St Petersburg, Russia, 75 year after Victory in WWII celebration. Drone show

​​pytorch lightning bolts
from linear, logistic regression on tpu-s to pre-trained gan-s

plb – is a collection of pytorch lightning implementations of popular models that are well tested and optimized for speed on multiple gpu-s and tpu-s

it is a new community built dl research and production toolbox, featuring a collection of well established and sota models and components, pre-trained weights, callbacks, loss functions, data sets, and data modules

everything is implemented in lightning and tested benchmarked, documented, and works on cpu-s, tpu-s, gpu-s, and 16-bit precision

more u can read at the blog post


github: https://github.com/PyTorchLightning/pytorch-lightning-bolts

#pytorchlightning #bolts #multiple

TensorBoard is a tool for providing the measurements and visualizations needed during the machine learning workflow. It enables tracking experiment metrics like loss and accuracy, visualizing the model graph, projecting embeddings to a lower dimensional space, and much more.

#ts, #python, #tensorflow, #machine, #learning, #visualization

Understanding the Role of Individual Units in a Deep Neural Network

Examine two types of networks that contain interpretable units: networks trained to classify images of scenes, and networks trained to synthesize images of scenes.

https://dissect.csail.mit.edu/

Github: https://github.com/davidbau/dissect

Website: https://www.pnas.org/content/early/2020/08/31/1907375117

Paper: https://arxiv.org/pdf/2009.05041.pdf

Silero Speech-To-Text Models V1 Released

We are proud to announce that we have released our high-quality (i.e. on par with premium Google models) speech-to-text Models for the following languages:

- English
- German
- Spanish

Why this is a big deal:

- STT Research is typically focused on huge compute budgets
- Pre-trained models and recipes did not generalize well, were difficult to use even as-is, relied on obsolete tech
- Until now STT community lacked easy to use high quality production grade STT models

How we solve it:

- We publish a set of pre-trained high-quality models for popular languages
- Our models are embarrassingly easy to use
- Our models are fast and can be run on commodity hardware

Even if you do not work with STT, please give us a star / share!

Links

- https://github.com/snakers4/silero-models

Caffe is a deep learning framework made with expression, speed, and modularity in mind.

#cpp, #dl, #deep, #learning, #framework

🔋 The Most Complete Guide to PyTorch for Data Scientists

https://www.kdnuggets.com/2020/09/most-complete-guide-pytorch-data-scientists.html

Code: https://github.com/MLWhiz/data_science_blogs/tree/master/pytorch_guide

@ai_machinelearning_big_data

Ignite is a high-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Ignite is a library that provides three high-level features:

- Extremely simple engine and event system
- Out-of-the-box metrics to easily evaluate models
- Built-in handlers to compose training pipeline, save artifacts and log parameters and metrics

#python, #pytorch, #ml, #neural, #network

KeenWrite: An Open Source Text Editor for Data Scientists
https://itsfoss.com/keenwrite/

Introduction to Pytorch Code Examples

An overview of training, models, loss functions and optimizers

Free course: https://cs230.stanford.edu/blog/pytorch/

Lectures: https://cs230.stanford.edu/lecture/

Github: https://github.com/thanhhff/CS230-Deep-Learning

@ai_machinelearning_big_data

Graph-based Neural Structured Learning in TFX

New learning paradigm to train neural networks by leveraging structured signals in addition to feature inputs.

https://www.tensorflow.org/tfx/tutorials/tfx/neural_structured_learning

Article: https://blog.tensorflow.org/2020/10/neural-structured-learning-in-tfx.html

Neural Structured Learning: https://www.tensorflow.org/neural_structured_learning

Github: https://github.com/tensorflow/neural-structured-learning#videos-and-colab-tutorials

@ai_machinelearning_big_data

Open cool NOT Kaggle contest – AIJ Contest 2020 🎉

◼️ Digital Peter: Recognition of Peter the Great’s manuscripts
October 9 – November 8
Digital Peter is an educational task with a historical slant created on the basis of several AI technologies (CV, NLP, and knowledge graphs). The task was prepared jointly with the Saint Petersburg Institute of History of the Russian Academy of Sciences, Federal Archival Agency of Russia and the Russian State Archive of Ancient Acts.
Participants are invited to create an algorithm for line-by-line recognition of manuscripts written by Peter the Great.

◼️ NoFloodWithAI: Flash floods on the Amur river
October 9 – November 1
NoFloodWithAI is a special track with a socially important theme prepared jointly with the Ministry of Emergency Situations, Ministry of Natural Resources and Rosgidromet of Russia.
Participants are invited to develop an algorithm for short-term forecasting of water levels in the Amur River for the following settlements: Dzhalinda, Blagoveshchensk, Innokentievka, Leninskoye, Khabarovsk, Komsomolsk-on-Amur, Nikolaevsk-on-Amur for 10 days in advance in order to prevent emergency situations in Russia’s regions. The results of the contest will be reused to mitigate environmental risks and minimize economic damage wrought on the regions.


◼️ AI4Humanities: ruGPT-3
October 16 – November 1
It is a track developed especially for those familiar with artificial neural networks. It will help to learn about a promising ruGPT-3 technology able to generate very complex meaningful texts based on just one request made in natural human language. For example, it can help you answer most questions included in basic or unified national exams (OGE or EGE), write Java code at the request "Please make a website for the online shop", come up with a business idea for a new startup, or write new popular science articles.


more on the project page: https://ods.ai/tracks/aij2020

#ods #aij #contest #peter #floods #rugpt3

Free course: Deep Learning with Pytorch by Yann LeCun

En: https://atcold.github.io/pytorch-Deep-Learning

Ru: https://atcold.github.io/pytorch-Deep-Learning/ru/

GitHub: https://github.com/Atcold/pytorch-Deep-Learning

YouTube: https://www.youtube.com/playlist?list=PLLHTzKZzVU9eaEyErdV26ikyolxOsz6mq

@ai_machinelearning_big_data