The first step is to translate the annotated dataset from source domain to target domain in an unsupervised manner. For more reference, you can find our modified training code and generating code in ./SPGAN. We wrote a detailed README. If you still has some question, feel free to contact me (dengwj16@gmail.com).
https://github.com/Simon4Yan/Learning-via-TranslationTags | person-reidentification domain-adaptation |
Implementation | Matlab |
License | MIT |
Platform |
A list of awesome papers and cool resources on transfer learning, domain adaptation and domain-to-domain translation in general! As you will notice, this list is currently mostly focused on domain adaptation (DA), but don't hesitate to suggest resources in other subfields of transfer learning. I accept pull requests. Papers are ordered by theme and inside each theme by publication date (submission date for arXiv papers). If the network or algorithm is given a name in a paper, this one is written in bold before the paper's name.
transfer-learning domain-adaptation unsupervised-learning paper awesome-listBaseline Code (with bottleneck) for Person-reID (pytorch). It is consistent with the new baseline result in Beyond Part Models: Person Retrieval with Refined Part Pooling and Camera Style Adaptation for Person Re-identification. We arrived Rank@1=88.24%, mAP=70.68% only with softmax loss.
open-reid pytorch person-reidentificationEverything about Transfer Learning and Domain Adaptation--迁移学习
transferlearning domainadaptationPytorch implementation of our method for adapting semantic segmentation from the synthetic dataset (source domain) to the real dataset (target domain). Based on this implementation, our result is ranked 3rd in the VisDA Challenge. Learning to Adapt Structured Output Space for Semantic Segmentation Yi-Hsuan Tsai*, Wei-Chih Hung*, Samuel Schulter, Kihyuk Sohn, Ming-Hsuan Yang and Manmohan Chandraker IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (spotlight) (* indicates equal contribution).
deep-learning computer-vision domain-adaptation semantic-segmentation generative-adversarial-network adversarial-learning pytorchWhat's new: Following the license on the DukeMTMC website, we added a few modifications to the license terms. You may check the license in this repo. The dataset is released only for academic research. DukeMTMC-reID [1] is a subset of the DukeMTMC dataset [2] for image-based re-identification, in the format of the Market-1501 dataset. The original dataset contains 85-minute high-resolution videos from 8 different cameras. Hand-drawn pedestrain bounding boxes are available.
person-reidentification dataset evaluation dukemtmc-reid iccv2017 person-re-identification person-reidJindong Wang et al. Transfer Learning Tutorial. 2018. 王晋东等. 迁移学习简明手册. 2018.
transfer-learning domain-adaptation[Project] [Youtube] [Paper] A research prototype developed by UC Berkeley and Adobe CTL. Latest development: [pix2pix]: Torch implementation for learning a mapping from input images to output images. [CycleGAN]: Torch implementation for learning an image-to-image translation (i.e. pix2pix) without input-output pairs. [pytorch-CycleGAN-and-pix2pix]: PyTorch implementation for both unpaired and paired image-to-image translation.
generative-adversarial-network image-manipulation computer-graphics computer-vision gan pix2pix dcgan deep-learningPyTorch implementation of StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. StarGAN can flexibly translate an input image to any desired target domain using only a single generator and a discriminator.
stargan gan image-to-image-translation pytorch generative-adversarial-network image-manipulation computer-vision neural-networksFeel free add to this via a pull request, with each section alphabetically ordered.
nmt mt neural-machine-translation machine-translation sequence-to-sequence deep-learningFelix Hieber, Tobias Domhan, Michael Denkowski, David Vilar, Artem Sokolov, Ann Clifton and Matt Post (2017): Sockeye: A Toolkit for Neural Machine Translation. In eprint arXiv:cs-CL/1712.05690.If you are interested in collaborating or have any questions, please submit a pull request or issue. You can also send questions to sockeye-dev-at-amazon-dot-com.
deep-learning deep-neural-networks mxnet machine-learning machine-translation neural-machine-translation encoder-decoder attention-mechanism sequence-to-sequence sequence-to-sequence-models sockeye attention-is-all-you-need attention-alignment-visualization attention-model seq2seq convolutional-neural-networks translationAlpha Pose is an accurate multi-person pose estimator, which is the first open-source system that achieves 70+ mAP (72.3 mAP) on COCO dataset and 80+ mAP (82.1 mAP) on MPII dataset. To match poses that correspond to the same person across frames, we also provide an efficient online pose tracker called Pose Flow. It is the first open-source online pose tracker that achieves both 60+ mAP (66.5 mAP) and 50+ MOTA (58.3 MOTA) on PoseTrack Challenge dataset. Note: Please read PoseFlow/README.md for details.
pose-estimation deep-learning iccv2017 posetracking torch computer-vision machine-learning tracking state-of-the-art gpu pytorch faster-rcnnFifteen puzzle, with its own goal-seeking to find the best solution
Neural Machine Translation with Keras (Theano and Tensorflow). for obtaining the required packages for running this library.
neural-machine-translation keras deep-learning sequence-to-sequence theano machine-learning nmt machine-translation lstm-networks gru tensorflow attention-mechanism web-demo transformer attention-is-all-you-need attention-model attention-seq2seqThis is another (work in progress) Chinese translation of Michael Nielsen's Neural Networks and Deep Learning, originally my learning notes of this free online book. It's written in LaTeX for better look and cross-referencing of math equations and plots. And I borrowed some finished work from https://github.com/tigerneil/neural-networks-and-deep-learning-zh-cn. To compile the source code to a PDF file, please make sure you have a latest TeX system installed. You can download and install a TeX distribution for your platform from http://tug.org.
This is fairseq, a sequence-to-sequence learning toolkit for Torch from Facebook AI Research tailored to Neural Machine Translation (NMT). It implements the convolutional NMT models proposed in Convolutional Sequence to Sequence Learning and A Convolutional Encoder Model for Neural Machine Translation as well as a standard LSTM-based model. It features multi-GPU training on a single machine as well as fast beam search generation on both CPU and GPU. We provide pre-trained models for English to French, English to German and English to Romanian translation. Note, there is now a PyTorch version fairseq-py of this toolkit and new development efforts will focus on it.
and all of the above can be used simultaneously to train novel and complex architectures. See the predefined models to discover how they are defined and the API documentation to customize them. Additional experimental models are available in the config/models/ directory and can be used with the option --model <model_file.py>.
neural-machine-translation tensorflow opennmt machine-translation deep-learning natural-language-processingThe Neural Monkey package provides a higher level abstraction for sequential neural network models, most prominently in Natural Language Processing (NLP). It is built on TensorFlow. It can be used for fast prototyping of sequential models in NLP which can be used e.g. for neural machine translation or sentence classification. The higher-level API brings together a collection of standard building blocks (RNN encoder and decoder, multi-layer perceptron) and a simple way of adding new building blocks implemented directly in TensorFlow.
neural-machine-translation tensorflow nlp sequence-to-sequence neural-networks nmt machine-translation mt deep-learning image-captioning encoder-decoder gpuTranslation of <Machine Learning Yearning> by Andrew NG
Tensor Comprehensions (TC) is a fully-functional C++ library to automatically synthesize high-performance machine learning kernels using Halide, ISL and NVRTC or LLVM. TC additionally provides basic integration with Caffe2 and PyTorch. We provide more details in our paper on arXiv. This library is designed to be highly portable, machine-learning-framework agnostic and only requires a simple tensor library with memory allocation, offloading and synchronization capabilities.
machine-learning domain-specific-languageThis is a Pytorch port of OpenNMT, an open-source (MIT) neural machine translation system. It is designed to be research friendly to try out new ideas in translation, summary, image-to-text, morphology, and many other domains. Codebase is relatively stable, but PyTorch is still evolving. We currently only support PyTorch 0.4 and recommend forking if you need to have stable code.
deep-learning pytorch machine-translation neural-machine-translation
We have large collection of open source products. Follow the tags from
Tag Cloud >>
Open source products are scattered around the web. Please provide information
about the open source projects you own / you use.
Add Projects.