Self-Attention-GAN-Tensorflow
Self-Attention-GAN-Tensorflow copied to clipboard
selt-attention
https://github.com/taki0112/Self-Attention-GAN-Tensorflow/blob/d5237658881663103fc4d05cd86fa5b590fde0c9/SAGAN.py#L183
The transposed matrix, f(x).T, should be in the front position, according to the paper.
https://github.com/taki0112/Self-Attention-GAN-Tensorflow/blob/d5237658881663103fc4d05cd86fa5b590fde0c9/ops.py#L93
It seems your want to reshape the tensor. x.shape[0] means batchsize and x.shape[-1] means channel. What does -1 mean? Because the author didn't publish the code, just read the paper ,i don't know why your want to reshape the tensor?
thx!