apple1986

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...

Sorry, we did not develop the 3D version currently. You can try to change the 2D convolution to 3D convolution , change the dimension of each patch dirtectly. Best wishes...

> loss_cons 请问这里的loss_cons是什么？谢谢