mirrors/fast-reid

mirror of https://github.com/JDAI-CV/fast-reid.git synced 2025-06-03 14:50:47 +08:00

Go to file

liaoxingyu fd90555e19 feat: add multi-dataset joint training

new feature that can support joint training, and find some bugs in funtion combine_all of datasets/bases.py that assume person id in dataset has been relabeld from 0 to num_class.
Another bug appears in msmt17 which trainset and testset person id both begin from 0, and we should change testset id from num_class of trainset.

2020-05-18 20:06:04 +08:00

feat: add MGN model

2020-05-15 11:39:54 +08:00

docs: update README

2020-05-12 23:00:15 +08:00

feat: support visualizing label list

2020-05-12 21:35:33 +08:00

feat: add multi-dataset joint training

2020-05-18 20:06:04 +08:00

add projects folder

2020-05-14 12:52:50 +08:00

update version0.2 code

2020-03-25 10:58:26 +08:00

fix: add a simple way to reset data prefetcher when resume training

2020-05-09 11:58:27 +08:00

.gitignore

Change architecture:

2020-02-18 21:01:23 +08:00

GETTING_STARTED.md

docs: update README

2020-05-12 23:00:15 +08:00

MODEL_ZOO.md

update model zoo results

2020-05-06 09:58:49 +08:00

README.md

docs: update README

2020-05-12 23:00:15 +08:00

README.md

FastReID

FastReID is a research platform that implements state-of-the-art re-identification algorithms.

Quick Start

The designed architecture follows this guide PyTorch-Project-Template, you can check each folder's purpose by yourself.

See GETTING_STARTED.md.

Learn more at out documentation. And see projects/ for some projects that are build on top of fastreid.

Install dependencies:

pytorch 1.0.0+
torchvision
yacs

Model Zoo and Baselines

We provide a large set of baseline results and trained models available for download in the Fastreid Model Zoo.

Languages

Python 86.7%

C++ 11%

Cython 1.3%

CMake 0.6%

Dockerfile 0.4%