Skip to content

linxiaobo110/CNN_AUTOENCODER

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CNN_AUTOENCODER

Usage

To train a model

$ python run.py --num_epochs=10 --plot

All options

usage: run.py [-h] [--num_epochs NUM_EPOCHS] [--batch_size BATCH_SIZE]
              [--mode MODE] [--plot]

optional arguments:
  -h, --help            show this help message and exit
  --num_epochs NUM_EPOCHS
                        Specify the number of epoches
  --batch_size BATCH_SIZE
                        Specify batch size
  --mode MODE           Specify mode: `train` or `eval`
  --plot                Whether plot the reconstructed images or not

Loss & Reconstruction

After training 8000+ steps ...

  • Loss

  • Reconstructed MNIST images

About

Use cnn autoencoder on mnist dataset

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%