Merge remote-tracking branch 'origin/dygraph' into dygraph

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 [ ${autocast} = "null" ]; then
+                set_autocast=" "
             else
-                cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${autocast_key}=${autocast} ${epoch_key}=${epoch_num} ${save_model_key}=${save_log}"
+                set_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}=${pretrain_model_value}"
+            else
+                set_pretrain=" "
+            fi
+
+            save_log="${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

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

tools/eval.py

@@ -27,7 +27,7 @@ from ppocr.data import build_dataloader
 from ppocr.modeling.architectures import build_model
 from ppocr.postprocess import build_post_process
 from ppocr.metrics import build_metric
-from ppocr.utils.save_load import init_model
+from ppocr.utils.save_load import init_model, load_pretrained_params
 from ppocr.utils.utility import print_dict
 import tools.program as program
 
@@ -55,7 +55,10 @@ def main():
 
     model = build_model(config['Architecture'])
     use_srn = config['Architecture']['algorithm'] == "SRN"
+    if "model_type" in config['Architecture'].keys():
         model_type = config['Architecture']['model_type']
+    else:
+        model_type = None
 
     best_model_dict = init_model(config, model)
     if len(best_model_dict):

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

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()

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

tools/program.py

@@ -186,7 +186,10 @@ def train(config,
     model.train()
 
     use_srn = config['Architecture']['algorithm'] == "SRN"
+    try: 
         model_type = config['Architecture']['model_type']
+    except: 
+        model_type = None
 
     if 'start_epoch' in best_model_dict:
         start_epoch = best_model_dict['start_epoch']

tools/train.py

@@ -98,7 +98,6 @@ def main(config, device, logger, vdl_writer):
     eval_class = build_metric(config['Metric'])
     # load pretrain model
     pre_best_model_dict = load_dygraph_params(config, model, logger, optimizer)
-
     logger.info('train dataloader has {} iters'.format(len(train_dataloader)))
     if valid_dataloader is not None:
         logger.info('valid dataloader has {} iters'.format(