A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation(DANN), support Office-31 and Office-Home dataset

Last update: Apr 16, 2022

Related tags

Deep Learning DANN-pytorch

Overview

DANN

A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation

Prerequisites

Linux or OSX

NVIDIA GPU + CUDA (may CuDNN) and corresponding PyTorch framework (version 0.3.1)

Python 2.7/3.5

Datasets

This responsity support Office-31 and Office-Home dataset

cd src
python train_DANN.py --gpu_id 0 --net ResNet50 --dset office --s_dset_path ../data/office/webcam_31_list.txt --t_dset_path ../data/office/amazon_31_list.txt --test_interval 500 --snapshot_interval 5000 --output_dir dann

You can set the command parameters to switch between different experiments. 
- "gpu_id" is the GPU ID to run experiments.
- "dset" parameter is the dataset selection. In our experiments, it can be "office" (for all the Office-31 tasks), "office-home" (for all the Office-Home tasks)
- "s_dset_path" is the source dataset list.
- "t_dset_path" is the target dataset list.
- "test_interval" is the interval of iterations between two test phase.
- "snapshot_interval" is the interval of iterations between two snapshot models.
- "output_dir" is the output directory of the log and snapshot.
- "net" sets the base network. For details of setting, you can see network.py.
    - For AlexNet, "net" is AlexNet.
    - For VGG, "net" is like VGG16. Detail names are in network.py.
    - For ResNet, "net" is like ResNet50. Detail names are in network.py.

A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation(DANN), support Office-31 and Office-Home dataset

Related tags

Overview

DANN

Prerequisites

Datasets

Owner

Semi-supervised Domain Adaptation via Minimax Entropy

This repository contains the implementation of the paper Contrastive Instance Association for 4D Panoptic Segmentation using Sequences of 3D LiDAR Scans

Continual World is a benchmark for continual reinforcement learning

This is the official pytorch implementation of AutoDebias, an automatic debiasing method for recommendation.

The repository offers the official implementation of our paper in PyTorch.

An Efficient Training Approach for Very Large Scale Face Recognition or F²C for simplicity.

Predicting Student Attentiveness using OpenCV

[NeurIPS'21] Projected GANs Converge Faster

Code for the ICCV 2021 Workshop paper: A Unified Efficient Pyramid Transformer for Semantic Segmentation.

NeRD: Neural Reflectance Decomposition from Image Collections

Cortex-compatible model server for Python and TensorFlow

Object detection and instance segmentation toolkit based on PaddlePaddle.

A collection of semantic image segmentation models implemented in TensorFlow

HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

QTool: A Low-bit Quantization Toolbox for Deep Neural Networks in Computer Vision

Code for unmixing audio signals in four different stems "drums, bass, vocals, others". The code is adapted from "Jukebox: A Generative Model for Music"

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.

Chatbot in 200 lines of code using TensorLayer

Simulating Sycamore quantum circuits classically using tensor network algorithm.

This repo contains the implementation of YOLOv2 in Keras with Tensorflow backend.

A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation(DANN), support Office-31 and Office-Home dataset

Related tags

Overview

DANN

Prerequisites

Datasets

Owner

Semi-supervised Domain Adaptation via Minimax Entropy

This repository contains the implementation of the paper Contrastive Instance Association for 4D Panoptic Segmentation using Sequences of 3D LiDAR Scans

Continual World is a benchmark for continual reinforcement learning

This is the official pytorch implementation of AutoDebias, an automatic debiasing method for recommendation.

The repository offers the official implementation of our paper in PyTorch.

An Efficient Training Approach for Very Large Scale Face Recognition or F²C for simplicity.

Predicting Student Attentiveness using OpenCV

[NeurIPS'21] Projected GANs Converge Faster

Code for the ICCV 2021 Workshop paper: A Unified Efficient Pyramid Transformer for Semantic Segmentation.

NeRD: Neural Reflectance Decomposition from Image Collections

Cortex-compatible model server for Python and TensorFlow

Object detection and instance segmentation toolkit based on PaddlePaddle.

A collection of semantic image segmentation models implemented in TensorFlow

HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

QTool: A Low-bit Quantization Toolbox for Deep Neural Networks in Computer Vision

Code for unmixing audio signals in four different stems "drums, bass, vocals, others". The code is adapted from "Jukebox: A Generative Model for Music"

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing.

Chatbot in 200 lines of code using TensorLayer

Simulating Sycamore quantum circuits classically using tensor network algorithm.

This repo contains the implementation of YOLOv2 in Keras with Tensorflow backend.

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.