Number of channels for model input

[kalpa61]

Encountered a code bug when replicating, specifically, the Vit model expected input channel is 2, but the input channel is 3, the source code missing the intermediate processing part? The following is the program error:

Traceback (most recent call last):
File "D:\PycharmProject\MEMix\main.py", line 239, in
run_training(cut_alpha=2.0, mix_alpha=1.0,num_classes=5)
File "D:\PycharmProject\MEMix\main.py", line 124, in run_training
ALL, attn, final = net_all(mix_flow, onset)
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "D:\PycharmProject\MEMix\model.py", line 272, in forward
x = self.model(x,y) # [B,768]
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "D:\PycharmProject\MEMix\model.py", line 201, in forward
x = self.forward_features(x,y)
File "D:\PycharmProject\MEMix\model.py", line 175, in forward_features
x = self.patch_embed(x)
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Anaconda3\envs\Mers\lib\site-packages\timm\layers\patch_embed.py", line 131, in forward
x = self.proj(x)
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "D:\Anaconda3\envs\Mers\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Given groups=1, weight of size [768, 2, 16, 16], expected input[34, 3, 224, 224] to have 2 channels, but got 3 channels instead