Tensor Comprehensions in PyTorch
http://pytorch.org/2018/03/05/tensor-comprehensions.html
http://pytorch.org/2018/03/05/tensor-comprehensions.html
Новое на Distill: The Building Blocks of Interpretability
https://distill.pub/2018/building-blocks/
https://distill.pub/2018/building-blocks/
Distill
The Building Blocks of Interpretability
Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them -- and the rich structure of this combinatorial space.
A collection of research directions around transfer learning and NLP
http://ruder.io/requests-for-research/
http://ruder.io/requests-for-research/
ruder.io
Requests for Research
It can be hard to find compelling topics to work on and know what questions to ask when you are just starting as a researcher. This post aims to provide inspiration and ideas for research directions to junior researchers and those trying to get into research.
Щи или распознавание 330 млн лиц на скорости 400 фото / сек
https://habrahabr.ru/company/odnoklassniki/blog/350566/
https://habrahabr.ru/company/odnoklassniki/blog/350566/
Habr
Щи, или Распознавание 330 млн лиц на скорости 400 фото / сек
Распознаванием лиц в 2018 году никого не удивишь – каждый студент, может, даже школьник, его делал. Но всё становится немного сложнее, когда у вас не датасет на 1 млн пользователей, а:
330...
330...
Первые шаги в Машинном обучении
https://habrahabr.ru/post/350984/
https://habrahabr.ru/post/350984/
Habr
Первые шаги в машинном обучении
Привет, дорогой друг, ты всегда хотел попробовать машинное обучение, но область выглядела загадочно и сложно? Я хотел бы поделиться с тобой моей историей как я сделал первые шаги в машинном обучении,...
Semantic Image Segmentation with DeepLab in Tensorflow
https://research.googleblog.com/2018/03/semantic-image-segmentation-with.html
https://research.googleblog.com/2018/03/semantic-image-segmentation-with.html
blog.research.google
Semantic Image Segmentation with DeepLab in TensorFlow
Weakly supervised learning of linear boundary
https://github.com/4d55397500/learning-scraps/tree/master/mitr
https://github.com/4d55397500/learning-scraps/tree/master/mitr
GitHub
4d55397500/learning-scraps
learning-scraps - low-level learning scraps
Plain python implementations of basic machine learning algorithms
https://github.com/zotroneneis/machine_learning_basics
https://github.com/zotroneneis/machine_learning_basics
GitHub
GitHub - zotroneneis/machine_learning_basics: Plain python implementations of basic machine learning algorithms
Plain python implementations of basic machine learning algorithms - zotroneneis/machine_learning_basics
Made a graph of nearest neighbors from word2vec embeddings. What do you think?
https://github.com/anvaka/word2vec-graph
https://github.com/anvaka/word2vec-graph
GitHub
GitHub - anvaka/word2vec-graph: Exploring word2vec embeddings as a graph of nearest neighbors
Exploring word2vec embeddings as a graph of nearest neighbors - anvaka/word2vec-graph
PyTorch Implementation of the "Magnet Loss": Metric Learning with Adaptive Density Discrimination from Facebook AI Research
https://github.com/vithursant/MagnetLoss-PyTorch
https://github.com/vithursant/MagnetLoss-PyTorch
GitHub
GitHub - vithursant/MagnetLoss-PyTorch: PyTorch implementation of a deep metric learning technique called "Magnet Loss" from Facebook…
PyTorch implementation of a deep metric learning technique called "Magnet Loss" from Facebook AI Research (FAIR) in ICLR 2016. - vithursant/MagnetLoss-PyTorch
Implementation of "Independently Recurrent Neural Network (IndRNN)" in TensorFlow
https://github.com/batzner/indrnn
https://github.com/batzner/indrnn
GitHub
GitHub - batzner/indrnn: TensorFlow implementation of Independently Recurrent Neural Networks
TensorFlow implementation of Independently Recurrent Neural Networks - batzner/indrnn
Pytorch implementation for Snapshot Ensemble with SGDR
http://jsideas.net/python/2018/03/14/snapshot_ensemble.html
http://jsideas.net/python/2018/03/14/snapshot_ensemble.html
Pytorch implementations of deep person re-identification models (pre-trained models available)
https://github.com/KaiyangZhou/deep-person-reid
https://github.com/KaiyangZhou/deep-person-reid
GitHub
GitHub - KaiyangZhou/deep-person-reid: Torchreid: Deep learning person re-identification in PyTorch.
Torchreid: Deep learning person re-identification in PyTorch. - KaiyangZhou/deep-person-reid
livelossplot - Live training loss plot in Jupyter Notebook for Keras, PyTorch and others
https://github.com/stared/livelossplot
https://github.com/stared/livelossplot
GitHub
GitHub - stared/livelossplot: Live training loss plot in Jupyter Notebook for Keras, PyTorch and others
Live training loss plot in Jupyter Notebook for Keras, PyTorch and others - stared/livelossplot
GAN with Keras: Application to Image Deblurring
https://blog.sicara.com/keras-generative-adversarial-networks-image-deblurring-45e3ab6977b5
https://blog.sicara.com/keras-generative-adversarial-networks-image-deblurring-45e3ab6977b5
How I built a style transfer website that runs (mostly) serverless. Happy to discuss how the sausage is made and would love to hear how others would have built something like this.
https://rodrigo.red/blog/style-transfer-sass/
https://rodrigo.red/blog/style-transfer-sass/
rodrigo.red
Style Transfer as a Service
Picmatix.com is an online tool that creates digital art by transferring styles to user pictures. This blog post outlines the serverless architecture that powers the website.