Pytorch implementation of Domain-Specific Batch Normalization for Unsupervised Domain Adaptation (CVPR2019).
If you want to cite our work, follow the link arXiv.
We recommand to create conda virtualenv nameded pytorch-py36
conda create -n pytorch-py36 python=3.6
source activate pytorch-py36-
Install PyTorch 1.3 with Python3.6, cuda10.1
-
Install other dependencies
conda install numpy scipy matplotlib cython h5py
conda install -c menpo opencv- For visualization using tensorboard
pip install tensorboardX
pip install tensorflow- For color log print
pip install coloredlogsdata directory looks like below:
data
├── Office
│ └── domain_adaptation_images
│ ├── amazon
│ ├── dslr
│ └── webcam
├── Office-home
│ └── OfficeHomeDataset_10072016
│ ├── Art
│ ├── Clipart
│ ├── Product
│ └── RealWorld
└── VisDA
├── test
├── train
└── validation
Datasets links to download.
- Refer this site and download the dataset.
- Download from here
- Download from here. Change domain name from "Real World" to "RealWorld" (Remove space between two words).
This is a example script for training MSTN on visda 2017 dataset for stage1. Use resnet101dsbn for resnet101 with domain-specific batchnorm
# DSCN
python trainval_multi.py --model-name resnet101dsbn --exp-setting visda --sm-loss --adv-loss --source-datasets train --target-datasets validation --batch-size 40 --save-dir output/resnet101dsbn_visda_stage1 --print-console
# cf. batchnorm
python trainval_multi.py --model-name resnet101 --exp-setting visda --sm-loss --adv-loss --source-datasets train --target-datasets validation --batch-size 40 --save-dir output/resnet101_visda_stage1 --print-consoleAfter training you can get stage1 model at save-dir.
For stage1, use finetune for single source unsupervised domain adaptation, and finetune_multi for multi source setting.
This is a example script for training MSTN on visda 2017 dataset for stage2.
# DSCN
python finetune_multi.py --model-name resnet101dsbn --exp-setting visda --source-dataset train --target-dataset validation --pseudo-target-loss default_ensemble --no-lambda --teacher-model-path output/resnet101dsbn_visda_stage1/best_resnet101dsbn+None+i0_train2validation.pth --learning-rate 5e-5 --batch-size 40 --save-dir output/resnet101dsbn_visda_stage2 --print-console
# cf. batchnorm
python finetune_multi.py --model-name resnet101 --exp-setting visda --source-dataset train --target-dataset validation --pseudo-target-loss default_ensemble --no-lambda --teacher-model-path output/resnet101_visda_stage1/best_resnet101+None+i0_train2validation.pth --learning-rate 5e-5 --batch-size 40 --save-dir output/resnet101_visda_stage2 --print-consolepython evlauate_multi.py --model-path [model-path] # for multi-source settingFile name should follow the format: "best_{model_name}+{jitter}+{infeatures}_{source_dataset}2{target_dataset}.pth"
example: best_resnet101dsbn+None+i0_train2validation.pth
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent