DeiT: Data-efficient Image Transformers
This repository contains PyTorch evaluation code, training code and pretrained models for DeiT (Data-Efficient Image Transformers).
They obtain competitive tradeoffs in terms of speed / precision:
For details see Training data-efficient image transformers & distillation through attention by Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles and Hervé Jégou.
If you use this code for a paper please cite:
@article{touvron2020deit,
title={Training data-efficient image transformers & distillation through attention},
author={Hugo Touvron and Matthieu Cord and Matthijs Douze and Francisco Massa and Alexandre Sablayrolles and Herv\'e J\'egou},
journal={arXiv preprint arXiv:2012.12877},
year={2020}
}
Model Zoo
We provide baseline DeiT models pretrained on ImageNet 2012.
| name | acc@1 | acc@5 | #params | url |
|---|---|---|---|---|
| DeiT-tiny | 72.2 | 91.1 | 5M | model |
| DeiT-small | 79.9 | 95.0 | 22M | model |
| DeiT-base | 81.8 | 95.6 | 86M | model |
| DeiT-tiny distilled | 74.5 | 91.9 | 6M | model |
| DeiT-small distilled | 81.2 | 95.4 | 22M | model |
| DeiT-base distilled | 83.4 | 96.5 | 87M | model |
| DeiT-base 384 | 82.9 | 96.2 | 87M | model |
| DeiT-base distilled 384 (1000 epochs) | 85.2 | 97.2 | 88M | model |
The models are also available via torch hub. Before using it, make sure you have the pytorch-image-models package timm==0.3.2 by Ross Wightman installed. Note that our work relies of the augmentations proposed in this library. In particular, the RandAugment and RandErasing augmentations that we invoke are the improved versions from the timm library, which already led the timm authors to report up to 79.35% top-1 accuracy with Imagenet training for their best model, i.e., an improvement of about +1.5% compared to prior art.
To load DeiT-base with pretrained weights on ImageNet simply do:
import torch
# check you have the right version of timm
import timm
assert timm.__version__ == "0.3.2"
# now load it with torchhub
model = torch.hub.load('facebookresearch/deit:main', 'deit_base_patch16_224', pretrained=True)
Additionnally, we provide a Colab notebook which goes over the steps needed to perform inference with DeiT.
Usage
First, clone the repository locally:
git clone https://github.com/facebookresearch/deit.git
Then, install PyTorch 1.7.0+ and torchvision 0.8.1+ and pytorch-image-models 0.3.2:
conda install -c pytorch pytorch torchvision
pip install timm==0.3.2
Data preparation
Download and extract ImageNet train and val images from http://image-net.org/. The directory structure is the standard layout for the torchvision datasets.ImageFolder, and the training and validation data is expected to be in the train/ folder and val folder respectively:
/path/to/imagenet/
train/
class1/
img1.jpeg
class2/
img2.jpeg
val/
class1/
img3.jpeg
class/2
img4.jpeg
Evaluation
To evaluate a pre-trained DeiT-base on ImageNet val with a single GPU run:
python main.py --eval --resume https://dl.fbaipublicfiles.com/deit/deit_base_patch16_224-b5f2ef4d.pth --data-path /path/to/imagenet
This should give
* Acc@1 81.846 Acc@5 95.594 loss 0.820
For Deit-small, run:
python main.py --eval --resume https://dl.fbaipublicfiles.com/deit/deit_small_patch16_224-cd65a155.pth --model deit_small_patch16_224 --data-path /path/to/imagenet
giving
* Acc@1 79.854 Acc@5 94.968 loss 0.881
Note that Deit-small is not the same model as in Timm.
And for Deit-tiny:
python main.py --eval --resume https://dl.fbaipublicfiles.com/deit/deit_tiny_patch16_224-a1311bcf.pth --model deit_tiny_patch16_224 --data-path /path/to/imagenet
which should give
* Acc@1 72.202 Acc@5 91.124 loss 1.219
Here you'll find the command-lines to reproduce the inference results for the distilled and finetuned models
deit_base_distilled_patch16_224
python main.py --eval --model deit_base_distilled_patch16_224 --resume https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_224-df68dfff.pth
giving
* Acc@1 83.372 Acc@5 96.482 loss 0.685
deit_small_distilled_patch16_224
python main.py --eval --model deit_small_distilled_patch16_224 --resume https://dl.fbaipublicfiles.com/deit/deit_small_distilled_patch16_224-649709d9.pth
giving
* Acc@1 81.164 Acc@5 95.376 loss 0.752
deit_tiny_distilled_patch16_224
python main.py --eval --model deit_tiny_distilled_patch16_224 --resume https://dl.fbaipublicfiles.com/deit/deit_tiny_distilled_patch16_224-b40b3cf7.pth
giving
* Acc@1 74.476 Acc@5 91.920 loss 1.021
deit_base_patch16_384
python main.py --eval --model deit_base_patch16_384 --input-size 384 --resume https://dl.fbaipublicfiles.com/deit/deit_base_patch16_384-8de9b5d1.pth
giving
* Acc@1 82.890 Acc@5 96.222 loss 0.764
deit_base_distilled_patch16_384
python main.py --eval --model deit_base_distilled_patch16_384 --input-size 384 --resume https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_384-d0272ac0.pth
giving
* Acc@1 85.224 Acc@5 97.186 loss 0.636
Training
To train DeiT-small and Deit-tiny on ImageNet on a single node with 4 gpus for 300 epochs run:
DeiT-small
python -m torch.distributed.launch --nproc_per_node=4 --use_env main.py --model deit_small_patch16_224 --batch-size 256 --data-path /path/to/imagenet --output_dir /path/to/save
DeiT-tiny
python -m torch.distributed.launch --nproc_per_node=4 --use_env main.py --model deit_tiny_patch16_224 --batch-size 256 --data-path /path/to/imagenet --output_dir /path/to/save
Multinode training
Distributed training is available via Slurm and submitit:
pip install submitit
To train DeiT-base model on ImageNet on 2 nodes with 8 gpus each for 300 epochs:
python run_with_submitit.py --model deit_base_patch16_224 --data-path /path/to/imagenet
To train DeiT-base with hard distillation using a RegNetY-160 as teacher, on 2 nodes with 8 GPUs with 32GB each for 300 epochs (make sure that the model weights for the teacher have been downloaded before to the correct location, to avoid multiple workers writing to the same file):
python run_with_submitit.py --model deit_base_distilled_patch16_224 --distillation-type hard --teacher-model regnety_160 --teacher-path https://dl.fbaipublicfiles.com/deit/regnety_160-a5fe301d.pth --use_volta32
To finetune a DeiT-base on 384 resolution images for 30 epochs, starting from a DeiT-base trained on 224 resolution images, do (make sure that the weights to the original model have been downloaded before, to avoid multiple workers writing to the same file):
python run_with_submitit.py --model deit_base_patch16_384 --batch-size 32 --finetune https://dl.fbaipublicfiles.com/deit/deit_base_patch16_224-b5f2ef4d.pth --input-size 384 --use_volta32 --nodes 2 --lr 5e-6 --weight-decay 1e-8 --epochs 30 --min-lr 5e-6
License
This repository is released under the Apache 2.0 license as found in the LICENSE file.
Contributing
We actively welcome your pull requests! Please see CONTRIBUTING.md and CODE_OF_CONDUCT.md for more info.
Can you please help me with this multinode training?
Best regards,
Mehdi
41 Dec 12, 2022
906 Dec 30, 2022
414 Jan 1, 2023
1.4k Dec 31, 2022
352 Dec 25, 2022
62 Oct 25, 2022
112 Dec 25, 2022
165 Dec 26, 2022
40 Dec 14, 2022
47 Oct 11, 2022
140 Dec 28, 2022
470 Dec 30, 2022
1.4k Jan 4, 2023
191 Dec 3, 2022
172 Dec 20, 2022
154 Dec 21, 2022
24 Dec 28, 2022
193 Dec 5, 2022