top of page
Search
  • Writer's pictureLena Du

When Cats meet GANs

Updated: Apr 21, 2022

Please refer to the Project webpage for result images


Part 1 DCGAN

1.1 Implement Data Augmentation

Deluxe data augmentation helps the model to be more robust.

1.2 DCGAN - Discriminator

Padding

The calculation of padding is:

m=⌊n+2p−K⌋S

, where m is the output size and n is the input size. p is the padding, K is the kernel size, and S is the stride. Given the size is downsampled by scale 2, we know n = 2m. With K = 4 and S = 2, we will have

2m=⌊2m+2p−4⌋

Then,

p=1

which means padding is 1.

1.3 DCGAN - Generator

The design of the first layer in DCGenerator is using conv, instead of up_conv. The idea is to use padding 3, kernel size 4, and stride 1 to obtain a 4x4 output. I also replaced nn.ReLU with nn.LeakyReLU for its better performance.


1.4 Result

As we can see, the result of the Deluxe data augmentation + full diffaug configuration with more iterations has better quality and resolution.

41 views0 comments

Recent Posts

See All

GAN Photo Editing

Project webpage GitHub Repo (incoming) B & W: Drew figures to explain the optimization process (in part1 and part2) Experiment with high-res models of Grumpy Cat Experiment with other datasets Part 1:

Neural Style Transfer (Student Choice Award winner)

Please refer to the Project webpage for result images GitHub repo B & W are explained in part4 Stylize images from the previous homework. Implemented my own cropping method. Tried to use a feedforward

Gradient Domain Fusion

Project webpage GitHub Repo 1. Brief description This project is using image blending to combine contents from 2 different images. The idea is to construct a linear system, which is restricted by the

Post: Blog2_Post
bottom of page