google-research / nested-transformer

NesT is a simple method, which aggragrates nested local transformers on image blocks. The idea makes vision transformers attain better accuracy, data efficiency, and convergence on the ImageNet benchmark. NesT can be scaled to small datasets to match convnet accuracy.

At the first time, download ImageNet following tensorflow_datasets instruction from command lines. Optionally, download all pre-trained checkpoints

The codebase does not support multi-node GPU training (>8 GPUs). The models reported in our paper is trained using TPU with 1024 total batch size.

Leave a Comment