mirror of https://github.com/JDAI-CV/fast-reid.git
Summary: change warmup way by iter not by epoch, which will make it more flexible when training small epochs |
||
---|---|---|
.. | ||
configs | ||
fastcls | ||
README.md | ||
train_net.py |
README.md
FastCls 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/FastCls/train_net.py --config-file projects/FastCls/config/base-cls.yml --num-gpus 4