Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/paddlepaddle/plsc
Paddle Large Scale Classification Tools，supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, Swin, DeiT, CaiT, FaceViT, MoCo, MAE, ConvMAE, CAE.
https://github.com/paddlepaddle/plsc
arcface cait convmae cosface data-parallel deit distributed-training face-recognition facevit hight-speed large-scale mae moco-v3 model-parallel paddle paddlepaddle partial-fc resnet swin-transformer vit
Last synced: 14 days ago
JSON representation
Paddle Large Scale Classification Tools，supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, Swin, DeiT, CaiT, FaceViT, MoCo, MAE, ConvMAE, CAE.
- Host: GitHub
- URL: https://github.com/paddlepaddle/plsc
- Owner: PaddlePaddle
- License: apache-2.0
- Created: 2019-12-13T16:30:59.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2023-06-06T11:13:52.000Z (over 1 year ago)
- Last Synced: 2024-04-26T16:21:25.474Z (7 months ago)
- Topics: arcface, cait, convmae, cosface, data-parallel, deit, distributed-training, face-recognition, facevit, hight-speed, large-scale, mae, moco-v3, model-parallel, paddle, paddlepaddle, partial-fc, resnet, swin-transformer, vit
- Language: Python
- Homepage:
- Size: 2.9 MB
- Stars: 144
- Watchers: 21
- Forks: 32
- Open Issues: 22
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
------------------------------------------------------------------------------------------
## Introduction
[PLSC](https://github.com/PaddlePaddle/PLSC) is an open source repo for a collection of Paddle Large Scale Classification Tools, which supports large-scale classification model pre-training as well as finetune for downstream tasks.
## Available Models
* [Face Recognition](./task/recognition/face/)
* [ViT](./task/classification/vit/)
* [Swin](./task/classification/swin/)
* [DeiT](./task/classification/deit/)
* [CaiT](./task/classification/cait/)
* [ConvNeXt](./task/classification/convnext)
* [MoCo v3](./task/ssl/mocov3/)
* [CAE](./task/ssl/cae/)
* [MAE](./task/ssl/mae/)
* [ConvMAE](./task/ssl/mae/)
* [ToMe](./task/accelerate/tome)
## Top News 🔥
**Update (2023-01-11):** PLSC v2.4 is released, we refactored the entire repository based on task types. This repository has been adapted to PaddlePaddle release 2.4. In terms of models, we have added 4 new ones, including [FaceViT](https://arxiv.org/abs/2203.15565), [CaiT](https://arxiv.org/abs/2103.17239), [MoCo v3](https://arxiv.org/abs/2104.02057), [MAE](https://arxiv.org/abs/2111.06377). At present, each model in the repository can be trained from scratch to achieve the original official accuracy, especially the training of ViT-Large on the ImageNet21K dataset. In addition, we also provide a method for ImageNet21K data preprocessing. In terms of AMP training, PLSC uses FP16 O2 training by default, which can speed up training while maintaining accuracy.
**Update (2022-07-18):** PLSC v2.3 is released, a new upgrade, more modular and highly extensible. Support more tasks, such as [ViT](https://arxiv.org/abs/2010.11929), [DeiT](https://arxiv.org/abs/2012.12877). The `static` graph mode will no longer be maintained as of this release.
**Update (2022-01-11):** Supported NHWC data format of FP16 to improve 10% throughtput and decreased 30% GPU memory. It supported 92 million classes on single node 8 NVIDIA V100 (32G) and has high training throughtput. Supported best checkpoint save. And we released 18 pretrained models and PLSC v2.2.
**Update (2021-12-11):** Released [Zhihu Technical Artical](https://zhuanlan.zhihu.com/p/443091282) and [Bilibili Open Class](https://www.bilibili.com/video/BV1VP4y1G73X)
**Update (2021-10-10):** Added FP16 training, improved throughtput and optimized GPU memory. It supported 60 million classes on single node 8 NVIDIA V100 (32G) and has high training throughtput.
**Update (2021-09-10):** This repository supported both `static` mode and `dynamic` mode to use paddlepaddle v2.2, which supported 48 million classes on single node 8 NVIDIA V100 (32G). It added [PartialFC](https://arxiv.org/abs/2010.05222), SparseMomentum, and [ArcFace](https://arxiv.org/abs/1801.07698), [CosFace](https://arxiv.org/abs/1801.09414) (we refer to MarginLoss). Backbone includes IResNet and MobileNet.
## Installation
PLSC provides two usage methods: one is as an external third-party library, and users can use `import plsc` in their own projects; the other is to develop and use it locally based on this repository.
**Note**: With the continuous iteration of the PaddlePaddle version, the PLSC `master` branch adapts to the PaddlePaddle `develop` branch, and API mismatches may occur in lower versions of PaddlePaddle.
### Install plsc as a third-party library
```shell
pip install git+https://github.com/PaddlePaddle/PLSC@master
```
For stable development, you can install a previous version of plsc.
```
pip install plsc==2.4
```
### Install plsc locally
```shell
git clone https://github.com/PaddlePaddle/PLSC.git
cd /path/to/PLSC/
# [optional] pip install -r requirements.txt
python setup.py develop
```
See [Installation instructions](./tutorials/get_started/installation.md).
## Getting Started
See [Quick Run Recognition](./tutorials/get_started/quick_run_recognition.md) for the basic usage of PLSC.
## Tutorials
* [Configuration](./tutorials/basic/config.md)
See more [tutorials](./tutorials/README.md).
## Documentation
* [Data Augmentation](./docs/data_augmentation.md)
See [documentation](./docs/README.md) for the usage of more APIs or modules.
## License
This project is released under the [Apache 2.0 license](./LICENSE).
## Citation
```
@misc{plsc,
title={PLSC: An Easy-to-use and High-Performance Large Scale Classification Tool},
author={PLSC Contributors},
howpublished = {\url{https://github.com/PaddlePaddle/PLSC}},
year={2022}
}
```