diff --git a/ppocr/data/rec/img_tools.py b/ppocr/data/rec/img_tools.py index e8ac4622f6dc4b2933230d98558b8ee3d6a114c6..9c4bfa4d3cf0d86b8c70cb95f425970bb1d67da7 100755 --- a/ppocr/data/rec/img_tools.py +++ b/ppocr/data/rec/img_tools.py @@ -97,10 +97,11 @@ def process_image(img, max_text_length=None, tps=None, infer_mode=False): - if not infer_mode or char_ops.character_type == "en" or tps != None: - norm_img = resize_norm_img(img, image_shape) - else: + if infer_mode and char_ops.character_type == "ch" and not tps: norm_img = resize_norm_img_chinese(img, image_shape) + else: + norm_img = resize_norm_img(img, image_shape) + norm_img = norm_img[np.newaxis, :] if label is not None: # char_num = char_ops.get_char_num() @@ -109,7 +110,8 @@ def process_image(img, logger.info( "Warning in ppocr/data/rec/img_tools.py:line106: Wrong data type." "Excepted string with length between 1 and {}, but " - "got '{}'. Label is '{}'".format(max_text_length, len(text),label)) + "got '{}'. Label is '{}'".format(max_text_length, + len(text), label)) return None else: if loss_type == "ctc": diff --git a/tools/infer/predict_rec.py b/tools/infer/predict_rec.py index 41e556bd15cbad16586e9e2ea5f39aa5b096cc81..cc580a69f741ae436fcc65f546083d311947b12c 100755 --- a/tools/infer/predict_rec.py +++ b/tools/infer/predict_rec.py @@ -53,7 +53,7 @@ class TextRecognizer(object): imgC, imgH, imgW = self.rec_image_shape assert imgC == img.shape[2] if self.character_type == "ch": - imgW = int(math.ceil(32 * max_wh_ratio)) + imgW = int((32 * max_wh_ratio)) h, w = img.shape[:2] ratio = w / float(h) if math.ceil(imgH * ratio) > imgW: