Skip to content

Latest commit

 

History

History
13 lines (7 loc) · 367 Bytes

README.md

File metadata and controls

13 lines (7 loc) · 367 Bytes

Pipeline

How to run training

First of all, create a config. You may find some examples of configs in folders mnist_pipeline, cifar_pipeline and imagenet_pipeline. Then, call:

python3 bin/train.py path_to_config

For example, for reproducing results from Fixup paper just call:

python3 bin/train.py cifar_pipeline/configs/resnet110_fixup.py