项目作者： satyenrajpal

项目描述：
Implementation of a Basic Variational Auto-Encoder

高级语言： Python

项目主页：

项目地址: git://github.com/satyenrajpal/VAE.git

创建时间： 2018-09-16T06:04:59Z
项目社区：https://github.com/satyenrajpal/VAE
开源协议：MIT License
下载

VAE

My implementation of a Basic Variational Auto-Encoder. There are a few changes in comparison to this paper -

Instead of upsampling by Nearest Neighbors, Conv Transpose is used
Reconstruction loss is a simple l2 loss

The teapot dataset is sourced from this repo.

Results -

MNIST -

To run the script, simply run python main.py --dataset DATASET[MNIST/Teapots] --img_dir IMAGE_DIRECTORY --save_dir SAVE_DIRECTORY

Additional arguments are provided in main.py for further customization