Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/hwalsuklee/tensorflow-mnist-vae
Tensorflow implementation of variational auto-encoder for MNIST
https://github.com/hwalsuklee/tensorflow-mnist-vae
autoencoder dae denoising-autoencoders mnist tensorflow vae variational-autoencoder
Last synced: about 5 hours ago
JSON representation
Tensorflow implementation of variational auto-encoder for MNIST
- Host: GitHub
- URL: https://github.com/hwalsuklee/tensorflow-mnist-vae
- Owner: hwalsuklee
- Created: 2017-03-20T15:40:35.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2017-04-11T07:08:25.000Z (almost 8 years ago)
- Last Synced: 2025-01-06T00:07:45.236Z (7 days ago)
- Topics: autoencoder, dae, denoising-autoencoders, mnist, tensorflow, vae, variational-autoencoder
- Language: Python
- Size: 374 KB
- Stars: 495
- Watchers: 18
- Forks: 182
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Variational Auto-Encoder for MNIST
An implementation of variational auto-encoder (VAE) for MNIST descripbed in the paper:
* [Auto-Encoding Variational Bayes](https://arxiv.org/pdf/1312.6114) by Kingma et al.
## Results
### Reproduce
Well trained VAE must be able to reproduce input image.
Figure 5 in the paper shows reproduce performance of learned generative models for different dimensionalities.
The following results can be reproduced with command:
```
python run_main.py --dim_z --num_epochs 60
```
Input image
2-D latent space
5-D latent space
10-D latent space
20-D latent space
### Denoising
When training, salt & pepper noise is added to input image, so that VAE can reduce noise and restore original input image.
The following results can be reproduced with command:
```
python run_main.py --dim_z 20 --add_noise True --num_epochs 40
```
Original input image
Input image with noise
Restored image via VAE
### Learned MNIST manifold
Visualizations of learned data manifold for generative models with 2-dim. latent space are given in Figure. 4 in the paper.
The following results can be reproduced with command:
```
python run_main.py --dim_z 2 --num_epochs 60 --PMLR True
```
Learned MNIST manifold
Distribution of labeled data
## Usage
### Prerequisites
1. Tensorflow
2. Python packages : numpy, scipy, PIL(or Pillow), matplotlib
### Command
```
python run_main.py --dim_z
```
*Example*:
`python run_main.py --dim_z 20`
### Arguments
*Required* :
* `--dim_z`: Dimension of latent vector. *Default*: `20`
*Optional* :
* `--results_path`: File path of output images. *Default*: `results`
* `--add_noise`: Boolean for adding salt & pepper noise to input image. *Default*: `False`
* `--n_hidden`: Number of hidden units in MLP. *Default*: `500`
* `--learn_rate`: Learning rate for Adam optimizer. *Default*: `1e-3`
* `--num_epochs`: The number of epochs to run. *Default*: `20`
* `--batch_size`: Batch size. *Default*: `128`
* `--PRR`: Boolean for plot-reproduce-result. *Default*: `True`
* `--PRR_n_img_x`: Number of images along x-axis. *Default*: `10`
* `--PRR_n_img_y`: Number of images along y-axis. *Default*: `10`
* `--PRR_resize_factor`: Resize factor for each displayed image. *Default*: `1.0`
* `--PMLR`: Boolean for plot-manifold-learning-result. *Default*: `False`
* `--PMLR_n_img_x`: Number of images along x-axis. *Default*: `20`
* `--PMLR_n_img_y`: Number of images along y-axis. *Default*: `20`
* `--PMLR_resize_factor`: Resize factor for each displayed image. *Default*: `1.0`
* `--PMLR_n_samples`: Number of samples in order to get distribution of labeled data. *Default*: `5000`
## References
The implementation is based on the projects:
[1] https://github.com/oduerr/dl_tutorial/tree/master/tensorflow/vae
[2] https://github.com/fastforwardlabs/vae-tf/tree/master
[3] https://github.com/kvfrans/variational-autoencoder
[4] https://github.com/altosaar/vae
## Acknowledgements
This implementation has been tested with Tensorflow r0.12 on Windows 10.