bruinxiong / transfer-learning-library

Transfer-Learning-Library

Introduction

Trans-Learn is an open-source and well-documented library for Transfer Learning. It is based on pure PyTorch with high performance and friendly API. Our code is pythonic, and the design is consistent with torchvision. You can easily develop new algorithms, or readily apply existing algorithms.

On July 24th, 2020, we released the v0.1 (preview version), the first sub-library is for Domain Adaptation (DALIB). The currently supported algorithms include:

• Domain Adversarial Neural Network (DANN)
• Deep Adaptation Network (DAN)
• Joint Adaptation Network (JAN)
• Conditional Domain Adversarial Network (CDAN)
• Maximum Classifier Discrepancy (MCD)
• Margin Disparity Discrepancy (MDD)

The performance of these algorithms were fairly evaluated in this benchmark.

Installation

DALIB is currently hosted on PyPI. It requires Python >= 3.6. You can simply install dalib with the following command:

pip install dalib

You can also install with the newest version through GitHub:

pip install git+https://github.com/thuml/Transfer-Learning-Library.git@master

After installation, open your python console and type the following. If no error occurs, you have successfully installed DALIB.

import dalib 
print(dalib.__version__)

For flexible use and modification, git clone the library is also a good choice.

Documentation

You can find the tutorial and API documentation on the website: DALIB API

Also, we have examples in the directory examples. A typical usage is

# Train a DANN on Office-31 Amazon -> Webcam task using ResNet 50.
# Assume you have put the datasets under the path `data/office-31`, 
# or you are glad to download the datasets automatically from the Internet to this path
python examples/dann.py data/office31 -d Office31 -s A -t W -a resnet50  --epochs 20

In the directory examples, you can find all the necessary running scripts to reproduce the benchmarks with specified hyper-parameters.

Contributing

We appreciate all contributions. If you are planning to contribute back bug-fixes, please do so without any further discussion. If you plan to contribute new features, utility functions or extensions, please first open an issue and discuss the feature with us.

Disclaimer on Datasets

This is a utility library that downloads and prepares public datasets. We do not host or distribute these datasets, vouch for their quality or fairness, or claim that you have licenses to use the dataset. It is your responsibility to determine whether you have permission to use the dataset under the dataset's license.

If you're a dataset owner and wish to update any part of it (description, citation, etc.), or do not want your dataset to be included in this library, please get in touch through a GitHub issue. Thanks for your contribution to the ML community!

Contact

If you have any problem with our code or have some suggestions, including the future feature, feel free to contact

• Junguang Jiang ([email protected])
• Bo Fu ([email protected])
• Mingsheng Long ([email protected])

or describe it in Issues.

Citation

If you use this toolbox or benchmark in your research, please cite this project.

@misc{dalib,
  author = {Junguang Jiang, Bo Fu, Mingsheng Long},
  title = {Transfer-Learning-library},
  year = {2020},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/thuml/Transfer-Learning-Library}},
}