Hi, thank you for the interesting work. I have a question about the proposed method.
a 2D convolution with an output channel of 1 along with a Sigmoid function is added
self.conv_gate = nn.Conv2d(out_channels, 1, 3, stride=1, padding=1)
x_gate = rearrange(x_2d, "b c f h w -> (b f) c h w")
c = x_gate.shape[1]
x_gate = self.sigmoid(self.conv_gate(x_gate)).repeat(1, c, 1, 1)
I would like to know what is the insight behind using a c -> 1 channel convolution and then repeating back c times. As a side question, what is the purpose of using a sigmoid function after this branch before multiplying to the conv_1d output?
Thanks.
Hi, thank you for the interesting work. I have a question about the proposed method.
I would like to know what is the insight behind using a c -> 1 channel convolution and then repeating back c times. As a side question, what is the purpose of using a sigmoid function after this branch before multiplying to the conv_1d output? Thanks.