modified default shape

tools/infer/predict_rec.py

@@ -296,8 +296,8 @@ class TextRecognizer(object):
                     gsrm_slf_attn_bias2_list.append(norm_img[4])
                     norm_img_batch.append(norm_img[0])
                 elif self.rec_algorithm == "SVTR":
-                    norm_img = self.resize_norm_img_svtr(
-                        img_list[indices[ino]], self.rec_image_shape)
+                    norm_img = self.resize_norm_img_svtr(img_list[indices[ino]],
+                                                         self.rec_image_shape)
                     norm_img = norm_img[np.newaxis, :]
                     norm_img_batch.append(norm_img)
                 else:
@@ -405,9 +405,13 @@ def main(args):
     valid_image_file_list = []
     img_list = []
 
+    logger.info(
+        "In PP-OCRv3, rec_image_shape parameter defaults to '3, 48, 320', "
+        "if you are using an older PP-OCR, please set --rec_image_shape='3,32,320'"
+    )
     # warmup 2 times
     if args.warmup:
-        img = np.random.uniform(0, 255, [32, 320, 3]).astype(np.uint8)
+        img = np.random.uniform(0, 255, [48, 320, 3]).astype(np.uint8)
         for i in range(2):
             res = text_recognizer([img] * int(args.rec_batch_num))
 

tools/infer/predict_system.py

@@ -59,7 +59,7 @@ class TextSystem(object):
         for bno in range(bbox_num):
             cv2.imwrite(
                 os.path.join(output_dir,
-                             f"mg_crop_{bno+self.crop_image_res_index}.jpg"),
+                             f"mg_crop_{bno+self.crop_image_res_index}.jpg "),
                 img_crop_list[bno])
             logger.debug(f"{bno}, {rec_res[bno]}")
         self.crop_image_res_index += bbox_num
@@ -133,6 +133,9 @@ def main(args):
     os.makedirs(draw_img_save_dir, exist_ok=True)
     save_results = []
 
+    logger.info("In PP-OCRv3, rec_image_shape parameter defaults to '3, 48, 320', "
+                "if you are using an older PP-OCR, please set --rec_image_shape='3,32,320'")
+                
     # warm up 10 times
     if args.warmup:
         img = np.random.uniform(0, 255, [640, 640, 3]).astype(np.uint8)

tools/infer/utility.py

@@ -81,7 +81,7 @@ def init_args():
     # params for text recognizer
     parser.add_argument("--rec_algorithm", type=str, default='CRNN')
     parser.add_argument("--rec_model_dir", type=str)
-    parser.add_argument("--rec_image_shape", type=str, default="3, 32, 320")
+    parser.add_argument("--rec_image_shape", type=str, default="3, 48, 320")
     parser.add_argument("--rec_batch_num", type=int, default=6)
     parser.add_argument("--max_text_length", type=int, default=25)
     parser.add_argument(