google/compare_gan

The code is configurable via Gin and runs on GPU/TPU/CPUs. You can easily install the library and all necessary dependencies by running: pip install -e . To see all available options please run python main.py We recommend using the ctpu tool to create a Cloud TPU and corresponding Compute Engine VM. We use v3-128 Cloud TPU v3 Pod for training models on ImageNet in 128x128 resolutions.