Merge pull request #2633 from littletomatodonkey/dyg/cp_add_save_rec

add save rec res

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/hubserving/ocr_cls/module.py

@@ -16,6 +16,7 @@ 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(
@@ -55,7 +56,6 @@ class OCRCls(hub.Module):
         sys.argv = sys.argv[:1]
         cfg = parse_args()
 
-        from ocr_det.params import read_params
         update_cfg_map = vars(read_params())
 
         for key in update_cfg_map:

tools/infer_rec.py

@@ -73,35 +73,45 @@ def main():
     global_config['infer_mode'] = True
     ops = create_operators(transforms, global_config)
 
+    save_res_path = config['Global'].get('save_res_path',
+                                         "./output/rec/predicts_rec.txt")
+    if not os.path.exists(os.path.dirname(save_res_path)):
+        os.makedirs(os.path.dirname(save_res_path))
+
     model.eval()
-    for file in get_image_file_list(config['Global']['infer_img']):
-        logger.info("infer_img: {}".format(file))
-        with open(file, 'rb') as f:
-            img = f.read()
-            data = {'image': img}
-        batch = transform(data, ops)
-        if config['Architecture']['algorithm'] == "SRN":
-            encoder_word_pos_list = np.expand_dims(batch[1], axis=0)
-            gsrm_word_pos_list = np.expand_dims(batch[2], axis=0)
-            gsrm_slf_attn_bias1_list = np.expand_dims(batch[3], axis=0)
-            gsrm_slf_attn_bias2_list = np.expand_dims(batch[4], axis=0)
-
-            others = [
-                paddle.to_tensor(encoder_word_pos_list),
-                paddle.to_tensor(gsrm_word_pos_list),
-                paddle.to_tensor(gsrm_slf_attn_bias1_list),
-                paddle.to_tensor(gsrm_slf_attn_bias2_list)
-            ]
-
-        images = np.expand_dims(batch[0], axis=0)
-        images = paddle.to_tensor(images)
-        if config['Architecture']['algorithm'] == "SRN":
-            preds = model(images, others)
-        else:
-            preds = model(images)
-        post_result = post_process_class(preds)
-        for rec_reuslt in post_result:
-            logger.info('\t result: {}'.format(rec_reuslt))
+
+    with open(save_res_path, "w") as fout:
+        for file in get_image_file_list(config['Global']['infer_img']):
+            logger.info("infer_img: {}".format(file))
+            with open(file, 'rb') as f:
+                img = f.read()
+                data = {'image': img}
+            batch = transform(data, ops)
+            if config['Architecture']['algorithm'] == "SRN":
+                encoder_word_pos_list = np.expand_dims(batch[1], axis=0)
+                gsrm_word_pos_list = np.expand_dims(batch[2], axis=0)
+                gsrm_slf_attn_bias1_list = np.expand_dims(batch[3], axis=0)
+                gsrm_slf_attn_bias2_list = np.expand_dims(batch[4], axis=0)
+
+                others = [
+                    paddle.to_tensor(encoder_word_pos_list),
+                    paddle.to_tensor(gsrm_word_pos_list),
+                    paddle.to_tensor(gsrm_slf_attn_bias1_list),
+                    paddle.to_tensor(gsrm_slf_attn_bias2_list)
+                ]
+
+            images = np.expand_dims(batch[0], axis=0)
+            images = paddle.to_tensor(images)
+            if config['Architecture']['algorithm'] == "SRN":
+                preds = model(images, others)
+            else:
+                preds = model(images)
+            post_result = post_process_class(preds)
+            for rec_reuslt in post_result:
+                logger.info('\t result: {}'.format(rec_reuslt))
+                if len(rec_reuslt) >= 2:
+                    fout.write(file + "\t" + rec_reuslt[0] + "\t" + str(
+                        rec_reuslt[1]) + "\n")
     logger.info("success!")