Skip to content

Taoerwang/tensorflow-models-with-simple-ways

Repository files navigation

Tensorflow models with simple ways

Some models with easy understanding code,it will help you understand what the model does.These models can only work with not very good results.

Models list

1.Adversarial Networks (GAN)

2.Special structure Convolutional network (Not recurring paper)

3.Other Models

  • None

Results of some models

The results are based on MNIST or Fashion-MNIST

AAE

ACGAN

Auto_encoder

Input image → Hidden layer → Output image

BGAN

BiGAN

CCGAN

Real image → Random cropping image → Repaired image

CGAN

CoGAN

A: MNIST      B: Rotate 90 degrees MNIST
The model try to convert between A and B.
A → B

B → A

CycleGAN

A: MNIST      B: Rotate 90 degrees MNIST
The model try to convert between A and B.
A → B

B → A

DCGAN

GAN

VAE

Input image → Hidden layer → Output image