Skip to content

Latest commit

 

History

History
49 lines (40 loc) · 1.49 KB

README.md

File metadata and controls

49 lines (40 loc) · 1.49 KB

DCGAN in Pytorch

Overview

This code is the Pytorch implementation of Deep Convolutional Generative Adversarial Networks on MNIST and Anime dataset.

Dataset

Anime dataset can be downloaded from https://zhuanlan.zhihu.com/p/24767059 or https://drive.google.com/drive/folders/1qDhrjL0iz9rKb5t90Iy81pJKKCy9zNXx?usp=sharing

Prerequisites

  • python(3.6)
  • pytorch(0.3.1)

Results on MNIST dataset

The network was trained for 50 epochs in MNIST dataset,

epoch:10 epoch:20 epoch:50

Results on Anime dataset

The network was trained for 200 epochs in Anime dataset.

epoch:10 epoch:50 epoch:200

References