# BigGAN-Tensorflow **Repository Path**: yrccry/BigGAN-Tensorflow ## Basic Information - **Project Name**: BigGAN-Tensorflow - **Description**: Simple Tensorflow implementation of "Large Scale GAN Training for High Fidelity Natural Image Synthesis" (BigGAN) - **Primary Language**: Unknown - **License**: MIT - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2021-04-27 - **Last Updated**: 2021-04-27 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # BigGAN-Tensorflow Simple Tensorflow implementation of ["Large Scale GAN Training for High Fidelity Natural Image Synthesis" (BigGAN)](https://arxiv.org/abs/1809.11096) ![main](./assets/main.png) ## Issue * **The paper** used `orthogonal initialization`, but `I used random normal initialization.` The reason is, when using the orthogonal initialization, it did not train properly. * I have applied a hierarchical latent space, but **not** a class embeddedding. ## Usage ### dataset * `mnist` and `cifar10` are used inside keras * For `your dataset`, put images like this: ``` ├── dataset    └── YOUR_DATASET_NAME ├── xxx.jpg (name, format doesn't matter) ├── yyy.png └── ... ``` ### train * python main.py --phase train --dataset celebA-HQ --gan_type hinge ### test * python main.py --phase test --dataset celebA-HQ --gan_type hinge ## Architecture ### 128x128 ### 256x256 ### 512x512 ## Author Junho Kim