Can backwark works in this way?

1 
   Hey, I write a model to generate sequential images. My model looks like this:

  netV's input is noise and hidden state,  its output is an image, the next hidden state and next noise.

I use a loop to to use netV to generate many images,which look like this:

 images = []
 for i in range( 8 ):
      image, noise_next, hidden_next = netV(noise, hidden)
      noise = noise_next
      hidden = hidden_next
      images.append(image)  
  
  The forward is ok. However, I'm not sure can the backwark works. Can the grad backward normally? I don't know how the grad flows in the backward
2

I don’t know how you do the backward. Could you give an example?
AFAIK, hidden.backward() would be ok, just like RNN.

3

The backward is:

   netD's input is many images. And the output is 0 or 1.

  images = []
  for i in range( 8 ):
       image, noise_next, hidden_next = netV(noise, hidden)
       noise = noise_next
       hidden = hidden_next
       images.append(image)  

 real_label is a bacth * 1 tesor filled with 1. The backward like this:

 output = netD(images)
 criterion = nn.BCELoss
 error = criterion(output, real_label)
 error.backward()

In my test when the images number less than 5. Grad can backward. However when the number is more than 5. The grad disappear. BTW, I’m not sure this is right.

4

if your code goes like this:

images = torch.cat(images)
output = netD(images)

It will work.
Also you can have a look at the example of DCGAN

5

That’s different. I try to generate sequential images. The netD’s input is more like a video.