DCGAN-tensorflow

GitHub describes it as A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks". The repository metadata lists JavaScript as its primary language. The metadata lists the MIT license. This article stays within the project description and details documented in the GitHub repository README.

GitHub describes it as A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks". The repository metadata lists JavaScript as its primary language. The metadata lists the MIT license. The README describes the project this way: Tensorflow implementation of Deep Convolutional Generative Adversarial Networks which is a stabilize Generative Adversarial Networks. The referenced torch code can be found here.

The README section "DCGAN in Tensorflow" states: Brandon Amos wrote an excellent blog post and image completion code based on this repo. To avoid the fast convergence of D (discriminator) network, G (generator) network is updated twice for each D network update, which differs from original paper.

The README section "Prerequisites" states: - Python 2.7 or Python 3.3+ - (Optional) moviepy (for visualization) - (Optional) Align&Cropped Images.zip : Large-scale CelebFaces Dataset

The README section "Usage" states: $ python main.py --dataset mnist --input height=28 --output height=28 --train $ python main.py --dataset celebA --input height=108 --train --crop

The repository README is the source for this review. It does not replace a local installation or an independent test.

• Source 1 · Project repository
• Source 2 · README