Hi everyone!
I have a network designed for 64x64 images (height/width), I’m trying to reform it to take input of 8x8. I’ve managed to fix the generator, but I’m stuck with the discriminator:
class Discriminator(nn.Module):
def __init__(self, latent_vector_size, features_d, num_channels):
super(Discriminator, self).__init__()
self.latent_vector_size = latent_vector_size
self.features_d = features_d
self.num_channels = 2 #num_channels # OVO JE PROMINJENO DA GLEDA SAMO JEDAN KANAL
self.optimizer = None
self.main = None
@staticmethod
def discriminator_block(in_filters, out_filters, stride, normalize):
layers = [
nn.Conv2d(
in_channels = in_filters,
out_channels = out_filters,
kernel_size = 3,
stride = stride,
padding = 1
)
]
if normalize:
layers.append(
nn.InstanceNorm2d(out_filters)
)
layers.append(
nn.LeakyReLU(0.2, inplace = True)
)
return layers
def build(self):
layers = []
in_filters = self.num_channels
for out_filters, stride, normalize in [(self.features_d, 2, False), (self.features_d * 2, 2, True),
(self.features_d * 4, 2, True), (self.features_d * 8, 1, True)]:
layers.extend(self.discriminator_block(
in_filters,
out_filters,
stride,
normalize
))
in_filters = out_filters
layers.append(
nn.Conv2d(
in_channels = out_filters,
out_channels = 1,
kernel_size = 3,
stride = 1,
padding = 1
)
)
self.main = nn.Sequential(*layers)
def forward(self, input):
return self.main(input)
def define_optim(self, learning_rate, beta1):
self.optimizer = optim.Adam(self.parameters(), lr = learning_rate, betas = (beta1, 0.999))
@staticmethod
def init_weights(layers):
classname = layers.__class__.__name__
if classname.find('Conv') != -1:
nn.init.normal_(layers.weight.data, 0.0, 0.02)
elif classname.find('BatchNorm') != -1:
nn.init.normal_(layers.weight.data, 1.0, 0.02)
nn.init.constant_(layers.bias.data, 0)
Input is [20, 2, 8, 8], but the discriminator gets to torch.Size([20, 16, 1, 1]). How can I adjust the discriminator so that nn.InstanceNorm2d gets the proper input size?
Thanks!