about input channels of vitstr
Name-Lessx opened this issue · 1 comments
I am reproducing the vit-tiny model but have a problem when testing on III5k.It prompts unmatched number of channels.Then i find the input images are RGB mode but the input channels of vitstr is just one.Why is this problem?I'm looking forward to your reply.
Thank you
RuntimeError Traceback (most recent call last)
/tmp/ipykernel_53850/3528011160.py in
296 opt.num_gpu = torch.cuda.device_count()
297
--> 298 test(opt)
/tmp/ipykernel_53850/3528011160.py in test(opt)
253 with torch.no_grad():
254
--> 255 _, accuracy_by_best_model, norm_ED_by_best_model, _, _, _, infer_time, length_of_data = validation(
256 model, criterion, test_loader, converter, opt)
257 print(f'{accuracy_by_best_model:0.3f}')
/tmp/ipykernel_53850/3528011160.py in validation(model, criterion, evaluation_loader, converter, opt)
39 start_time = time.time()
40
---> 41 preds = model(image, seqlen=converter.batch_max_length,is_train=False)
42 _, preds_index = preds.topk(1, dim=-1, largest=True, sorted=True)
43 forward_time = time.time() - start_time
~/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~/model.py in forward(self, input, is_train, seqlen)
44
45 """ Prediction stage """
---> 46 prediction = self.vitstr(input, seqlen=seqlen)
47
48 return prediction
~/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~/modules/Vistr.py in forward(self, x, seqlen)
73
74 def forward(self, x, seqlen: int =25):
---> 75 x = self.forward_features(x)
76 x = x[:, :seqlen]
77
~/modules/Vistr.py in forward_features(self, x)
59 def forward_features(self, x):
60 B = x.shape[0]
---> 61 x = self.patch_embed(x)
62
63 cls_tokens = self.cls_token.expand(B, -1, -1) # stole cls_tokens impl from Phil Wang, thanks
~/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~/miniconda3/lib/python3.8/site-packages/timm/models/layers/patch_embed.py in forward(self, x)
33 _assert(H == self.img_size[0], f"Input image height ({H}) doesn't match model ({self.img_size[0]}).")
34 _assert(W == self.img_size[1], f"Input image width ({W}) doesn't match model ({self.img_size[1]}).")
---> 35 x = self.proj(x)
36 if self.flatten:
37 x = x.flatten(2).transpose(1, 2) # BCHW -> BNC
~/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
725 result = self._slow_forward(*input, **kwargs)
726 else:
--> 727 result = self.forward(*input, **kwargs)
728 for hook in itertools.chain(
729 _global_forward_hooks.values(),
~/miniconda3/lib/python3.8/site-packages/torch/nn/modules/conv.py in forward(self, input)
421
422 def forward(self, input: Tensor) -> Tensor:
--> 423 return self._conv_forward(input, self.weight)
424
425 class Conv3d(_ConvNd):
~/miniconda3/lib/python3.8/site-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight)
417 weight, self.bias, self.stride,
418 _pair(0), self.dilation, self.groups)
--> 419 return F.conv2d(input, weight, self.bias, self.stride,
420 self.padding, self.dilation, self.groups)
421
RuntimeError: Given groups=1, weight of size [192, 1, 16, 16], expected input[16, 3, 224, 224] to have 1 channels, but got 3 channels instead
vitstr loads rgb but converts it to grayscale before processing.
deep-text-recognition-benchmark/dataset.py
Line 210 in ea0d077
There is an option to use an rgb image as is:
deep-text-recognition-benchmark/dataset.py
Line 207 in ea0d077