Question about gated deconv
r06922019 opened this issue · 2 comments
r06922019 commented
Hi,
Thanks for your great work.
In your code,
https://github.com/run-youngjoo/SC-FEGAN/blob/master/ops.py#L50
this line states g = tf.nn.sigmoid(deconv)
However, IMHO the sigmoid should be applied to g itself to construct the gate
It should be g = tf.nn.sigmoid(g)
right?
Did I misunderstand anything?
Thanks for your great work again!
r06922019 commented
Also, according to this line,
https://github.com/run-youngjoo/SC-FEGAN/blob/master/ops.py#L46
g = tf.nn.conv2d_transpose(input_, w, output_shape=output_shape, strides=[1, d_h, d_w, 1])
it seems that the gate g
shares the same w
used in deconv
Can you provide some thoughts on this?
Thanks again
abtExp commented
You're right.