Last active
April 25, 2020 05:18
-
-
Save sicongzhao/9e998b5138376550d7d5ae3662574704 to your computer and use it in GitHub Desktop.
Demystify Transposed Convolutional Layers
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import torch | |
from torch import nn | |
# Create 2x2 input tensor | |
input_data = torch.tensor([[[[1.,2.],[3.,4.]]]]) | |
# Create a TCL layer with kernel_size=3 | |
transConv1 = nn.ConvTranspose2d(1, 1, 3, bias=False) | |
# Set kernel weights to be 1 | |
transConv1.weight.data = torch.ones(1,1,3,3) | |
# Calculate the output | |
transConv1(input_data) | |
# Output | |
# tensor([[[[ 1., 3., 3., 2.], | |
# [ 4., 10., 10., 6.], | |
# [ 4., 10., 10., 6.], | |
# [ 3., 7., 7., 4.]]]]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment