oldpan / faceswap-deepfake-pytorch Goto Github PK

How do I test with two images？

could you offer the inference?thanks

Hello, this link is invalid.
https://space.oldpan.me/f/cccac1136338407797cb/?dl=1

Good Job! Why not implement the same padding in ConvTranspose2d?

Your padding_same_conv.py is a brilliant implementation for pytorch users needing padding=same. It really helps me and I cannot express anything but gratitude for your wonderful work.

However, I think there might be some mistakes in your implementation, especially in your conv2d_same_padding function.
You only calculate the number of elements padded for the col of the input, and just copy it to the row, which might be wrong when stride[0] != stride [1] and dilation[0] != dilation[1].
And the type of your initial value of stride and dilation might be list according to your following code but not the int you set.

I try to predict but the result are far way from reasonable... Might me did something wrong with preprocess?

Hello author, I want to know how to test/pred it with two face pic ? I mean , writer a test.py file to run.
I writer this file to load model to test, but it doesn't work.(Don't Change the Face).

作者你好，我想问下，你这个测试文件该怎么写啊？就是写一个test.py文件，加载模型，输入两张人脸图像进行换脸。我自己写了一个，但是没有换脸成功，就好像模型没有加载成功似的。请问你能不能写一个这个文件呢？

such as "torch.nn.MaxPool2d(kernel_size=2, stride=(2,1), padding=(0,1))"