Skip to content

Latest commit

 

History

History

token_labeling

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
exp
exp
 
 
tlt
tlt
 
 
README.md
README.md
 
 
main.py
main.py
 
 
validate.py
validate.py
 
 

README.md

Image classification with UniFormer

We follow LV-ViT to train our models with Token Labeling.

Model Zoo

ImageNet-1K pretrained with Token Labeling (224x224)

The followed models and logs can be downloaded on Google Drive: total_models, total_logs.

We also release the models on Baidu Cloud: total_models (p05h), total_logs (wsvi).

We follow LV-ViT to train our models with Token Labeling. Please see token_labeling for more details.

Model Top-1 #Param. FLOPs Model Log Shell
UniFormer-S 83.4 (+0.5) 22M 3.6G google google run.sh
UniFormer-S† 83.9 (+0.5) 24M 4.2G google google run.sh
UniFormer-B 85.1 (+1.3) 50M 8.3G google google run.sh
UniFormer-L+Layer Scale 85.6 100M 12.6G google google run.sh

Due to the models UniFormer-S/S†/B use head_dim=32, which cause much memory cost for downstream tasks. We re-train these models with head_dim=64. All models are trained with 224x224 resolution.

Model Top-1 #Param. FLOPs Model Log Shell
UniFormer-S 83.4 (+0.5) 22M 3.6G google google run.sh
UniFormer-S† 83.6 (+0.2) 24M 4.2G google google run.sh
UniFormer-B 84.8 (+1.0) 50M 8.3G google google run.sh

Large resolution fine-tuning (384x384)

The followed models and logs can be downloaded on Google Drive: total_models, total_logs.

We also release the models on Baidu Cloud: total_models (p05h), total_logs (wsvi).

We fine-tune the above models with Token Labeling on resolution of 384x384. Please see token_labeling for more details.

Model Top-1 #Param. FLOPs Model Log Shell
UniFormer-S 84.6 22M 11.9G google google run.sh
UniFormer-S† 84.9 24M 13.7G google google run.sh
UniFormer-B 86.0 50M 27.2G google google run.sh
UniFormer-L+Layer Scale 86.3 100M 39.2G google google run.sh

Usage

Our repository is built base on the TokenLabeling repository.

Installation

  • Clone this repo:

    git clone https://github.com/Sense-X/UniFormer.git
cd UniFormer

  • Install PyTorch 1.7.0+ and torchvision 0.8.1+

    conda install -c pytorch pytorch torchvision

  • Install other packages

    pip install timm

Download label data

For Token Labeling, we need to download the dense label map.

We provide NFNet-F6 generated dense label map in Google Drive and BaiDu Yun (password: y6j2). As NFNet-F6 are based on pure ImageNet data, no extra training data is involved.

Training

Simply run the training scripts in exp as followed:

bash ./exp/uniformer_small_tl_224/run.sh

You should set the dense label data path via --token-label-data.

Evaluation

Simply run the evaluating scripts in exp as followed:

bash ./exp/uniformer_small_tl_224/test.sh

You should set the checkpoint file path via --checkpoint.

Fine-tuning

Simply run the training scripts in exp as followed:

bash ./exp/uniformer_small_tl_384/run.sh

You should set the pretrained model file path via --finetune.

Acknowledgement

This repository is built using the timm library and the TokenLabeling repository.