Merge branch 'dygraph' into dygraph

configs/e2e/e2e_r50_vd_pg.yml

@@ -60,8 +60,10 @@ PostProcess:
   name: PGPostProcess
   score_thresh: 0.5
   mode: fast   # fast or slow two ways
+
 Metric:
   name: E2EMetric
+  mode: A   # two ways for eval, A: label from txt,  B: label from gt_mat
   gt_mat_dir:  ./train_data/total_text/gt  # the dir of gt_mat
   character_dict_path: ppocr/utils/ic15_dict.txt
   main_indicator: f_score_e2e
@@ -70,13 +72,13 @@ Train:
   dataset:
     name: PGDataSet
     data_dir: ./train_data/total_text/train
-    label_file_list: [./train_data/total_text/train/]
+    label_file_list: [./train_data/total_text/train/train.txt]
     ratio_list: [1.0]
     transforms:
       - DecodeImage: # load image
           img_mode: BGR
           channel_first: False
-      - E2ELabelEncode:
+      - E2ELabelEncodeTrain:
       - PGProcessTrain:
           batch_size: 14  # same as loader: batch_size_per_card
           min_crop_size: 24
@@ -94,11 +96,12 @@ Eval:
   dataset:
     name: PGDataSet
     data_dir: ./train_data/total_text/test
-    label_file_list: [./train_data/total_text/test/]
+    label_file_list: [./train_data/total_text/test/test.txt]
     transforms:
       - DecodeImage: # load image
           img_mode: RGB
           channel_first: False
+      - E2ELabelEncodeTest:
       - E2EResizeForTest:
           max_side_len: 768
       - NormalizeImage:
@@ -108,7 +111,7 @@ Eval:
           order: 'hwc'
       - ToCHWImage:
       - KeepKeys:
-          keep_keys: [ 'image', 'shape', 'img_id']
+          keep_keys: [ 'image', 'shape', 'polys', 'texts', 'ignore_tags', 'img_id']
   loader:
     shuffle: False
     drop_last: False

configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: True
+  save_res_path: ./output/rec/predicts_chinese_common_v2.0.txt
 
 
 Optimizer:

configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: True
+  save_res_path: ./output/rec/predicts_chinese_lite_v2.0.txt
 
 
 Optimizer:

configs/rec/rec_icdar15_train.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_ic15.txt
 
 Optimizer:
   name: Adam

configs/rec/rec_mv3_none_bilstm_ctc.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_mv3_none_bilstm_ctc.txt
 
 Optimizer:
   name: Adam

configs/rec/rec_mv3_none_none_ctc.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_mv3_none_none_ctc.txt
 
 Optimizer:
   name: Adam

configs/rec/rec_mv3_tps_bilstm_att.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_mv3_tps_bilstm_att.txt
 
 
 Optimizer:

configs/rec/rec_mv3_tps_bilstm_ctc.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_mv3_tps_bilstm_ctc.txt
 
 Optimizer:
   name: Adam

configs/rec/rec_r34_vd_none_bilstm_ctc.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_r34_vd_none_bilstm_ctc.txt
 
 Optimizer:
   name: Adam

configs/rec/rec_r34_vd_none_none_ctc.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_r34_vd_none_none_ctc.txt
 
 Optimizer:
   name: Adam

configs/rec/rec_r34_vd_tps_bilstm_att.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_b3_rare_r34_none_gru.txt
 
 
 Optimizer:

configs/rec/rec_r34_vd_tps_bilstm_ctc.yml

@@ -19,6 +19,7 @@ Global:
   max_text_length: 25
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_r34_vd_tps_bilstm_ctc.txt
 
 Optimizer:
   name: Adam

configs/rec/rec_r50_fpn_srn.yml

@@ -20,6 +20,7 @@ Global:
   num_heads: 8
   infer_mode: False
   use_space_char: False
+  save_res_path: ./output/rec/predicts_srn.txt
 
 
 Optimizer:

deploy/cpp_infer/include/postprocess_op.h

@@ -51,6 +51,7 @@ public:
                                                float &ssid);
 
   float BoxScoreFast(std::vector<std::vector<float>> box_array, cv::Mat pred);
+  float PolygonScoreAcc(std::vector<cv::Point> contour, cv::Mat pred);
 
   std::vector<std::vector<std::vector<int>>>
   BoxesFromBitmap(const cv::Mat pred, const cv::Mat bitmap,

deploy/cpp_infer/src/postprocess_op.cpp

@@ -159,6 +159,39 @@ std::vector<std::vector<float>> PostProcessor::GetMiniBoxes(cv::RotatedRect box,
   return array;
 }
 
+float PostProcessor::PolygonScoreAcc(std::vector<cv::Point> contour,
+		                  cv::Mat pred){
+  int width = pred.cols;
+  int height = pred.rows;
+  std::vector<float> box_x;
+  std::vector<float> box_y;
+  for(int i=0; i<contour.size(); ++i){
+    box_x.push_back(contour[i].x);
+    box_y.push_back(contour[i].y);
+  }
+
+  int xmin = clamp(int(std::floor(*(std::min_element(box_x.begin(), box_x.end())))), 0, width - 1);
+  int xmax = clamp(int(std::ceil(*(std::max_element(box_x.begin(), box_x.end())))), 0, width - 1);
+  int ymin = clamp(int(std::floor(*(std::min_element(box_y.begin(), box_y.end())))), 0, height - 1);
+  int ymax = clamp(int(std::ceil(*(std::max_element(box_y.begin(), box_y.end())))), 0, height - 1);
+
+  cv::Mat mask;
+  mask = cv::Mat::zeros(ymax - ymin + 1, xmax - xmin + 1, CV_8UC1);
+
+  cv::Point rook_point[contour.size()];
+  for(int i=0; i<contour.size(); ++i){
+    rook_point[i] = cv::Point(int(box_x[i]) - xmin, int(box_y[i]) - ymin);
+  }
+  const cv::Point *ppt[1] = {rook_point};
+  int npt[] = {int(contour.size())};
+  cv::fillPoly(mask, ppt, npt, 1, cv::Scalar(1));
+
+  cv::Mat croppedImg;
+  pred(cv::Rect(xmin, ymin, xmax - xmin + 1, ymax - ymin + 1)).copyTo(croppedImg);
+  float score = cv::mean(croppedImg, mask)[0];
+  return score;
+}
+
 float PostProcessor::BoxScoreFast(std::vector<std::vector<float>> box_array,
                                   cv::Mat pred) {
   auto array = box_array;
@@ -235,6 +268,8 @@ PostProcessor::BoxesFromBitmap(const cv::Mat pred, const cv::Mat bitmap,
 
     float score;
     score = BoxScoreFast(array, pred);
+    /* compute using polygon*/ 
+    // score = PolygonScoreAcc(contours[_i], pred);
     if (score < box_thresh)
       continue;
 

deploy/cpp_infer/src/preprocess_op.cpp

@@ -77,19 +77,10 @@ void ResizeImgType0::Run(const cv::Mat &img, cv::Mat &resize_img,
 
   int resize_h = int(float(h) * ratio);
   int resize_w = int(float(w) * ratio);
-  if (resize_h % 32 == 0)
-    resize_h = resize_h;
-  else if (resize_h / 32 < 1 + 1e-5)
-    resize_h = 32;
-  else
-    resize_h = (resize_h / 32) * 32;
   
-  if (resize_w % 32 == 0)
-    resize_w = resize_w;
-  else if (resize_w / 32 < 1 + 1e-5)
-    resize_w = 32;
-  else
-    resize_w = (resize_w / 32) * 32;
+  resize_h = max(int(round(float(resize_h) / 32) * 32), 32);
+  resize_w = max(int(round(float(resize_w) / 32) * 32), 32);
+
   if (!use_tensorrt) {
     cv::resize(img, resize_img, cv::Size(resize_w, resize_h));
     ratio_h = float(resize_h) / float(h);

deploy/hubserving/ocr_cls/module.py

@@ -6,6 +6,7 @@ from __future__ import print_function
 import os
 import sys
 sys.path.insert(0, ".")
+import copy
 
 from paddlehub.common.logger import logger
 from paddlehub.module.module import moduleinfo, runnable, serving
@@ -14,6 +15,8 @@ import paddlehub as hub
 
 from tools.infer.utility import base64_to_cv2
 from tools.infer.predict_cls import TextClassifier
+from tools.infer.utility import parse_args
+from deploy.hubserving.ocr_cls.params import read_params
 
 
 @moduleinfo(
@@ -28,8 +31,7 @@ class OCRCls(hub.Module):
         """
         initialize with the necessary elements
         """
-        from ocr_cls.params import read_params
-        cfg = read_params()
+        cfg = self.merge_configs()
 
         cfg.use_gpu = use_gpu
         if use_gpu:
@@ -48,6 +50,20 @@ class OCRCls(hub.Module):
 
         self.text_classifier = TextClassifier(cfg)
 
+    def merge_configs(self, ):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
     def read_images(self, paths=[]):
         images = []
         for img_path in paths:

deploy/hubserving/ocr_det/module.py

@@ -7,6 +7,8 @@ import os
 import sys
 sys.path.insert(0, ".")
 
+import copy
+
 from paddlehub.common.logger import logger
 from paddlehub.module.module import moduleinfo, runnable, serving
 import cv2
@@ -15,6 +17,8 @@ import paddlehub as hub
 
 from tools.infer.utility import base64_to_cv2
 from tools.infer.predict_det import TextDetector
+from tools.infer.utility import parse_args
+from deploy.hubserving.ocr_system.params import read_params
 
 
 @moduleinfo(
@@ -29,8 +33,7 @@ class OCRDet(hub.Module):
         """
         initialize with the necessary elements
         """
-        from ocr_det.params import read_params
-        cfg = read_params()
+        cfg = self.merge_configs()
 
         cfg.use_gpu = use_gpu
         if use_gpu:
@@ -49,6 +52,20 @@ class OCRDet(hub.Module):
 
         self.text_detector = TextDetector(cfg)
 
+    def merge_configs(self, ):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
     def read_images(self, paths=[]):
         images = []
         for img_path in paths:

deploy/hubserving/ocr_det/params.py

@@ -22,6 +22,7 @@ def read_params():
     cfg.det_db_box_thresh = 0.5
     cfg.det_db_unclip_ratio = 1.6
     cfg.use_dilation = False
+    cfg.det_db_score_mode = "fast"
 
     # #EAST parmas
     # cfg.det_east_score_thresh = 0.8

deploy/hubserving/ocr_rec/module.py

@@ -6,6 +6,7 @@ from __future__ import print_function
 import os
 import sys
 sys.path.insert(0, ".")
+import copy
 
 from paddlehub.common.logger import logger
 from paddlehub.module.module import moduleinfo, runnable, serving
@@ -14,6 +15,8 @@ import paddlehub as hub
 
 from tools.infer.utility import base64_to_cv2
 from tools.infer.predict_rec import TextRecognizer
+from tools.infer.utility import parse_args
+from deploy.hubserving.ocr_rec.params import read_params
 
 
 @moduleinfo(
@@ -28,8 +31,7 @@ class OCRRec(hub.Module):
         """
         initialize with the necessary elements
         """
-        from ocr_rec.params import read_params
-        cfg = read_params()
+        cfg = self.merge_configs()
 
         cfg.use_gpu = use_gpu
         if use_gpu:
@@ -48,6 +50,20 @@ class OCRRec(hub.Module):
 
         self.text_recognizer = TextRecognizer(cfg)
 
+    def merge_configs(self, ):
+        # deafult cfg
+        backup_argv = copy.deepcopy(sys.argv)
+        sys.argv = sys.argv[:1]
+        cfg = parse_args()
+
+        update_cfg_map = vars(read_params())
+
+        for key in update_cfg_map:
+            cfg.__setattr__(key, update_cfg_map[key])
+
+        sys.argv = copy.deepcopy(backup_argv)
+        return cfg
+
     def read_images(self, paths=[]):
         images = []
         for img_path in paths: