Skip to content

Official pytorch implement for “Transformer-Based Source-Free Domain Adaptation”

Notifications You must be signed in to change notification settings

ygjwd12345/TransDA

Repository files navigation

Official implementation for TransDA

Official pytorch implement for “Transformer-Based Source-Free Domain Adaptation”. Accepted by APIN 2022

Overview:

Result:

Prerequisites:

  • python == 3.6.8
  • pytorch ==1.1.0
  • torchvision == 0.3.0
  • numpy, scipy, sklearn, PIL, argparse, tqdm

Prepare pretrain model

We choose R50-ViT-B_16 as our encoder.

wget https://storage.googleapis.com/vit_models/imagenet21k/R50+ViT-B_16.npz 
mkdir ./model/vit_checkpoint/imagenet21k 
mv R50+ViT-B_16.npz ./model/vit_checkpoint/imagenet21k/R50+ViT-B_16.npz

Our checkpoints could be find in Dropbox

Dataset:

  • Please manually download the datasets Office, Office-Home, VisDA, Office-Caltech from the official websites, and modify the path of images in each '.txt' under the folder './data/'.
  • The script "download_visda2017.sh" in data fold also can use to download visda

Training

Office-31

```python
sh run_office_uda.sh
```

Office-Home

```python
sh run_office_home_uda.sh
```

Office-VisDA

```python
sh run_visda.sh
```

Reference

ViT

TransUNet

SHOT

About

Official pytorch implement for “Transformer-Based Source-Free Domain Adaptation”

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published