Merge branch 'PaddlePaddle:dygraph' into dygraph

configs/det/det_r50_vd_sast_icdar15.yml

@@ -8,7 +8,7 @@ Global:
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [4000, 5000]
   cal_metric_during_train: False
-  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained/
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
   checkpoints:
   save_inference_dir:
   use_visualdl: False

configs/det/det_r50_vd_sast_totaltext.yml

@@ -8,7 +8,7 @@ Global:
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [4000, 5000]
   cal_metric_during_train: False
-  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained/
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
   checkpoints: 
   save_inference_dir:
   use_visualdl: False

test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

+===========================paddle2onnx_params===========================
+2onnx: paddle2onnx
+--model_dir:./inference/ch_ppocr_mobile_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--save_file:./inference/det_mobile_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
\ No newline at end of file

test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt

+===========================serving_params===========================
+model_name:ocr_det_mobile
+python:python3.7|cpp
+trans_model:-m paddle_serving_client.convert
+--dirname:./inference/ch_ppocr_mobile_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--serving_server:./deploy/pdserving/ppocr_det_mobile_2.0_serving/
+--serving_client:./deploy/pdserving/ppocr_det_mobile_2.0_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency=1
+op.det.local_service_conf.devices:null|0
+op.det.local_service_conf.use_mkldnn:True|False
+op.det.local_service_conf.thread_num:1|6
+op.det.local_service_conf.use_trt:False|True
+op.det.local_service_conf.precision:fp32|fp16|int8
+pipline:pipeline_rpc_client.py|pipeline_http_client.py
+--image_dir:../../doc/imgs
\ No newline at end of file

test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

+===========================paddle2onnx_params===========================
+2onnx: paddle2onnx
+--model_dir:./inference/ch_ppocr_server_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--save_file:./inference/det_server_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--det_model_dir:
+--image_dir:./inference/det_inference
\ No newline at end of file

test_tipc/configs/ppocr_det_server/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt

+===========================serving_params===========================
+model_name:ocr_det_server
+python:python3.7|cpp
+trans_model:-m paddle_serving_client.convert
+--dirname:./inference/ch_ppocr_server_v2.0_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--serving_server:./deploy/pdserving/ppocr_det_server_2.0_serving/
+--serving_client:./deploy/pdserving/ppocr_det_server_2.0_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency=1
+op.det.local_service_conf.devices:null|0
+op.det.local_service_conf.use_mkldnn:True|False
+op.det.local_service_conf.thread_num:1|6
+op.det.local_service_conf.use_trt:False|True
+op.det.local_service_conf.precision:fp32|fp16|int8
+pipline:pipeline_rpc_client.py|pipeline_http_client.py
+--image_dir:../../doc/imgs_words_en
\ No newline at end of file

test_tipc/configs/ppocr_rec_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

+===========================paddle2onnx_params===========================
+2onnx: paddle2onnx
+--model_dir:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--save_file:./inference/rec_mobile_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--rec_model_dir:
+--image_dir:./inference/rec_inference
\ No newline at end of file

test_tipc/configs/ppocr_rec_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt

+===========================serving_params===========================
+model_name:ocr_rec_mobile
+python:python3.7|cpp
+trans_model:-m paddle_serving_client.convert
+--dirname:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--serving_server:./deploy/pdserving/ppocr_rec_mobile_2.0_serving/
+--serving_client:./deploy/pdserving/ppocr_rec_mobile_2.0_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency=1
+op.rec.local_service_conf.devices:null|0
+op.rec.local_service_conf.use_mkldnn:True|False
+op.rec.local_service_conf.thread_num:1|6
+op.rec.local_service_conf.use_trt:False|True
+op.rec.local_service_conf.precision:fp32|fp16|int8
+pipline:pipeline_rpc_client.py|pipeline_http_client.py
+--image_dir:../../doc/imgs_words_en
\ No newline at end of file

test_tipc/configs/ppocr_rec_server/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

+===========================paddle2onnx_params===========================
+2onnx: paddle2onnx
+--model_dir:./inference/ch_ppocr_server_v2.0_rec_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--save_file:./inference/rec_server_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--rec_model_dir:
+--image_dir:./inference/rec_inference
\ No newline at end of file

test_tipc/configs/ppocr_rec_server/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt

+===========================serving_params===========================
+model_name:ocr_rec_server
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--dirname:./inference/ch_ppocr_server_v2.0_rec_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--serving_server:./deploy/pdserving/ppocr_rec_server_2.0_serving/
+--serving_client:./deploy/pdserving/ppocr_rec_server_2.0_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_rec.py --config=config.yml --opt op.rec.concurrency=1
+op.rec.local_service_conf.devices:null|0
+op.rec.local_service_conf.use_mkldnn:True|False
+op.rec.local_service_conf.thread_num:1|6
+op.rec.local_service_conf.use_trt:False|True
+op.rec.local_service_conf.precision:fp32|fp16|int8
+pipline:pipeline_rpc_client.py|pipeline_http_client.py
+--image_dir:../../doc/imgs_words_en
\ No newline at end of file

test_tipc/docs/test_paddle2onnx.md

@@ -18,10 +18,10 @@ PaddleServing预测功能测试的主程序为`test_paddle2onnx.sh`，可以测
 先运行`prepare.sh`准备数据和模型，然后运行`test_paddle2onnx.sh`进行测试，最终在```test_tipc/output```目录下生成`paddle2onnx_infer_*.log`后缀的日志文件。
 
 ```shell
-bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile_params.txt "paddle2onnx_infer"
+bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt "paddle2onnx_infer"
 
 # 用法:
-bash test_tipc/test_paddle2onnx.sh ./test_tipc/configs/ppocr_det_mobile_params.txt
+bash test_tipc/test_paddle2onnx.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt
 ```  
 
 #### 运行结果

test_tipc/docs/test_serving.md

@@ -20,10 +20,10 @@ PaddleServing预测功能测试的主程序为`test_serving.sh`，可以测试
 先运行`prepare.sh`准备数据和模型，然后运行`test_serving.sh`进行测试，最终在```test_tipc/output```目录下生成`serving_infer_*.log`后缀的日志文件。
 
 ```shell
-bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile_params.txt "serving_infer"
+bash test_tipc/prepare.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt "serving_infer"
 
 # 用法:
-bash test_tipc/test_serving.sh ./test_tipc/configs/ppocr_det_mobile_params.txt
+bash test_tipc/test_serving.sh ./test_tipc/configs/ppocr_det_mobile/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt
 ```  
 
 #### 运行结果

test_tipc/prepare.sh

@@ -87,7 +87,8 @@ elif [ ${MODE} = "whole_infer" ];then
         rm -rf ./train_data/icdar2015
         wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar --no-check-certificate
-        cd ./inference && tar xf ${eval_model_name}.tar && tar xf ch_det_data_50.tar && cd ../
+        wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar --no-check-certificate
+        cd ./inference && tar xf ${eval_model_name}.tar && tar xf ch_det_data_50.tar && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && cd ../
     elif [ ${model_name} = "ocr_server_det" ]; then
         wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar --no-check-certificate
         wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar  --no-check-certificate

test_tipc/test_paddle2onnx.sh

@@ -11,7 +11,7 @@ python=$(func_parser_value "${lines[2]}")
 
 
 # parser params
-dataline=$(awk 'NR==111, NR==123{print}'  $FILENAME)
+dataline=$(awk 'NR==1, NR==12{print}'  $FILENAME)
 IFS=$'\n'
 lines=(${dataline})
 

test_tipc/test_serving.sh

@@ -2,7 +2,7 @@
 source test_tipc/common_func.sh
 
 FILENAME=$1
-dataline=$(awk 'NR==67, NR==84{print}'  $FILENAME)
+dataline=$(awk 'NR==1, NR==18{print}'  $FILENAME)
 
 # parser params
 IFS=$'\n'

test_tipc/test_train_inference_python.sh

@@ -244,7 +244,7 @@ else
     export Count=0
     USE_GPU_KEY=(${train_use_gpu_value})
     for gpu in ${gpu_list[*]}; do
-        use_gpu=${USE_GPU_KEY[Count]}
+        train_use_gpu=${USE_GPU_KEY[Count]}
         Count=$(($Count + 1))
         ips=""
         if [ ${gpu} = "-1" ];then
@@ -302,11 +302,20 @@ else
                 set_pretrain=$(func_set_params "${pretrain_model_key}" "${pretrain_model_value}")
                 set_batchsize=$(func_set_params "${train_batch_key}" "${train_batch_value}")
                 set_train_params1=$(func_set_params "${train_param_key1}" "${train_param_value1}")
-                set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${use_gpu}")
+                set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${train_use_gpu}")
+                if [ ${#ips} -le 26 ];then
                     save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}"
+                    nodes=1
+                else
+                    IFS=","
+                    ips_array=(${ips})
+                    IFS="|"
+                    nodes=${#ips_array[@]}
+                    save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}_nodes_${nodes}"
+                fi
 
                 # load pretrain from norm training if current trainer is pact or fpgm trainer
-                if [ ${trainer} = ${pact_key} ] || [ ${trainer} = ${fpgm_key} ]; then
+                if ([ ${trainer} = ${pact_key} ] || [ ${trainer} = ${fpgm_key} ]) && [ ${nodes} -le 1 ]; then
                     set_pretrain="${load_norm_train_model}"
                 fi
 
@@ -325,7 +334,7 @@ else
 
                 set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/${train_model_name}")
                 # save norm trained models to set pretrain for pact training and fpgm training 
-                if [ ${trainer} = ${trainer_norm} ]; then
+                if [ ${trainer} = ${trainer_norm} ] && [ ${nodes} -le 1]; then
                     load_norm_train_model=${set_eval_pretrain}
                 fi
                 # run eval 

tools/infer/utility.py

@@ -205,7 +205,7 @@ def create_predictor(args, mode, logger):
                     "nearest_interp_v2_0.tmp_0": [1, 256, 2, 2]
                 }
                 max_input_shape = {
-                    "x": [1, 3, 2000, 2000],
+                    "x": [1, 3, 1280, 1280],
                     "conv2d_92.tmp_0": [1, 120, 400, 400],
                     "conv2d_91.tmp_0": [1, 24, 200, 200],
                     "conv2d_59.tmp_0": [1, 96, 400, 400],
@@ -255,16 +255,16 @@ def create_predictor(args, mode, logger):
                 opt_input_shape.update(opt_pact_shape)
             elif mode == "rec":
                 min_input_shape = {"x": [1, 3, 32, 10]}
-                max_input_shape = {"x": [args.rec_batch_num, 3, 32, 2000]}
+                max_input_shape = {"x": [args.rec_batch_num, 3, 32, 1024]}
                 opt_input_shape = {"x": [args.rec_batch_num, 3, 32, 320]}
             elif mode == "cls":
                 min_input_shape = {"x": [1, 3, 48, 10]}
-                max_input_shape = {"x": [args.rec_batch_num, 3, 48, 2000]}
+                max_input_shape = {"x": [args.rec_batch_num, 3, 48, 1024]}
                 opt_input_shape = {"x": [args.rec_batch_num, 3, 48, 320]}
             else:
                 min_input_shape = {"x": [1, 3, 10, 10]}
-                max_input_shape = {"x": [1, 3, 1000, 1000]}
-                opt_input_shape = {"x": [1, 3, 500, 500]}
+                max_input_shape = {"x": [1, 3, 512, 512]}
+                opt_input_shape = {"x": [1, 3, 256, 256]}
             config.set_trt_dynamic_shape_info(min_input_shape, max_input_shape,
                                               opt_input_shape)