Skip to content

Xiaojiean/Training_YOLOv3_with_Multi-GPUs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PyTorch-YOLOv3-Multi_GPUs-Training

Training PyTorch-YOLOv3 with multi-GPUs.

Installation

Clone and install requirements
$ git clone https://github.com/zhangyongshun/Training_YOLOv3_with_Multi-GPUs.git
$ cd Training_YOLOv3_with_Multi-GPUs/
$ sudo pip install -r requirements.txt
Download pretrained weights
$ cd weights/
$ bash download_weights.sh
Download COCO
$ cd data/
$ bash get_coco_dataset.sh

Train with COCO

To train on COCO using a Darknet-53 backend pretrained on ImageNet run:

$ Modify the configs in config/config.py, especially paths of data and weights.
$ python train.py 

What we modify

We make the same number of targets for each image in function ListDataset.collate_fn of utils/dataset.py.

About

Modify from https://github.com/eriklindernoren/PyTorch-YOLOv3 to support training with multi-GPUs

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published