apple1986
commented
7 months ago 这个默认输入的维度是(4,1,224,224)，因为Transformer模块求自注意力与通道数有关，如果输入512x512，你需要调整后面的通道数，或者在卷积网络之后再加一个resize（或者其它调整尺度的模块）
在 2024-04-18 11:31:46，"degts" @.***> 写道：
您好，我在运行LeViT-UNet模型时遇到了一下错误： Traceback (most recent call last): File "D:/Program Files/JetBrains/PyCharm Community Edition 2023.1.4/plugins/python-ce/helpers/pydev/pydevd.py", line 1496, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "D:\Program Files\JetBrains\PyCharm Community Edition 2023.1.4\plugins\python-ce\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "E:\test\test2_muscle and adipose segmentation\test2_SL\train.py", line 364, in Train(train_root) File "E:\test\test2_muscle and adipose segmentation\test2_SL\train.py", line 211, in Train outputs = net(inputs) File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, kwargs) File "E:\test\test2_muscle and adipose segmentation\test2_SL\model_LeViT_UNet_128s.py", line 583, in forward x = self.block_1(x) # torch.Size([1, 196, 128])--> torch.Size([1, 196, 128]) : CNN->Trans File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, *kwargs) File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\container.py", line 204, in forward input = module(input) File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(input, kwargs) File "E:\test\test2_muscle and adipose segmentation\test2_SL\model_LeViT_UNet_128s.py", line 151, in forward return x + self.m(x) File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, *kwargs) File "E:\test\test2_muscle and adipose segmentation\test2_SL\model_LeViT_UNet_128s.py", line 216, in forward (q @ k.transpose(-2, -1)) self.scale RuntimeError: The size of tensor a (1024) must match the size of tensor b (196) at non-singleton dimension 3
LeViT-UNet网络调用命令为：net = Build_LeViT_UNet_128s(num_classes=5) 我的输入数据的维度是(4，1，512，512)，num_classes是5，请问这个错误是由什么引起的呢？
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>
degts
您好，我在运行LeViT-UNet模型时遇到了一下错误： Traceback (most recent call last): File "D:/Program Files/JetBrains/PyCharm Community Edition 2023.1.4/plugins/python-ce/helpers/pydev/pydevd.py", line 1496, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "D:\Program Files\JetBrains\PyCharm Community Edition 2023.1.4\plugins\python-ce\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "E:\test\test2_muscle and adipose segmentation\test2_SL\train.py", line 364, in
Train(train_root)
File "E:\test\test2_muscle and adipose segmentation\test2_SL\train.py", line 211, in Train
outputs = net(inputs)
File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, kwargs) File "E:\test\test2_muscle and adipose segmentation\test2_SL\model_LeViT_UNet_128s.py", line 583, in forward x = self.block_1(x) # torch.Size([1, 196, 128])--> torch.Size([1, 196, 128]) : CNN->Trans File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, *kwargs) File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\container.py", line 204, in forward input = module(input) File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(input, kwargs) File "E:\test\test2_muscle and adipose segmentation\test2_SL\model_LeViT_UNet_128s.py", line 151, in forward return x + self.m(x) File "D:\ProgramData\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, *kwargs) File "E:\test\test2_muscle and adipose segmentation\test2_SL\model_LeViT_UNet_128s.py", line 216, in forward (q @ k.transpose(-2, -1)) self.scale RuntimeError: The size of tensor a (1024) must match the size of tensor b (196) at non-singleton dimension 3
LeViT-UNet网络调用命令为：net = Build_LeViT_UNet_128s(num_classes=5) 我的输入数据的维度是(4，1，512，512)，num_classes是5，请问这个错误是由什么引起的呢？