merge dygraph

tests/configs/rec_icdar15_r34_train.yml

+Global:
+  use_gpu: true
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/ic15/
+  save_epoch_step: 3
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints:
+  save_inference_dir: ./
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path: ppocr/utils/en_dict.txt
+  character_type: EN
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_ic15.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: ResNet
+    layers: 34
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 256
+  Head:
+    name: CTCHead
+    fc_decay: 0
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data/
+    label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+    use_shared_memory: False
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data
+    label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 4
+    use_shared_memory: False

tests/ocr_det_params.txt

@@ -12,7 +12,7 @@ train_model_name:latest
 train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
 null:null
 ##
-trainer:norm_train|pact_train
+trainer:norm_train|pact_train|fpgm_train
 norm_train:tools/train.py -c tests/configs/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
 pact_train:deploy/slim/quantization/quant.py -c tests/configs/det_mv3_db.yml -o
 fpgm_train:deploy/slim/prune/sensitivity_anal.py -c tests/configs/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/det_mv3_db_v2.0_train/best_accuracy
@@ -21,7 +21,7 @@ null:null
 null:null
 ##
 ===========================eval_params=========================== 
-eval:tools/eval.py -c tests/configs/det_mv3_db.yml -o
+eval:null
 null:null
 ##
 ===========================infer_params===========================
@@ -35,7 +35,7 @@ export1:null
 export2:null
 ##
 train_model:./inference/ch_ppocr_mobile_v2.0_det_train/best_accuracy
-infer_export:tools/export_model.py -c configs/det/det_mv3_db.yml -o
+infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o
 infer_quant:False
 inference:tools/infer/predict_det.py
 --use_gpu:True|False

tests/ocr_kl_quant_params.txt

+===========================train_params===========================
+model_name:ocr_system
+python:python3.7
+gpu_list:null
+Global.use_gpu:null
+Global.auto_cast:null
+Global.epoch_num:null
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:null
+Global.pretrained_model:null
+train_model_name:null
+train_infer_img_dir:null
+null:null
+##
+trainer:
+norm_train:null
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.pretrained_model:
+norm_export:null 
+quant_export:null 
+fpgm_export:null 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/ch_ppocr_mobile_v2.0_det_infer/
+kl_quant:deploy/slim/quantization/quant_kl.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml  -o  
+infer_quant:True
+inference:tools/infer/predict_det.py
+--use_gpu:TrueFalse
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32|fp16|int8
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--save_log_path:null
+--benchmark:True
+null:null

tests/ocr_ppocr_mobile_params.txt

 ===========================train_params===========================
-model_name:ocr_system
+model_name:ocr_system_mobile
 python:python3.7
 gpu_list:null
 Global.use_gpu:null

tests/ocr_ppocr_server_params.txt

+===========================train_params===========================
+model_name:ocr_system_server
+python:python3.7
+gpu_list:null
+Global.use_gpu:null
+Global.auto_cast:null
+Global.epoch_num:null
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:null
+Global.pretrained_model:null
+train_model_name:null
+train_infer_img_dir:null
+null:null
+##
+trainer:
+norm_train:null
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.pretrained_model:
+norm_export:null
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/ch_ppocr_server_v2.0_det_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_system.py
+--use_gpu:True
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32|fp16|int8
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--save_log_path:null
+--benchmark:True
+--rec_model_dir:./inference/ch_ppocr_server_v2.0_rec_infer/
+===========================cpp_infer_params===========================
+use_opencv:True
+infer_model:./inference/ch_ppocr_server_v2.0_det_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr system
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32|fp16
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--rec_model_dir:./inference/ch_ppocr_server_v2.0_rec_infer/
+--benchmark:True
\ No newline at end of file

tests/ocr_rec_params.txt

@@ -63,4 +63,19 @@ inference:./deploy/cpp_infer/build/ppocr rec
 --rec_model_dir:
 --image_dir:./inference/rec_inference/
 null:null
---benchmark:True
\ No newline at end of file
+--benchmark:True
+===========================serving_params===========================
+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_http_client.py --image_dir=../../doc/imgs_words_en
\ No newline at end of file

tests/ocr_rec_server_params.txt

+===========================train_params===========================
+model_name:ocr_server_rec
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:null
+Global.epoch_num:lite_train_infer=2|whole_train_infer=300
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_infer=128|whole_train_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train|pact_train
+norm_train:tools/train.py -c tests/configs/rec_icdar15_r34_train.yml -o
+pact_train:deploy/slim/quantization/quant.py -c tests/configs/rec_icdar15_r34_train.yml -o
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:tools/eval.py -c tests/configs/rec_icdar15_r34_train.yml -o
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.pretrained_model:
+norm_export:tools/export_model.py -c tests/configs/rec_icdar15_r34_train.yml -o
+quant_export:deploy/slim/quantization/export_model.py -c tests/configs/rec_icdar15_r34_train.yml -o
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:./inference/ch_ppocr_server_v2.0_rec_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1|6
+--use_tensorrt:True|False
+--precision:fp32|fp16|int8
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+--save_log_path:./test/output/
+--benchmark:True
+null:null
+===========================cpp_infer_params===========================
+use_opencv:True
+infer_model:./inference/ch_ppocr_server_v2.0_rec_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr rec
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32|fp16
+--rec_model_dir:
+--image_dir:./inference/rec_inference/
+null:null
+--benchmark:True
+===========================serving_params===========================
+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_http_client.py --image_dir=../../doc/imgs_words_en
\ No newline at end of file

tests/prepare.sh

@@ -75,17 +75,28 @@ elif [ ${MODE} = "infer" ];then
         wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar
         wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
         cd ./inference && tar xf ch_ppocr_server_v2.0_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
-    elif  [ ${model_name} = "ocr_system" ]; then
+    elif  [ ${model_name} = "ocr_system_mobile" ]; then
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar
         wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar
         cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf ch_det_data_50.tar && cd ../
-    else 
+    elif  [ ${model_name} = "ocr_system_server" ]; then
+        wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar
+        wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
+        wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar
+        cd ./inference && tar xf ch_ppocr_server_v2.0_det_infer.tar && tar xf ch_ppocr_server_v2.0_rec_infer.tar && tar xf ch_det_data_50.tar && cd ../
+    elif [ ${model_name} = "ocr_rec" ]; then
         rm -rf ./train_data/ic15_data
         eval_model_name="ch_ppocr_mobile_v2.0_rec_infer"
         wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar
         wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar
         cd ./inference && tar xf ${eval_model_name}.tar && tar xf rec_inference.tar && cd ../
+    elif [ ${model_name} = "ocr_server_rec" ]; then
+        rm -rf ./train_data/ic15_data
+        eval_model_name="ch_ppocr_server_v2.0_rec_infer"
+        wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar
+        wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar
+        cd ./inference && tar xf ${eval_model_name}.tar && tar xf rec_inference.tar && cd ../
     fi 
 elif [ ${MODE} = "cpp_infer" ];then
     if [ ${model_name} = "ocr_det" ]; then
@@ -107,12 +118,15 @@ fi
 if [ ${MODE} = "serving_infer" ];then
     # prepare serving env
     python_name=$(func_parser_value "${lines[2]}")
-    ${python_name} -m pip install install paddle-serving-server-gpu==0.6.1.post101
+    wget https://paddle-serving.bj.bcebos.com/chain/paddle_serving_server_gpu-0.0.0.post101-py3-none-any.whl
+    ${python_name} -m pip install install paddle_serving_server_gpu-0.0.0.post101-py3-none-any.whl
     ${python_name} -m pip install paddle_serving_client==0.6.1
-    ${python_name} -m pip install paddle-serving-app==0.6.1
+    ${python_name} -m pip install paddle-serving-app==0.6.3
     wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar
     wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar
-    cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && cd ../
+    wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar
+    wget -nc  -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar
+    cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf ch_ppocr_server_v2.0_rec_infer.tar && tar xf ch_ppocr_server_v2.0_det_infer.tar cd ../
 fi
 
 if [ ${MODE} = "cpp_infer" ];then

tests/readme.md

 
-# 介绍
+# 从训练到推理部署工具链测试方法介绍
 
 test.sh和params.txt文件配合使用，完成OCR轻量检测和识别模型从训练到预测的流程测试。
 
@@ -36,7 +36,7 @@ test.sh包含四种运行模式，每种模式的运行数据不同，分别用
 
 - 模式1：lite_train_infer，使用少量数据训练，用于快速验证训练到预测的走通流程，不验证精度和速度；
 ```shell
-bash test/prepare.sh ./tests/ocr_det_params.txt 'lite_train_infer'
+bash tests/prepare.sh ./tests/ocr_det_params.txt 'lite_train_infer'
 bash tests/test.sh ./tests/ocr_det_params.txt 'lite_train_infer'
 ```  
 
@@ -66,3 +66,7 @@ bash tests/test.sh ./tests/ocr_det_params.txt 'whole_train_infer'
 bash tests/prepare.sh ./tests/ocr_det_params.txt 'cpp_infer'
 bash tests/test.sh ./tests/ocr_det_params.txt 'cpp_infer'
 ```  
+
+# 日志输出
+最终在```tests/output```目录下生成.log后缀的日志文件
+

tests/test.sh

@@ -321,7 +321,7 @@ function func_serving(){
                     if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then
                         continue
                     fi
-                    if [[ ${use_trt} = "Falg_quantse" || ${precision} =~ "int8" ]]; then
+                    if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [[ ${_flag_quant} = "True" ]]; then
                         continue
                     fi
                     _save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_1.log"
@@ -433,7 +433,9 @@ if [ ${MODE} = "infer" ]; then
             save_infer_dir=$(dirname $infer_model)
             set_export_weight=$(func_set_params "${export_weight}" "${infer_model}")
             set_save_infer_key=$(func_set_params "${save_infer_key}" "${save_infer_dir}")
-            export_cmd="${python} ${norm_export} ${set_export_weight} ${set_save_infer_key}"
+            export_cmd="${python} ${infer_run_exports[Count]} ${set_export_weight} ${set_save_infer_key}"
+            echo ${infer_run_exports[Count]} 
+            echo  $export_cmd
             eval $export_cmd
             status_export=$?
             status_check $status_export "${export_cmd}" "${status_log}"

tools/export_model.py

@@ -60,6 +60,8 @@ def export_single_model(model, arch_config, save_path, logger):
                     "When there is tps in the network, variable length input is not supported, and the input size needs to be the same as during training"
                 )
                 infer_shape[-1] = 100
+            if arch_config["algorithm"] == "NRTR":
+                infer_shape = [1, 32, 100]
         elif arch_config["model_type"] == "table":
             infer_shape = [3, 488, 488]
         model = to_static(

tools/infer/predict_det.py

@@ -89,6 +89,14 @@ class TextDetector(object):
                 postprocess_params["sample_pts_num"] = 2
                 postprocess_params["expand_scale"] = 1.0
                 postprocess_params["shrink_ratio_of_width"] = 0.3
+        elif self.det_algorithm == "PSE":
+            postprocess_params['name'] = 'PSEPostProcess'
+            postprocess_params["thresh"] = args.det_pse_thresh
+            postprocess_params["box_thresh"] = args.det_pse_box_thresh
+            postprocess_params["min_area"] = args.det_pse_min_area
+            postprocess_params["box_type"] = args.det_pse_box_type
+            postprocess_params["scale"] = args.det_pse_scale
+            self.det_pse_box_type = args.det_pse_box_type
         else:
             logger.info("unknown det_algorithm:{}".format(self.det_algorithm))
             sys.exit(0)
@@ -209,7 +217,7 @@ class TextDetector(object):
             preds['f_score'] = outputs[1]
             preds['f_tco'] = outputs[2]
             preds['f_tvo'] = outputs[3]
-        elif self.det_algorithm == 'DB':
+        elif self.det_algorithm in ['DB', 'PSE']:
             preds['maps'] = outputs[0]
         else:
             raise NotImplementedError
@@ -217,7 +225,9 @@ class TextDetector(object):
         #self.predictor.try_shrink_memory()
         post_result = self.postprocess_op(preds, shape_list)
         dt_boxes = post_result[0]['points']
-        if self.det_algorithm == "SAST" and self.det_sast_polygon:
+        if (self.det_algorithm == "SAST" and
+                self.det_sast_polygon) or (self.det_algorithm == "PSE" and
+                                           self.det_pse_box_type == 'poly'):
             dt_boxes = self.filter_tag_det_res_only_clip(dt_boxes, ori_im.shape)
         else:
             dt_boxes = self.filter_tag_det_res(dt_boxes, ori_im.shape)

tools/infer/predict_rec.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 import os
 import sys
-
+from PIL import Image
 __dir__ = os.path.dirname(os.path.abspath(__file__))
 sys.path.append(__dir__)
 sys.path.append(os.path.abspath(os.path.join(__dir__, '../..')))
@@ -61,6 +61,13 @@ class TextRecognizer(object):
                 "character_dict_path": args.rec_char_dict_path,
                 "use_space_char": args.use_space_char
             }
+        elif self.rec_algorithm == 'NRTR':
+            postprocess_params = {
+                'name': 'NRTRLabelDecode',
+                "character_type": args.rec_char_type,
+                "character_dict_path": args.rec_char_dict_path,
+                "use_space_char": args.use_space_char
+            }
         self.postprocess_op = build_post_process(postprocess_params)
         self.predictor, self.input_tensor, self.output_tensors, self.config = \
             utility.create_predictor(args, 'rec', logger)
@@ -87,6 +94,16 @@ class TextRecognizer(object):
 
     def resize_norm_img(self, img, max_wh_ratio):
         imgC, imgH, imgW = self.rec_image_shape
+        if self.rec_algorithm == 'NRTR':
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+            # return padding_im
+            image_pil = Image.fromarray(np.uint8(img))
+            img = image_pil.resize([100, 32], Image.ANTIALIAS)
+            img = np.array(img)
+            norm_img = np.expand_dims(img, -1)
+            norm_img = norm_img.transpose((2, 0, 1))
+            return norm_img.astype(np.float32) / 128. - 1.
+
         assert imgC == img.shape[2]
         max_wh_ratio = max(max_wh_ratio, imgW / imgH)
         imgW = int((32 * max_wh_ratio))
@@ -252,14 +269,16 @@ class TextRecognizer(object):
             else:
                 self.input_tensor.copy_from_cpu(norm_img_batch)
                 self.predictor.run()
-
                 outputs = []
                 for output_tensor in self.output_tensors:
                     output = output_tensor.copy_to_cpu()
                     outputs.append(output)
                 if self.benchmark:
                     self.autolog.times.stamp()
-                preds = outputs[0]
+                if len(outputs) != 1:
+                    preds = outputs
+                else:
+                    preds = outputs[0]
             rec_result = self.postprocess_op(preds)
             for rno in range(len(rec_result)):
                 rec_res[indices[beg_img_no + rno]] = rec_result[rno]

tools/infer/utility.py

@@ -63,6 +63,13 @@ def init_args():
     parser.add_argument("--det_sast_nms_thresh", type=float, default=0.2)
     parser.add_argument("--det_sast_polygon", type=str2bool, default=False)
 
+    # PSE parmas
+    parser.add_argument("--det_pse_thresh", type=float, default=0)
+    parser.add_argument("--det_pse_box_thresh", type=float, default=0.85)
+    parser.add_argument("--det_pse_min_area", type=float, default=16)
+    parser.add_argument("--det_pse_box_type", type=str, default='box')
+    parser.add_argument("--det_pse_scale", type=int, default=1)
+
     # params for text recognizer
     parser.add_argument("--rec_algorithm", type=str, default='CRNN')
     parser.add_argument("--rec_model_dir", type=str)

tools/program.py

@@ -353,7 +353,7 @@ def eval(model,
          valid_dataloader,
          post_process_class,
          eval_class,
-         model_type,
+         model_type=None,
          use_srn=False,
          use_sar=False):
     model.eval()
@@ -404,7 +404,8 @@ def preprocess(is_train=False):
     alg = config['Architecture']['algorithm']
     assert alg in [
         'EAST', 'DB', 'SAST', 'Rosetta', 'CRNN', 'STARNet', 'RARE', 'SRN',
-        'CLS', 'PGNet', 'Distillation', 'NRTR', 'TableAttn', 'SAR', 'ASTER'
+        'CLS', 'PGNet', 'Distillation', 'NRTR', 'TableAttn', 'SAR', 'PSE',
+        'ASTER'
     ]
 
     device = 'gpu:{}'.format(dist.ParallelEnv().dev_id) if use_gpu else 'cpu'