I’d like to reconstruct 3D object from 2D images.
For that, I try to use convolutional auto encoder. However, in which layer should I lift the dimensionality?
I wrote a code below, however, it shows an error “RuntimeError: invalid argument 2: size ‘[1 x 1156 x 1156]’ is invalid for input of with 2312 elements at pytorch-src/torch/lib/TH/THStorage.c:41”
class dim_lifting(nn.Module):
def __init__(self):
super(dim_lifting, self).__init__()
self.encode = nn.Sequential(
nn.Conv2d(1, 34, kernel_size=5, padding=2),
nn.MaxPool2d(2),
nn.Conv2d(34, 16, kernel_size=5, padding=2),
nn.MaxPool2d(2),
nn.Conv2d(16, 8, kernel_size=5, padding=2),
nn.MaxPool2d(2),
nn.LeakyReLU()
)
self.fc1 = nn.Linear(2312, 2312)
self.decode = nn.Sequential(
nn.ConvTranspose3d(1, 16, kernel_size=5, padding=2),
nn.LeakyReLU(),
nn.ConvTranspose3d(16, 32, kernel_size=5, padding=2),
nn.LeakyReLU(),
nn.MaxPool2d(2))
def forward(self, x):
out = self.encode(x)
out = out.view(out.size(0), -1)
out = self.fc1(out)
out = out.view(1, 1156, 1156)
out = self.decode(out)
return out