Alibaba Open-Sourced Mars Framework for Numpy like distributed computation based on Tensorflow. Looks interesting, but not tried yet.
https://github.com/mars-project/mars
https://github.com/mars-project/mars
GitHub
GitHub - mars-project/mars: Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas…
Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions. - mars-project/mars
We are making course on Object Detection with PyTorch. For course you need to know python and have basic skills in ML and convolution networks.
If you are interested please leave you email and we will ping you when it will be ready https://upscri.be/vg7ilp
If you are interested please leave you email and we will ping you when it will be ready https://upscri.be/vg7ilp
Fresh Kaggle on 3D object Detection for autonomous cars
https://www.kaggle.com/c/3d-object-detection-for-autonomous-vehicles/
https://www.kaggle.com/c/3d-object-detection-for-autonomous-vehicles/
HuggingFace has ported their very popular Transformer library to TensorFlow 2.0 / Keras / PyTorch.
https://github.com/huggingface/transformers
https://github.com/huggingface/transformers
GitHub
GitHub - huggingface/transformers: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models…
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. - GitHub - huggingface/t...
https://movement.uber.com Just include Kyiv in their service. Now you can access their data about speed on streets of Kyiv at any time for free
How about a real step-by-step tutorial on very realistic fake news comments generation?
https://arxiv.org/pdf/1909.11974.pdf
https://arxiv.org/pdf/1909.11974.pdf
Tensorflow 2.0 released. But i still recommend PyTorch :)
https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab
https://medium.com/tensorflow/tensorflow-2-0-is-now-available-57d706c2a9ab
Medium
TensorFlow 2.0 is now available!
Earlier this year, we announced TensorFlow 2.0 in alpha at the TensorFlow Dev Summit. Today, we’re delighted to announce that the final…
Awesome overview article on Computation Photography (russian) https://vas3k.ru/blog/computational_photography/
vas3k.blog
Вычислительная Фотография
На презентациях любого смартфона сегодня отдельное место уделяют успехе его камеры. Pixel научился снимать в полной темноте, Huawei зумит лучше бинокля, Samsung получил восемь объективов, а в iPhone ваши друзья выглядят на 30% богаче.
Greate paper on controllable speach generation
https://google.github.io/tacotron/publications/semisupervised_generative_modeling_for_controllable_speech_synthesis/
https://google.github.io/tacotron/publications/semisupervised_generative_modeling_for_controllable_speech_synthesis/
We are building totally new course on Computer Vision to give you the best of our expertise in this area. 100% of theory in course will be showed on practical stuff, to give you understanding how it works in real life. All models will be built and trained from scratch.
Our course consist from:
- PyTorch Basics
- Single Object Localisation
- Multi-object detection with One Shot Detection models. Yolo
- Multi-object detection with One Shot Detection models. SSD
- Multi-object detection with Regional models. Fast-RCNN
- Multi-object detection with Regional models. Mask-RCNN
Subscribe and we will let you know when it will be ready
https://upscri.be/vg7ilp
Our course consist from:
- PyTorch Basics
- Single Object Localisation
- Multi-object detection with One Shot Detection models. Yolo
- Multi-object detection with One Shot Detection models. SSD
- Multi-object detection with Regional models. Fast-RCNN
- Multi-object detection with Regional models. Mask-RCNN
Subscribe and we will let you know when it will be ready
https://upscri.be/vg7ilp
Siraj Raval was not only stealing money from subscribers, but also stealing papers and post them as his own. Guys like this should be banned from community.
https://twitter.com/AndrewM_Webb/status/1183150368945049605?s=19
https://twitter.com/AndrewM_Webb/status/1183150368945049605?s=19
Twitter
Andrew M. Webb
So in @sirajraval's livestream yesterday he mentioned his 'recent neural qubit paper'. I've found that huge chunks of it are plagiarised from a paper by Nathan Killoran, Seth Lloyd, and co-authors. E.g., in the attached images, red is Siraj, green is original
Guys just solved Generalized inverse FFT. Congrats!
https://techxplore.com/news/2019-10-year-old-puzzle.html
https://www.nature.com/articles/s41598-019-50234-9
https://techxplore.com/news/2019-10-year-old-puzzle.html
https://www.nature.com/articles/s41598-019-50234-9
Tech Xplore
Engineers solve 50-year-old puzzle in signal processing
Something called the fast Fourier transform is running on your cell phone right now. The FFT, as it is known, is a signal-processing algorithm that you use more than you realize. It is, according to the ...
Ребята, напоминаю что уже в эту субботу 19го числа в Киеве пройдет Data Science UA Conference - самая движовая конфа по DS/ML в стране.
Будет множество крутых спикеров, два бомбезных воркшопа по реконструкции 3D сцены с Pytorch и Unsupervised image alignment(крайне полезная штука для видео), и море крутых спецов и компаний с которыми можно запартнериться да и просто весело потусить)
Билетики можно купить тут: https://bit.ly/2m31Epd
(с промокодом Nikishaev - скидка 10%)
ЗЫ: Мы тоже идем, так что рад буду всех увидить и обсудить насущные боли наши и страдания. Если кто не знает в данный момент мы делаем риал-тайм обучающий движек для игр типа LoL, DOTA, CS:GO. Так что СV, рекомендационные системы, да и в целом обучение это к нам. Ищите парня в зеленом килте и громко говорящего - это я. До встречки :)
Будет множество крутых спикеров, два бомбезных воркшопа по реконструкции 3D сцены с Pytorch и Unsupervised image alignment(крайне полезная штука для видео), и море крутых спецов и компаний с которыми можно запартнериться да и просто весело потусить)
Билетики можно купить тут: https://bit.ly/2m31Epd
(с промокодом Nikishaev - скидка 10%)
ЗЫ: Мы тоже идем, так что рад буду всех увидить и обсудить насущные боли наши и страдания. Если кто не знает в данный момент мы делаем риал-тайм обучающий движек для игр типа LoL, DOTA, CS:GO. Так что СV, рекомендационные системы, да и в целом обучение это к нам. Ищите парня в зеленом килте и громко говорящего - это я. До встречки :)