fix max_wh_ratio for predict

tools/infer/predict_rec.py

@@ -60,12 +60,12 @@ class TextRecognizer(object):
             self.loss_type = 'srn'
         self.char_ops = CharacterOps(char_ops_params)
 
-    def resize_norm_img(self, img, wh_ratio):
+    def resize_norm_img(self, img, max_wh_ratio):
         imgC, imgH, imgW = self.rec_image_shape
         assert imgC == img.shape[2]
-        max_wh_ration = max(wh_ratio, imgW * 1.0 / imgH)
+        wh_ratio = max(max_wh_ratio, imgW * 1.0 / imgH)
         if self.character_type == "ch":
-            imgW = int((32 * max_wh_ratio))
+            imgW = int((32 * wh_ratio))
         h, w = img.shape[:2]
         ratio = w / float(h)
         if math.ceil(imgH * ratio) > imgW:
@@ -174,14 +174,16 @@ class TextRecognizer(object):
         for beg_img_no in range(0, img_num, batch_num):
             end_img_no = min(img_num, beg_img_no + batch_num)
             norm_img_batch = []
+            max_wh_ratio = 0
             for ino in range(beg_img_no, end_img_no):
                 # h, w = img_list[ino].shape[0:2]
                 h, w = img_list[indices[ino]].shape[0:2]
                 wh_ratio = w * 1.0 / h
+                max_wh_ratio = max(max_wh_ratio, wh_ratio)
             for ino in range(beg_img_no, end_img_no):
                 if self.loss_type != "srn":
                     norm_img = self.resize_norm_img(img_list[indices[ino]],
-                                                    wh_ratio)
+                                                    max_wh_ratio)
                     norm_img = norm_img[np.newaxis, :]
                     norm_img_batch.append(norm_img)
                 else: