Merge pull request #3833 from opendatalab/master

master->dev

mineru/model/utils/pytorchocr/modeling/backbones/rec_lcnetv3.py

@@ -256,7 +256,7 @@ class LearnableRepLayer(nn.Module):
                 input_dim = self.in_channels // self.groups
                 kernel_value = torch.zeros(
                     (self.in_channels, input_dim, self.kernel_size, self.kernel_size),
-                    dtype=branch.weight.dtype,  device=branch.weight.device,
+                    dtype=branch.weight.dtype, device=branch.weight.device,
                 )
                 for i in range(self.in_channels):
                     kernel_value[

mineru/model/utils/tools/infer/predict_rec.py

@@ -137,7 +137,7 @@ class TextRecognizer(BaseOCRV20):
         h, w = img.shape[:2]
         ratio = w / float(h)
         ratio_imgH = max(math.ceil(imgH * ratio), self.limited_min_width)
-        resized_w = min(imgW,int(ratio_imgH))
+        resized_w = min(imgW, int(ratio_imgH))
         resized_image = cv2.resize(img, (resized_w, imgH)) /127.5 - 1
         padding_im = np.zeros((imgC, imgH, imgW), dtype=np.float32)
         padding_im[:, :, 0:resized_w] = resized_image.transpose((2, 0, 1))

mineru/version.py

@@ -1 +1 @@
-__version__ = "2.5.4"
+__version__ = "2.6.1"