• This is an implementation of Deep Convolutional Generative Adversarial Networks. Looking for Text to Image Synthesis? click here

• For earlier version, please check dcgan release and tensorlayer

• For more computer vision applications, check TLXCV

🔥🔥🔥🔥🔥🔥 You need install TensorLayerX at first!

🔥🔥🔥🔥🔥🔥 Please install TensorLayerX via source

pip install tensorlayerx

or

pip install git+https://github.com/tensorlayer/tensorlayerx.git 

First, download the aligned face images from google or baidu to a data folder.

Please place dataset 'img_align_celeba.zip' under 'data/celebA/' by default.

Your directory structure should look like this:

dcgan/
    └── data.py
    └── model.py
    └── train.py
    └── README.md
    └── data
          └── celebA
            └── img_align_celeba.zip

Second, train the GAN:

$ python train.py