A ConvNet for the 2020s

Official PyTorch implementation of ConvNeXt, from the following paper:

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

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


  • ImageNet-1K Training Code
  • ImageNet-22K Pre-training Code
  • ImageNet-1K Fine-tuning Code
  • Downstream Transfer (Detection, Segmentation) Code

Results and Pre-trained Models

ImageNet-1K trained models

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

ImageNet-22K trained models

name resolution acc@1 #params FLOPs 22k model 1k model
ConvNeXt-B 224×224 85.8 89M 15.4G model model
ConvNeXt-B 384×384 86.8 89M 47.0G model
ConvNeXt-L 224×224 86.6 198M 34.4G model model
ConvNeXt-L 384×384 87.5 198M 101.0G model
ConvNeXt-XL 224×224 87.0 350M 60.9G model model
ConvNeXt-XL 384×384 87.8 350M 179.0G model

ImageNet-1K trained models (isotropic)

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


Please check INSTALL.md for installation instructions.


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


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


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.


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


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


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


If you find this repository helpful, please consider citing:

  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 = {arXiv preprint arXiv:2201.03545},
  year    = {2022},


View Github