History

liaoxingyu 7e652fea2a feat: Add contiguous parameters support Support contiguous parameters to train faster. It can split parameters into different contiguous groups by freeze_layer, lr and weight decay.		2021-07-05 11:10:37 +08:00
..
configs	feat: Add contiguous parameters support	2021-07-05 11:10:37 +08:00
fastclas	Minor changes	2021-05-31 17:27:14 +08:00
README.md	bugfix for ClasDataset	2021-04-08 11:01:15 +08:00
train_net.py	Minor changes	2021-05-31 17:27:14 +08:00

README.md

FastClas in FastReID

This project provides a baseline and example for image classification based on fastreid.

Datasets Preparation

We refer to pytorch tutorial for dataset preparation. This is just an example for building a classification task based on fastreid. You can customize your own datasets and model.

Usage

If you want to train models with 4 gpus, you can run

python3 projects/FastClas/train_net.py --config-file projects/FastClas/config/base-clas.yml --num-gpus 4