post_process_class, eval_class, model_type, use_srn) logger.info('metric eval ***************') diff --git a/doc/doc_ch/recognition.md b/doc/doc_ch/recognition.md index 0f860065bef9eff8f90c18f120e43dcf0c2a47aa..2efd80e6e15dbcfbb3c342633d795eddbfd7558a 100644 --- a/doc/doc_ch/recognition.md +++ b/doc/doc_ch/recognition.md @@ -375,7 +375,9 @@ PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi 更多支持语种请参考: [多语言模型](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_ch/multi_languages.md#%E8%AF%AD%E7%A7%8D%E7%BC%A9%E5%86%99) -多语言模型训练方式与中文模型一致，训练数据集均为100w的合成数据，少量的字体可以在 [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) 上下载，提取码：frgi。 +多语言模型训练方式与中文模型一致，训练数据集均为100w的合成数据，少量的字体可以通过下面两种方式下载。 +* [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA)。提取码：frgi。 +* [google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view) 如您希望在现有模型效果的基础上调优，请参考下列说明修改配置文件： diff --git a/doc/doc_en/recognition_en.md b/doc/doc_en/recognition_en.md index e23166e0caef4f6a246502fa12101f86d61e4eac..556b75a515ed676557142157aa412f2783005eec 100644 --- a/doc/doc_en/recognition_en.md +++ b/doc/doc_en/recognition_en.md @@ -375,7 +375,9 @@ Currently, the multi-language algorithms supported by PaddleOCR are: For more supported languages, please refer to : [Multi-language model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md#4-support-languages-and-abbreviations) -The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded on [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA),Extraction code:frgi. +The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded using the following two methods. +* [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA),Extraction code:frgi. +* [Google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view) If you want to finetune on the basis of the existing model effect, please refer to the following instructions to modify the configuration file: diff --git a/test/ocr_det_params.txt b/test/ocr_det_params.txt index 01ac82d3d7d459ca324ec61cfcaac2386660a211..bdfd4d4f47431bca97437963e1dc56d1b57838bb 100644 --- a/test/ocr_det_params.txt +++ b/test/ocr_det_params.txt @@ -1,13 +1,12 @@ model_name:ocr_det python:python3.7 gpu_list:0|0,1 -Global.auto_cast:False +Global.auto_cast:null Global.epoch_num:10 Global.save_model_dir:./output/ -Global.save_inference_dir:./output/ Train.loader.batch_size_per_card: -Global.use_gpu -Global.pretrained_model +Global.use_gpu: +Global.pretrained_model:null trainer:norm|pact norm_train:tools/train.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained @@ -17,6 +16,8 @@ distill_train:null eval:tools/eval.py -c configs/det/det_mv3_db.yml -o +Global.save_inference_dir:./output/ +Global.pretrained_model: norm_export:tools/export_model.py -c configs/det/det_mv3_db.yml -o quant_export:deploy/slim/quantization/export_model.py -c configs/det/det_mv3_db.yml -o fpgm_export:deploy/slim/prune/export_prune_model.py @@ -29,7 +30,6 @@ inference:tools/infer/predict_det.py --rec_batch_num:1 --use_tensorrt:True|False --precision:fp32|fp16|int8 ---det_model_dir ---image_dir ---save_log_path - +--det_model_dir:./inference/ch_ppocr_mobile_v2.0_det_infer/ +--image_dir:./inference/ch_det_data_50/all-sum-510/ +--save_log_path:./test/output/ diff --git a/test/prepare.sh b/test/prepare.sh index e2427292ccf6f369662f7df83c0445dc46083b38..f6941b9ced8eb3b2fc6dda2a7ac76d025f7a18e1 100644 --- a/test/prepare.sh +++ b/test/prepare.sh @@ -26,9 +26,9 @@ IFS=$'\n' # The training params model_name=$(func_parser_value "${lines[0]}") train_model_list=$(func_parser_value "${lines[0]}") + trainer_list=$(func_parser_value "${lines[10]}") -echo $train_model_list # MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer'] MODE=$2 # prepare pretrained weights and dataset @@ -68,8 +68,8 @@ else rm -rf ./train_data/icdar2015 wget -nc -P ./train_data https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar if [ ${model_name} = "ocr_det" ]; then - eval_model_name="ch_ppocr_mobile_v2.0_det_train" - wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar + eval_model_name="ch_ppocr_mobile_v2.0_det_infer" + wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar cd ./inference && tar xf ${eval_model_name}.tar && cd ../ else eval_model_name="ch_ppocr_mobile_v2.0_rec_train" @@ -102,7 +102,7 @@ for train_model in ${train_model_list[*]}; do # eval for slim_trainer in ${trainer_list[*]}; do if [ ${slim_trainer} = "norm" ]; then - if [ ${model_name} = "ocr_det" ]; then + if [ ${model_name} = "det" ]; then eval_model_name="ch_ppocr_mobile_v2.0_det_train" wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar cd ./inference && tar xf ${eval_model_name}.tar && cd ../ @@ -112,7 +112,7 @@ for train_model in ${train_model_list[*]}; do cd ./inference && tar xf ${eval_model_name}.tar && cd ../ fi elif [ ${slim_trainer} = "pact" ]; then - if [ ${model_name} = "ocr_det" ]; then + if [ ${model_name} = "det" ]; then eval_model_name="ch_ppocr_mobile_v2.0_det_quant_train" wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_quant_train.tar cd ./inference && tar xf ${eval_model_name}.tar && cd ../ @@ -122,7 +122,7 @@ for train_model in ${train_model_list[*]}; do cd ./inference && tar xf ${eval_model_name}.tar && cd ../ fi elif [ ${slim_trainer} = "distill" ]; then - if [ ${model_name} = "ocr_det" ]; then + if [ ${model_name} = "det" ]; then eval_model_name="ch_ppocr_mobile_v2.0_det_distill_train" wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_distill_train.tar cd ./inference && tar xf ${eval_model_name}.tar && cd ../ @@ -132,7 +132,7 @@ for train_model in ${train_model_list[*]}; do cd ./inference && tar xf ${eval_model_name}.tar && cd ../ fi elif [ ${slim_trainer} = "fpgm" ]; then - if [ ${model_name} = "ocr_det" ]; then + if [ ${model_name} = "det" ]; then eval_model_name="ch_ppocr_mobile_v2.0_det_prune_train" wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_train.tar cd ./inference && tar xf ${eval_model_name}.tar && cd ../ diff --git a/test/test.sh b/test/test.sh index 2a27563ffaa2b1b96b58cbff89546acf7a286210..f2ac3f8b29af1be08e8eb5b836133dc53ad3d5b2 100644 --- a/test/test.sh +++ b/test/test.sh @@ -41,59 +41,51 @@ gpu_list=$(func_parser_value "${lines[2]}") autocast_list=$(func_parser_value "${lines[3]}") autocast_key=$(func_parser_key "${lines[3]}") epoch_key=$(func_parser_key "${lines[4]}") +epoch_num=$(func_parser_value "${lines[4]}") save_model_key=$(func_parser_key "${lines[5]}") -save_infer_key=$(func_parser_key "${lines[6]}") -train_batch_key=$(func_parser_key "${lines[7]}") -train_use_gpu_key=$(func_parser_key "${lines[8]}") -pretrain_model_key=$(func_parser_key "${lines[9]}") - -trainer_list=$(func_parser_value "${lines[10]}") -norm_trainer=$(func_parser_value "${lines[11]}") -pact_trainer=$(func_parser_value "${lines[12]}") -fpgm_trainer=$(func_parser_value "${lines[13]}") -distill_trainer=$(func_parser_value "${lines[14]}") - -eval_py=$(func_parser_value "${lines[15]}") -norm_export=$(func_parser_value "${lines[16]}") -pact_export=$(func_parser_value "${lines[17]}") -fpgm_export=$(func_parser_value "${lines[18]}") -distill_export=$(func_parser_value "${lines[19]}") - -inference_py=$(func_parser_value "${lines[20]}") -use_gpu_key=$(func_parser_key "${lines[21]}") -use_gpu_list=$(func_parser_value "${lines[21]}") -use_mkldnn_key=$(func_parser_key "${lines[22]}") -use_mkldnn_list=$(func_parser_value "${lines[22]}") -cpu_threads_key=$(func_parser_key "${lines[23]}") -cpu_threads_list=$(func_parser_value "${lines[23]}") -batch_size_key=$(func_parser_key "${lines[24]}") -batch_size_list=$(func_parser_value "${lines[24]}") -use_trt_key=$(func_parser_key "${lines[25]}") -use_trt_list=$(func_parser_value "${lines[25]}") -precision_key=$(func_parser_key "${lines[26]}") -precision_list=$(func_parser_value "${lines[26]}") -model_dir_key=$(func_parser_key "${lines[27]}") -image_dir_key=$(func_parser_key "${lines[28]}") -save_log_key=$(func_parser_key "${lines[29]}") +train_batch_key=$(func_parser_key "${lines[6]}") +train_use_gpu_key=$(func_parser_key "${lines[7]}") +pretrain_model_key=$(func_parser_key "${lines[8]}") +pretrain_model_value=$(func_parser_value "${lines[8]}") + +trainer_list=$(func_parser_value "${lines[9]}") +norm_trainer=$(func_parser_value "${lines[10]}") +pact_trainer=$(func_parser_value "${lines[11]}") +fpgm_trainer=$(func_parser_value "${lines[12]}") +distill_trainer=$(func_parser_value "${lines[13]}") + +eval_py=$(func_parser_value "${lines[14]}") + +save_infer_key=$(func_parser_key "${lines[15]}") +export_weight=$(func_parser_key "${lines[16]}") +norm_export=$(func_parser_value "${lines[17]}") +pact_export=$(func_parser_value "${lines[18]}") +fpgm_export=$(func_parser_value "${lines[19]}") +distill_export=$(func_parser_value "${lines[20]}") + +inference_py=$(func_parser_value "${lines[21]}") +use_gpu_key=$(func_parser_key "${lines[22]}") +use_gpu_list=$(func_parser_value "${lines[22]}") +use_mkldnn_key=$(func_parser_key "${lines[23]}") +use_mkldnn_list=$(func_parser_value "${lines[23]}") +cpu_threads_key=$(func_parser_key "${lines[24]}") +cpu_threads_list=$(func_parser_value "${lines[24]}") +batch_size_key=$(func_parser_key "${lines[25]}") +batch_size_list=$(func_parser_value "${lines[25]}") +use_trt_key=$(func_parser_key "${lines[26]}") +use_trt_list=$(func_parser_value "${lines[26]}") +precision_key=$(func_parser_key "${lines[27]}") +precision_list=$(func_parser_value "${lines[27]}") +infer_model_key=$(func_parser_key "${lines[28]}") +infer_model=$(func_parser_value "${lines[28]}") +image_dir_key=$(func_parser_key "${lines[29]}") +infer_img_dir=$(func_parser_value "${lines[29]}") +save_log_key=$(func_parser_key "${lines[30]}") LOG_PATH="./test/output" mkdir -p ${LOG_PATH} status_log="${LOG_PATH}/results.log" -if [ ${MODE} = "lite_train_infer" ]; then - export infer_img_dir="./train_data/icdar2015/text_localization/ch4_test_images/" - export epoch_num=10 -elif [ ${MODE} = "whole_infer" ]; then - export infer_img_dir="./train_data/icdar2015/text_localization/ch4_test_images/" - export epoch_num=10 -elif [ ${MODE} = "whole_train_infer" ]; then - export infer_img_dir="./train_data/icdar2015/text_localization/ch4_test_images/" - export epoch_num=300 -else - export infer_img_dir="./inference/ch_det_data_50/all-sum-510" - export infer_model_dir="./inference/ch_ppocr_mobile_v2.0_det_train/best_accuracy" -fi - function func_inference(){ IFS='|' @@ -109,8 +101,8 @@ function func_inference(){ for use_mkldnn in ${use_mkldnn_list[*]}; do for threads in ${cpu_threads_list[*]}; do for batch_size in ${batch_size_list[*]}; do - _save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}" - command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_mkldnn_key}=${use_mkldnn} ${cpu_threads_key}=${threads} ${model_dir_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir} ${save_log_key}=${_save_log_path} --benchmark=True" + _save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log" + command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_mkldnn_key}=${use_mkldnn} ${cpu_threads_key}=${threads} ${infer_model_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir} ${save_log_key}=${_save_log_path} --benchmark=True" eval $command status_check $? "${command}" "${status_log}" done @@ -123,8 +115,8 @@ function func_inference(){ continue fi for batch_size in ${batch_size_list[*]}; do - _save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}" - command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_trt_key}=${use_trt} ${precision_key}=${precision} ${model_dir_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir} ${save_log_key}=${_save_log_path} --benchmark=True" + _save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log" + command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_trt_key}=${use_trt} ${precision_key}=${precision} ${infer_model_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir} ${save_log_key}=${_save_log_path} --benchmark=True" eval $command status_check $? "${command}" "${status_log}" done @@ -138,12 +130,13 @@ if [ ${MODE} != "infer" ]; then IFS="|" for gpu in ${gpu_list[*]}; do - train_use_gpu=True + use_gpu=True if [ ${gpu} = "-1" ];then - train_use_gpu=False + use_gpu=False env="" elif [ ${#gpu} -le 1 ];then env="export CUDA_VISIBLE_DEVICES=${gpu}" + eval ${env} elif [ ${#gpu} -le 15 ];then IFS="," array=(${gpu}) @@ -155,6 +148,7 @@ for gpu in ${gpu_list[*]}; do ips=${array[0]} gpu=${array[1]} IFS="|" + env=" " fi for autocast in ${autocast_list[*]}; do for trainer in ${trainer_list[*]}; do @@ -179,13 +173,32 @@ for gpu in ${gpu_list[*]}; do continue fi - save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}" - if [ ${#gpu} -le 2 ];then # epoch_num #TODO - cmd="${python} ${run_train} ${train_use_gpu_key}=${train_use_gpu} ${autocast_key}=${autocast} ${epoch_key}=${epoch_num} ${save_model_key}=${save_log} " - elif [ ${#gpu} -le 15 ];then - cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${autocast_key}=${autocast} ${epoch_key}=${epoch_num} ${save_model_key}=${save_log}" + # not set autocast when autocast is null + if [ ${autocast} = "null" ]; then + set_autocast=" " + else + set_autocast="${autocast_key}=${autocast}" + fi + # not set epoch when whole_train_infer + if [ ${MODE} != "whole_train_infer" ]; then + set_epoch="${epoch_key}=${epoch_num}" + else + set_epoch=" " + fi + # set pretrain + if [ ${pretrain_model_value} != "null" ]; then + set_pretrain="${pretrain_model_key}=${pretrain_model_value}" else - cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${autocast_key}=${autocast} ${epoch_key}=${epoch_num} ${save_model_key}=${save_log}" + set_pretrain=" " + fi + + save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}" + if [ ${#gpu} -le 2 ];then # train with cpu or single gpu + cmd="${python} ${run_train} ${train_use_gpu_key}=${use_gpu} ${save_model_key}=${save_log} ${set_epoch} ${set_pretrain} ${set_autocast}" + elif [ ${#gpu} -le 15 ];then # train with multi-gpu + cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${save_model_key}=${save_log} ${set_epoch} ${set_pretrain} ${set_autocast}" + else # train with multi-machine + cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${save_model_key}=${save_log} ${set_pretrain} ${set_epoch} ${set_autocast}" fi # run train eval $cmd @@ -198,24 +211,27 @@ for gpu in ${gpu_list[*]}; do # run export model save_infer_path="${save_log}" - export_cmd="${python} ${run_export} ${save_model_key}=${save_log} ${pretrain_model_key}=${save_log}/latest ${save_infer_key}=${save_infer_path}" + export_cmd="${python} ${run_export} ${save_model_key}=${save_log} ${export_weight}=${save_log}/latest ${save_infer_key}=${save_infer_path}" eval $export_cmd status_check $? "${export_cmd}" "${status_log}" #run inference + eval $env save_infer_path="${save_log}" func_inference "${python}" "${inference_py}" "${save_infer_path}" "${LOG_PATH}" "${infer_img_dir}" + eval "unset CUDA_VISIBLE_DEVICES" done done done else - save_infer_path="${LOG_PATH}/${MODE}" - run_export=${norm_export} - export_cmd="${python} ${run_export} ${save_model_key}=${save_infer_path} ${pretrain_model_key}=${infer_model_dir} ${save_infer_key}=${save_infer_path}" - eval $export_cmd - status_check $? "${export_cmd}" "${status_log}" - + GPUID=$3 + if [ ${#GPUID} -le 0 ];then + env=" " + else + env="export CUDA_VISIBLE_DEVICES=${GPUID}" + fi + echo $env #run inference - func_inference "${python}" "${inference_py}" "${save_infer_path}" "${LOG_PATH}" "${infer_img_dir}" + func_inference "${python}" "${inference_py}" "${infer_model}" "${LOG_PATH}" "${infer_img_dir}" fi diff --git a/test1/table/README_ch.md b/test1/table/README_ch.md index 03f002f98b3f37a251638d1b1e11812ef703f5fc..5c3c9a285f6452e763b499695f5d8d875f21cd44 100644 --- a/test1/table/README_ch.md +++ b/test1/table/README_ch.md @@ -19,7 +19,29 @@ ### 2.1 训练 -TBD +#### 数据准备 +训练数据使用公开数据集[PubTabNet](https://arxiv.org/abs/1911.10683)，可以从[官网](https://github.com/ibm-aur-nlp/PubTabNet)下载。PubTabNet数据集包含约50万张表格数据的图像，以及图像对应的html格式的注释。 + +#### 启动训练 +*如果您安装的是cpu版本，请将配置文件中的 `use_gpu` 字段修改为false* +```shell +# 单机单卡训练 +python3 tools/train.py -c configs/table/table_mv3.yml +# 单机多卡训练，通过 --gpus 参数设置使用的GPU ID +python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs/table/table_mv3.yml +``` + +上述指令中，通过-c 选择训练使用configs/table/table_mv3.yml配置文件。有关配置文件的详细解释，请参考[链接](./config.md)。 + +#### 断点训练 + +如果训练程序中断，如果希望加载训练中断的模型从而恢复训练，可以通过指定Global.checkpoints指定要加载的模型路径： +```shell +python3 tools/train.py -c configs/table/table_mv3.yml -o Global.checkpoints=./your/trained/model +``` + +**注意**：`Global.checkpoints`的优先级高于`Global.pretrain_weights`的优先级，即同时指定两个参数时，优先加载`Global.checkpoints`指定的模型，如果`Global.checkpoints`指定的模型路径有误，会加载`Global.pretrain_weights`指定的模型。 + ### 2.2 评估 先cd到PaddleOCR/ppstructure目录下 diff --git a/tools/infer/predict_det.py b/tools/infer/predict_det.py index bbf3659cbc6c34e550ba08440312a09da6362df0..6a45f81e48371093edc9391bd3b8dd263df25c92 100755 --- a/tools/infer/predict_det.py +++ b/tools/infer/predict_det.py @@ -175,7 +175,7 @@ class TextDetector(object): st = time.time() - if args.benchmark: + if self.args.benchmark: self.autolog.times.start() data = transform(data, self.preprocess_op) @@ -186,7 +186,7 @@ class TextDetector(object): shape_list = np.expand_dims(shape_list, axis=0) img = img.copy() - if args.benchmark: + if self.args.benchmark: self.autolog.times.stamp() self.input_tensor.copy_from_cpu(img) @@ -195,7 +195,7 @@ class TextDetector(object): for output_tensor in self.output_tensors: output = output_tensor.copy_to_cpu() outputs.append(output) - if args.benchmark: + if self.args.benchmark: self.autolog.times.stamp() preds = {} @@ -220,7 +220,7 @@ class TextDetector(object): else: dt_boxes = self.filter_tag_det_res(dt_boxes, ori_im.shape) - if args.benchmark: + if self.args.benchmark: self.autolog.times.end(stamp=True) et = time.time() return dt_boxes, et - st diff --git a/tools/infer/predict_system.py b/tools/infer/predict_system.py index 715bd3fa9d596dd60f7f789f3e367734ffec608b..eae0e27cd284ccce9f41f0c20b05dee09f46fc84 100755 --- a/tools/infer/predict_system.py +++ b/tools/infer/predict_system.py @@ -174,8 +174,6 @@ def main(args): logger.info("The predict total time is {}".format(time.time() - _st)) logger.info("\nThe predict total time is {}".format(total_time)) - img_num = text_sys.text_detector.det_times.img_num - if __name__ == "__main__": args = utility.parse_args() diff --git a/tools/infer/utility.py b/tools/infer/utility.py index cf14e4abd71f1ac6e2ceec11163e635daef11f4d..bf05a0dbaf56b6ccee3b8d3941c3890bca104832 100755 --- a/tools/infer/utility.py +++ b/tools/infer/utility.py @@ -37,7 +37,7 @@ def init_args(): parser.add_argument("--use_gpu", type=str2bool, default=True) parser.add_argument("--ir_optim", type=str2bool, default=True) parser.add_argument("--use_tensorrt", type=str2bool, default=False) - parser.add_argument("--min_subgraph_size", type=int, default=3) + parser.add_argument("--min_subgraph_size", type=int, default=10) parser.add_argument("--precision", type=str, default="fp32") parser.add_argument("--gpu_mem", type=int, default=500) @@ -164,7 +164,7 @@ def create_predictor(args, mode, logger): config.enable_use_gpu(args.gpu_mem, 0) if args.use_tensorrt: config.enable_tensorrt_engine( - precision_mode=inference.PrecisionType.Float32, + precision_mode=precision, max_batch_size=args.max_batch_size, min_subgraph_size=args.min_subgraph_size) # skip the minmum trt subgraph