It’s coming from the number of features of the activation you are trying to pass to self.fc1.
I.e. x would have the shape here:
x = x.reshape(x.size(0), -1)
print(x.shape) # should be [batch_size, 387200]
x = F.relu(self.fc1(x))
It’s coming from the number of features of the activation you are trying to pass to self.fc1.
I.e. x would have the shape here:
x = x.reshape(x.size(0), -1)
print(x.shape) # should be [batch_size, 387200]
x = F.relu(self.fc1(x))