Machine Learning World pinned «As all you know our channel spend all money from avertisment on supporting homeless animals. Yesterday we start helping this cat https://www.facebook.com/anikishaev/posts/2331822493561951 (photo 18+) He was injured quite badly, but after surgery he is doing…»
Good article on basic of linear regresions(russian) https://m.habr.com/ru/company/ods/blog/322076/
Хабр
Базовые принципы машинного обучения на примере линейной регрессии
Здравствуйте, коллеги! Это блог открытой русскоговорящей дата саентологической ложи . Нас уже легион, точнее 2500+ человек в слаке. За полтора года мы нагенерили 800к+ сообщений (ради этого слак...
If you didn't know, there is a collection of datasets, ready to use with TF
https://github.com/tensorflow/datasets
https://github.com/tensorflow/datasets
GitHub
GitHub - tensorflow/datasets: TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ... - tensorflow/datasets
Good article on BERT architecture
https://towardsdatascience.com/breaking-bert-down-430461f60efb
https://towardsdatascience.com/breaking-bert-down-430461f60efb
Medium
Breaking BERT Down
What is BERT?
New era of float operations (russian)
https://habr.com/ru/post/462385/
https://habr.com/ru/post/462385/
Хабр
Новый подход может помочь нам избавиться от вычислений с плавающей запятой
В 1985 году Институт инженеров электротехники и электроники (IEEE) установил стандарт IEEE 754, отвечающий за форматы чисел с плавающей запятой и арифметики, к...
Reimplemented HDRNet model aka Deep Bilateral Learning for Real-Time Image Enhancements in PyTorch
https://github.com/creotiv/hdrnet-pytorch
Now you dont need to fuck you brain off compiling cuda operations in TF, and on my machine it works even faster then original implementation
https://github.com/creotiv/hdrnet-pytorch
Now you dont need to fuck you brain off compiling cuda operations in TF, and on my machine it works even faster then original implementation
GitHub
GitHub - creotiv/hdrnet-pytorch: Unofficial PyTorch implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement'…
Unofficial PyTorch implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017 https://groups.csail.mit.edu/graphics/hdrnet/ - creotiv/hdrnet-pytorch
That's fucken awesome result of Video Style Transfer https://dcgi.fel.cvut.cz/home/sykorad/ebsynth.html
dcgi.fel.cvut.cz
Stylizing Video by Example
Example of how deep fake can save the world)
https://www.youtube.com/watch?v=Y1HGgICqZ3c
https://www.youtube.com/watch?v=Y1HGgICqZ3c
YouTube
I used "deep fakes" to fix the Lion King
(YouTube has automatically flagged this video as "for kids" and disabled the comments. They have rejected all my appeals to get it turned off. Sorry guys!)
Check out the amazing fan art used here at: https://www.instagram.com/ellejart/
Made with: https://ebsynth.com/
Check out the amazing fan art used here at: https://www.instagram.com/ellejart/
Made with: https://ebsynth.com/
U-GAT-IT: new model for unpaired image-to-image translation. New SOTA in unsupervised image generation
https://arxiv.org/abs/1907.10830
https://github.com/taki0112/UGATIT
https://arxiv.org/abs/1907.10830
https://github.com/taki0112/UGATIT
Nice work on how to sync different videos
https://ai.googleblog.com/2019/08/video-understanding-using-temporal.html
https://ai.googleblog.com/2019/08/video-understanding-using-temporal.html
research.google
Video Understanding Using Temporal Cycle-Consistency Learning
Posted by Debidatta Dwibedi, Research Associate, Google Research In the last few years there has been great progress in the field of video unders...
NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data
https://arxiv.org/pdf/1908.03190.pdf
https://arxiv.org/pdf/1908.03190.pdf
JPEG Artifacts removal with Wavelet transforms
Very good result (from what i saw)
https://sci-hub.tw/10.1109/ICIEA.2006.257369
Very good result (from what i saw)
https://sci-hub.tw/10.1109/ICIEA.2006.257369
Hey guys we are on the way to building our first online course on Machin Learning and need you help to find out best fit with your interests.
Which course would you be interested in?
public poll
PyTorch Basics + CV (Object detection) – 181
👍👍👍👍👍👍👍 35%
PyTorch Basics + Audio (Shazam like app or Music Generation) – 150
👍👍👍👍👍👍 29%
DataScience Basics + Recommendation Systems – 117
👍👍👍👍👍 23%
DataScience Basics + Tabled data prediction – 47
👍👍 9%
PyTorch Basics + CV (Style Transfer) – 24
👍 5%
👥 519 people voted so far.
public poll
PyTorch Basics + CV (Object detection) – 181
👍👍👍👍👍👍👍 35%
PyTorch Basics + Audio (Shazam like app or Music Generation) – 150
👍👍👍👍👍👍 29%
DataScience Basics + Recommendation Systems – 117
👍👍👍👍👍 23%
DataScience Basics + Tabled data prediction – 47
👍👍 9%
PyTorch Basics + CV (Style Transfer) – 24
👍 5%
👥 519 people voted so far.
HYBRID OPTICAL-ELECTRONIC CONVOLUTIONAL NEURAL NETWORKS FOR IMAGE CLASSIFICATION
https://www.computationalimaging.org/publications/hybrid-optical-electronic-convolutional-neural-networks/
https://www.computationalimaging.org/publications/hybrid-optical-electronic-convolutional-neural-networks/
Our guys just got mentioned by NVidia. Congrats to VideoGorillas team https://news.developer.nvidia.com/researchers-at-videogorillas-use-ai-to-remaster-archived-content-to-4k-resolution-and-above/
NVIDIA Developer Blog
Researchers at VideoGorillas Use AI to Remaster Archived Content to 4K Resolution and Above | NVIDIA Developer Blog
To meet the growing pace of innovation, one company is developing a new AI-enhanced solution to exceed visual expectations at lower costs.