All Projects → pfnet-research → chainer-ADDA

pfnet-research / chainer-ADDA

Licence: MIT license
Adversarial Discriminative Domain Adaptation in Chainer

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to chainer-ADDA

Capsnet
CapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules" - State Of the Art
Stars: ✭ 423 (+1662.5%)
Mutual labels:  chainer, mnist
bert-AAD
Adversarial Adaptation with Distillation for BERT Unsupervised Domain Adaptation
Stars: ✭ 27 (+12.5%)
Mutual labels:  adda, domain-adaptation
Nnpulearning
Non-negative Positive-Unlabeled (nnPU) and unbiased Positive-Unlabeled (uPU) learning reproductive code on MNIST and CIFAR10
Stars: ✭ 181 (+654.17%)
Mutual labels:  chainer, mnist
Cross Domain Detection
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation [Inoue+, CVPR2018].
Stars: ✭ 320 (+1233.33%)
Mutual labels:  chainer, domain-adaptation
MNIST-adversarial-images
Create adversarial images to fool a MNIST classifier in TensorFlow
Stars: ✭ 13 (-45.83%)
Mutual labels:  mnist, adversarial
deep-learning-platforms
deep-learning platforms,framework,data(深度学习平台、框架、资料)
Stars: ✭ 17 (-29.17%)
Mutual labels:  chainer
game-feature-learning
Code for paper "Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery", Ren et al., CVPR'18
Stars: ✭ 68 (+183.33%)
Mutual labels:  domain-adaptation
NumNum
Multi-digit prediction from Google Street's images using deep CNN with TensorFlow, OpenCV and Python.
Stars: ✭ 39 (+62.5%)
Mutual labels:  svhn
Natural-language-understanding-papers
NLU: domain-intent-slot; text2SQL
Stars: ✭ 77 (+220.83%)
Mutual labels:  domain-adaptation
DSTC6-End-to-End-Conversation-Modeling
DSTC6: End-to-End Conversation Modeling Track
Stars: ✭ 56 (+133.33%)
Mutual labels:  chainer
kaggle-champs-scalar-coupling
19th place solution in "Predicting Molecular Properties"
Stars: ✭ 26 (+8.33%)
Mutual labels:  chainer
transfer-learning-algorithms
Implementation of many transfer learning algorithms in Python with Jupyter notebooks
Stars: ✭ 42 (+75%)
Mutual labels:  domain-adaptation
chainer-Fast-WaveNet
A Chainer implementation of Fast WaveNet(mel-spectrogram vocoder).
Stars: ✭ 33 (+37.5%)
Mutual labels:  chainer
AdaBound-tensorflow
An optimizer that trains as fast as Adam and as good as SGD in Tensorflow
Stars: ✭ 44 (+83.33%)
Mutual labels:  mnist
deeplearning-mpo
Replace FC2, LeNet-5, VGG, Resnet, Densenet's full-connected layers with MPO
Stars: ✭ 26 (+8.33%)
Mutual labels:  mnist
keras gpyopt
Using Bayesian Optimization to optimize hyper parameter in Keras-made neural network model.
Stars: ✭ 56 (+133.33%)
Mutual labels:  mnist
BIFI
[ICML 2021] Break-It-Fix-It: Unsupervised Learning for Program Repair
Stars: ✭ 74 (+208.33%)
Mutual labels:  domain-adaptation
DRCN
Pytorch implementation of Deep Reconstruction Classification Networks
Stars: ✭ 31 (+29.17%)
Mutual labels:  domain-adaptation
ganslate
Simple and extensible GAN image-to-image translation framework. Supports natural and medical images.
Stars: ✭ 17 (-29.17%)
Mutual labels:  domain-adaptation
mnist-flask
A Flask web app for handwritten digit recognition using machine learning
Stars: ✭ 34 (+41.67%)
Mutual labels:  mnist

chainer-ADDA

Implementation of Adversarial Discriminative Domain Adaptation in Chainer.

Note this code depends on this version of Chainer (or newer). Please check out the source from that link rather than installing via pip.

Results

The following results are for the SVHN to MNIST domain adaptation task. loss

Training % accuracy (Paper) % accuracy (This implementation)
source only 0.601 0.575
ADDA 0.760 0.800

Usage

Run python train.py -g 0 to train everything using GPU 0. SVHN and MNIST datasets will download automatically. If a classifier pretrained on the source (SVHN) domain is not found, one will be trained first, then continue on to do ADDA.

Resources

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].