A ConvNet for the 2020s

Official PyTorch implementation of ConvNeXt, from the following paper:

A ConvNet for the 2020s. CVPR 2022.
Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell and Saining Xie
Facebook AI Research, UC Berkeley
[arXiv][video]

---

We propose ConvNeXt, a pure ConvNet model constructed entirely from standard ConvNet modules. ConvNeXt is accurate, efficient, scalable and very simple in design.

Catalog

• ImageNet-1K Training Code
• ImageNet-22K Pre-training Code
• ImageNet-1K Fine-tuning Code
• Downstream Transfer (Detection, Segmentation) Code
• Image Classification [Colab] and Web Demo
• Fine-tune on CIFAR with Weights & Biases logging [Colab]

Results and Pre-trained Models

ImageNet-1K trained models

name	resolution	acc@1	#params	FLOPs	model
ConvNeXt-T	224x224	82.1	28M	4.5G	model
ConvNeXt-S	224x224	83.1	50M	8.7G	model
ConvNeXt-B	224x224	83.8	89M	15.4G	model
ConvNeXt-B	384x384	85.1	89M	45.0G	model
ConvNeXt-L	224x224	84.3	198M	34.4G	model
ConvNeXt-L	384x384	85.5	198M	101.0G	model

ImageNet-22K trained models

name	resolution	acc@1	#params	FLOPs	22k model	1k model
ConvNeXt-T	224x224	82.9	29M	4.5G	model	model
ConvNeXt-T	384x384	84.1	29M	13.1G	-	model
ConvNeXt-S	224x224	84.6	50M	8.7G	model	model
ConvNeXt-S	384x384	85.8	50M	25.5G	-	model
ConvNeXt-B	224x224	85.8	89M	15.4G	model	model
ConvNeXt-B	384x384	86.8	89M	47.0G	-	model
ConvNeXt-L	224x224	86.6	198M	34.4G	model	model
ConvNeXt-L	384x384	87.5	198M	101.0G	-	model
ConvNeXt-XL	224x224	87.0	350M	60.9G	model	model
ConvNeXt-XL	384x384	87.8	350M	179.0G	-	model

ImageNet-1K trained models (isotropic)

name	resolution	acc@1	#params	FLOPs	model
ConvNeXt-S	224x224	78.7	22M	4.3G	model
ConvNeXt-B	224x224	82.0	87M	16.9G	model
ConvNeXt-L	224x224	82.6	306M	59.7G	model

Installation

Please check INSTALL.md for installation instructions.

Evaluation

We give an example evaluation command for a ImageNet-22K pre-trained, then ImageNet-1K fine-tuned ConvNeXt-B:

Single-GPU

python main.py --model convnext_base --eval true \
--resume https://dl.fbaipublicfiles.com/convnext/convnext_base_22k_1k_224.pth \
--input_size 224 --drop_path 0.2 \
--data_path /path/to/imagenet-1k

Multi-GPU

python -m torch.distributed.launch --nproc_per_node=8 main.py \
--model convnext_base --eval true \
--resume https://dl.fbaipublicfiles.com/convnext/convnext_base_22k_1k_224.pth \
--input_size 224 --drop_path 0.2 \
--data_path /path/to/imagenet-1k

This should give

* Acc@1 85.820 Acc@5 97.868 loss 0.563

• For evaluating other model variants, change --model, --resume, --input_size accordingly. You can get the url to pre-trained models from the tables above.
• Setting model-specific --drop_path is not strictly required in evaluation, as the DropPath module in timm behaves the same during evaluation; but it is required in training. See TRAINING.md or our paper for the values used for different models.

Training

See TRAINING.md for training and fine-tuning instructions.

Acknowledgement

This repository is built using the timm library, DeiT and BEiT repositories.

License

This project is released under the MIT license. Please see the LICENSE file for more information.

Citation

If you find this repository helpful, please consider citing:

@Article{liu2022convnet,
  author  = {Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
  title   = {A ConvNet for the 2020s},
  journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year    = {2022},
}

---

---

Execution

1. main.py

   • 전체 code 실행
   • get_args_parser( )의 parameter 수정

   --data_path : Train data  위치 --> list 형태로 입력
   --eval_data_path : Validation data 위치 --> string 형태로 입력
   --nb_classes : class 수 지정 --> amb class를 포함하는 경우 4로 지정
   --use_softlabel : soft label을 사용할 경우 True 설정
   --soft_label_ratio : soft label의 target ratio(amb_pos : amb_neg)
   --label_ratio : pos,neg target ratio
   # Image Crop & Padding --> data set image load와 관련된 항목
   

2. engine.py

   • train, validation, prediction(check result)과 관련된 코드
   • prediction(evaluation) 모듈(새로 추가)
     • prediction 모듈은 train 결과를 불러와 evaluation
     • args.pred가 True로 설정되면 prediction진입
     • 결과 image구분과 graph 결과 생성

3. preprocess_data.py & datasets.py

   • dataset 생성과 image crop 및 전처리 관련 코드
   • 두 파일내에 있는 function 및 class를 활용
   • split_data
     • 데이터 셋을 train, val, test으로 구분하는 모듈
     • 기존에 split파일이 있으면 새로 목록을 구성하지 않음
     • tset, val 비율에 따라 파일명 생성
   • make_list
     • dataloader를 통해서 불러올 raw데이터 list생성

4. softLabelLoss.py

   • 다양한 loss를 적용하기 위한 code
   • args.np_class 가 2 혹은 4일 경우 target을 수정
   • args.use_sortlabel 이 True일 경우 4class -> 2class로 변경

5. load_board.py

   • log에 저장되어 있는 tensorboard 저장파일 파싱
   • csv로 결과 저장
   • path에 log파일이 저장되어 있는 폴더 이름 수정 후 실행
   • 추가로 필요한 부분이 있는 경우 col, val 부분을 수정
   • csv 폴더에 csv파일 생성

6. run.py

   • 루틴한 실험을 진행하기 위한 코드
   • base : 변동이 없는 parameter 설정
   • 변동이 있는 parameter는 list형태로 지정하고 for문으로 실행