Data Science by ODS.ai 🦜
49.6K subscribers
407 photos
43 videos
7 files
1.55K links
First Telegram Data Science channel. Covering all technical and popular staff about anything related to Data Science: AI, Big Data, Machine Learning, Statistics, general Math and the applications of former. To reach editors contact: @haarrp
Download Telegram
​​Neighbourhood Components Analysis
a PyTorch implementation of Neighbourhood Components Analysis

NCA learns a linear transformation of the dataset such that the expected leave-one-out performance of kNN in the transformed space is maximized.

The authors propose a novel method for learning a Mahalanobis distance measure to be used in the KNN classification algorithm. The algorithm directly maximizes a stochastic variant of the leave-one-out KNN score on the training set.

It can also learn low-dimensional linear embedding of labeled data that can be used for data visualization and fast classification. Unlike other methods, this classification model is non-parametric, making no assumptions about the shape of the class distributions or the boundaries between them.

The performance of the method is demonstrated on several data sets, both for metric learning and linear dimensionality reduction.

paper (only pdf): https://www.cs.toronto.edu/~hinton/absps/nca.pdf
github: https://github.com/kevinzakka/nca

#kNN #pca #nca #PyTorch
​​StarGAN v2 code release on GitHub

The better news is if you put a human into the animal model you do in fact get out a feline version of the human, and it's even wearing a suit.

GitHub: https://github.com/clovaai/stargan-v2
ArXiV: https://arxiv.org/abs/1912.01865
YouTube: https://www.youtube.com/watch?v=0EVh5Ki4dIY&feature=youtu.be

#GAN #StarGAN #PyTorch
Live U-Net implementation online session today

Famous Abhishek Thakur (First 4x GM on Kaggle) is going to show you how to implement the original U-Net with #PyTorch.

Session starts in 4 hours from now (at 6PM CET / 9.30PM IST), make sure you turned the notifications on if you are interested.

YouTube Link: https://www.youtube.com/watch?v=u1loyDCoGbE

#Livecoding #Unet
​​ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network

The authors propose a set of design principles that improves model performance significantly based on the analysis of representation bottlenecks.

Authors think that commonly used architectures have a representation bottleneck and try to fix it by expanding channel size, using more expand layers, and better activation functions. This also improves the performance of models on ImageNet and good results on transfer learning on classification and object detection.
Authors hope that their design ideas could be used by NAS to create even better models.


Paper: https://arxiv.org/abs/2007.00992
Code: https://github.com/clovaai/rexnet

#deeplearning #pretraining #transferlearning #computervision #pytorch
​​Funnel Activation for Visual Recognition

Authors offer a new activation function for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by adding a negligible overhead of spatial condition.

Extensive experiments on COCO, ImageNet and CityScape show significant improvement and robustness.


Paper: https://arxiv.org/abs/2007.11824
Code: https://github.com/megvii-model/FunnelAct

#deeplearning #activationfunction #computervision #pytorch
πŸ₯Self-supervised Learning for Medical images

Due to standard imaging procedures, medical images (X-ray, CT scans, etc) are usually well aligned.
This paper gives an opportunity to utilize such an alignment to automatically connect similar pairs of images for training.

GitHub: https://github.com/fhaghighi/TransVW
ArXiV: https://arxiv.org/abs/2102.10680

#biolearning #medical #dl #pytorch #keras
🦜 Hi!

We are the first Telegram Data Science channel.


Channel was started as a collection of notable papers, news and releases shared for the members of Open Data Science (ODS) community. Through the years of just keeping the thing going we grew to an independent online Media supporting principles of Free and Open access to the information related to Data Science.


Ultimate Posts

* Where to start learning more about Data Science. https://github.com/open-data-science/ultimate_posts/tree/master/where_to_start
* @opendatascience channel audience research. https://github.com/open-data-science/ods_channel_stats_eda


Open Data Science

ODS.ai is an international community of people anyhow related to Data Science.

Website: https://ods.ai



Hashtags

Through the years we accumulated a big collection of materials, most of them accompanied by hashtags.

#deeplearning #DL β€” post about deep neural networks (> 1 layer)
#cv β€” posts related to Computer Vision. Pictures and videos
#nlp #nlu β€” Natural Language Processing and Natural Language Understanding. Texts and sequences
#audiolearning #speechrecognition β€” related to audio information processing
#ar β€” augmeneted reality related content
#rl β€” Reinforcement Learning (agents, bots and neural networks capable of playing games)
#gan #generation #generatinveart #neuralart β€” about neural artt and image generation
#transformer #vqgan #vae #bert #clip #StyleGAN2 #Unet #resnet #keras #Pytorch #GPT3 #GPT2 β€” related to special architectures or frameworks
#coding #CS β€” content related to software engineering sphere
#OpenAI #microsoft #Github #DeepMind #Yandex #Google #Facebook #huggingface β€” hashtags related to certain companies
#productionml #sota #recommendation #embeddings #selfdriving #dataset #opensource #analytics #statistics #attention #machine #translation #visualization


Chats

- Data Science Chat https://t.me/datascience_chat
- ODS Slack through invite form at website

ODS resources

* Main website: https://ods.ai
* ODS Community Telegram Channel (in Russian): @ods_ru
* ML trainings Telegram Channel: @mltrainings
* ODS Community Twitter: https://twitter.com/ods_ai

Feedback and Contacts

You are welcome to reach administration through telegram bot: @opendatasciencebot
​​Segment Anything

The Segment Anything project aims to democratize image segmentation in computer vision, a core task used across various applications such as scientific imagery analysis and photo editing. Traditionally, accurate segmentation models require specialized expertise, AI training infrastructure, and large amounts of annotated data. This project introduces a new task, dataset, and model for image segmentation to overcome these challenges and make segmentation more accessible.

The researchers are releasing the Segment Anything Model (SAM) and the Segment Anything 1-Billion mask dataset (SA-1B), the largest segmentation dataset to date. These resources will enable a wide range of applications and further research into foundational models for computer vision. The SA-1B dataset is available for research purposes, while the SAM is provided under the permissive Apache 2.0 open license. Users can explore the demo to try SAM with their own images.

Paper link: https://arxiv.org/abs/2304.02643

Code link: https://github.com/facebookresearch/segment-anything

Demo link: https://segment-anything.com/demo

Blogpost link: https://ai.facebook.com/blog/segment-anything-foundation-model-image-segmentation/

Dataset link: https://ai.facebook.com/datasets/segment-anything/

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-sam

#deeplearning #cv #pytorch #imagesegmentation #dataset
​​DINOv2: Learning Robust Visual Features without Supervision

Get ready for a game-changer in computer vision! Building on the groundbreaking achievements in natural language processing, foundation models are revolutionizing the way we use images in various systems. By generating all-purpose visual features that excel across diverse image distributions and tasks without finetuning, these models are set to redefine the field.

The researchers behind this work have combined cutting-edge techniques to scale pretraining in terms of data and model size, turbocharging the training process like never before. They've devised an ingenious automatic pipeline to create a rich, diverse, and curated image dataset, setting a new standard in the self-supervised literature. To top it off, they've trained a colossal ViT model with a staggering 1 billion parameters and distilled it into a series of smaller, ultra-efficient models. These models outshine the best available all-purpose features, OpenCLIP, on most benchmarks at both image and pixel levels.

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-dinov2

Project link: https://dinov2.metademolab.com/
#deeplearning #cv #pytorch #imagesegmentation #sota #pretraining
Forwarded from Machinelearning
βœ”οΈ БСсплатныС ΠΏΠΎΠ»Π΅Π·Π½Ρ‹Π΅ руководства ΠΏΠΎ дистилляции ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ:

1. Руководство ΠΏΠΎ дистилляции ΠΎΡ‚ OpenAI πŸ–₯

Руководство содСрТит ΠΏΠΎΠ΄Ρ€ΠΎΠ±Π½ΠΎΠ΅ описаниС процСсса ΠΏΠ΅Ρ€Π΅Π΄Π°Ρ‡ΠΈ Π·Π½Π°Π½ΠΈΠΉ ΠΎΡ‚ Π±ΠΎΠ»Π΅Π΅ ΠΊΡ€ΡƒΠΏΠ½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΠΈ ΠΊ ΠΊΠΎΠΌΠΏΠ°ΠΊΡ‚Π½ΠΎΠΉ, c сохранСниСм высокой ΠΏΡ€ΠΎΠΈΠ·Π²ΠΎΠ΄ΠΈΡ‚Π΅Π»ΡŒΠ½ΠΎΡΡ‚ΠΈ ΠΌΠΎΠ΄Π΅Π»ΠΈ.

ΠžΡΠ½ΠΎΠ²Π½Ρ‹Π΅ аспСкты, рассмотрСнныС Π² руководствС:
- Π‘ΠΎΡ…Ρ€Π°Π½Π΅Π½ΠΈΠ΅ Π²Ρ‹Ρ…ΠΎΠ΄Π½Ρ‹Ρ… Π΄Π°Π½Π½Ρ‹Ρ… ΠΊΡ€ΡƒΠΏΠ½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΠΈ: Π‘ΠΎΠ·Π΄Π°Π½ΠΈΠ΅ Π½Π°Π±ΠΎΡ€Π° Π΄Π°Π½Π½Ρ‹Ρ…, содСрТащСго прСдсказания большой ΠΌΠΎΠ΄Π΅Π»ΠΈ, ΠΊΠΎΡ‚ΠΎΡ€Ρ‹Π΅ Π±ΡƒΠ΄ΡƒΡ‚ ΠΈΡΠΏΠΎΠ»ΡŒΠ·ΠΎΠ²Π°Ρ‚ΡŒΡΡ для обучСния мСньшСй ΠΌΠΎΠ΄Π΅Π»ΠΈ.

- ΠžΡ†Π΅Π½ΠΊΠ° ΠΏΡ€ΠΎΠΈΠ·Π²ΠΎΠ΄ΠΈΡ‚Π΅Π»ΡŒΠ½ΠΎΡΡ‚ΠΈ ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ: Π‘Ρ€Π°Π²Π½ΠΈΡ‚Π΅Π»ΡŒΠ½Ρ‹ΠΉ Π°Π½Π°Π»ΠΈΠ· точности ΠΈ эффСктивности ΠΊΠ°ΠΊ ΠΊΡ€ΡƒΠΏΠ½ΠΎΠΉ, Ρ‚Π°ΠΊ ΠΈ ΠΊΠΎΠΌΠΏΠ°ΠΊΡ‚Π½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ Π½Π° основС Ρ€Π°Π·Π»ΠΈΡ‡Π½Ρ‹Ρ… ΠΌΠ΅Ρ‚Ρ€ΠΈΠΊ.

- Π‘ΠΎΠ·Π΄Π°Π½ΠΈΠ΅ ΠΎΠ±ΡƒΡ‡Π°ΡŽΡ‰ΠΈΡ… Π΄Π°Π½Π½Ρ‹Ρ… для ΠΊΠΎΠΌΠΏΠ°ΠΊΡ‚Π½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΠΈ:
ИспользованиС прСдсказаний ΠΊΡ€ΡƒΠΏΠ½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΠΈ для Π³Π΅Π½Π΅Ρ€Π°Ρ†ΠΈΠΈ ΠΎΠ±ΡƒΡ‡Π°ΡŽΡ‰Π΅Π³ΠΎ Π½Π°Π±ΠΎΡ€Π° Π΄Π°Π½Π½Ρ‹Ρ…, ΡΠΏΠΎΡΠΎΠ±ΡΡ‚Π²ΡƒΡŽΡ‰Π΅Π³ΠΎ эффСктивному ΠΎΠ±ΡƒΡ‡Π΅Π½ΠΈΡŽ мСньшСй ΠΌΠΎΠ΄Π΅Π»ΠΈ.

- ΠžΡ†Π΅Π½ΠΊΠ° Π΄ΠΎΠΎΠ±ΡƒΡ‡Π΅Π½Π½ΠΎΠΉ ΠΊΠΎΠΌΠΏΠ°ΠΊΡ‚Π½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΠΈ: ΠŸΡ€ΠΎΠ²Π΅Ρ€ΠΊΠ° ΠΏΡ€ΠΎΠΈΠ·Π²ΠΎΠ΄ΠΈΡ‚Π΅Π»ΡŒΠ½ΠΎΡΡ‚ΠΈ ΠΈ точности ΠΊΠΎΠΌΠΏΠ°ΠΊΡ‚Π½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΠΈ послС процСсса дистилляции для подтвСрТдСния соотвСтствия трСбованиям.

πŸ”—Π‘ΡΡ‹Π»ΠΊΠ°

2. Π£Ρ‡Π΅Π±Π½ΠΈΠΊ ΠΏΠΎ дистилляции Π·Π½Π°Π½ΠΈΠΉ ΠΎΡ‚ PyTorch πŸ”₯

Руководство ΠΎΡ‚ PyTorch, ΠΊΠΎΡ‚ΠΎΡ€ΠΎΠ΅ содСрТит практичСскоС Π²Π²Π΅Π΄Π΅Π½ΠΈΠ΅ Π² Ρ‚Π΅Ρ…Π½ΠΈΠΊΡƒ ΠΏΠ΅Ρ€Π΅Π΄Π°Ρ‡ΠΈ Π·Π½Π°Π½ΠΈΠΉ для развёртывания ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ Π½Π° устройствах с ΠΎΠ³Ρ€Π°Π½ΠΈΡ‡Π΅Π½Π½Ρ‹ΠΌΠΈ Π²Ρ‹Ρ‡ΠΈΡΠ»ΠΈΡ‚Π΅Π»ΡŒΠ½Ρ‹ΠΌΠΈ рСсурсами.

ΠžΡΠ½ΠΎΠ²Π½Ρ‹Π΅ аспСкты руководства:

- Π˜Π·Π²Π»Π΅Ρ‡Π΅Π½ΠΈΠ΅ скрытых прСдставлСний: Π’ Π³Π°ΠΉΠ΄Π΅ ΠΏΠΎΠΊΠ°Π·Π°Π½ΠΎ, ΠΊΠ°ΠΊ ΠΏΠΎΠ»ΡƒΡ‡ΠΈΡ‚ΡŒ ΠΏΡ€ΠΎΠΌΠ΅ΠΆΡƒΡ‚ΠΎΡ‡Π½Ρ‹Π΅ прСдставлСния ΠΈΠ· ΠΎΠ±ΡƒΡ‡Π΅Π½Π½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΠΈ для дальнСйшСго использования.

- ΠœΠΎΠ΄ΠΈΡ„ΠΈΠΊΠ°Ρ†ΠΈΡ Ρ†ΠΈΠΊΠ»ΠΎΠ² обучСния Π² PyTorch: Π—Π΄Π΅ΡΡŒ рассматриваСтся интСграция Π΄ΠΎΠΏΠΎΠ»Π½ΠΈΡ‚Π΅Π»ΡŒΠ½Ρ‹Ρ… Ρ„ΡƒΠ½ΠΊΡ†ΠΈΠΉ Π² стандартныС Ρ†ΠΈΠΊΠ»Ρ‹ обучСния для эффСктивной ΠΏΠ΅Ρ€Π΅Π΄Π°Ρ‡ΠΈ Π·Π½Π°Π½ΠΈΠΉ.

- На ΠΏΡ€ΠΈΠΌΠ΅Ρ€Π΅ ΠΏΠΎΠΊΠ°Π·Π°Π½ процСсс обучСния ΠΊΠΎΠΌΠΏΠ°ΠΊΡ‚Π½ΠΎΠΉ ΠΌΠΎΠ΄Π΅Π»ΠΈ, с ипользованиСм прСдсказания Π±ΠΎΠ»Π΅Π΅ слоТной ΠΌΠΎΠ΄Π΅Π»ΠΈ Π² качСствС ΠΎΡ€ΠΈΠ΅Π½Ρ‚ΠΈΡ€Π°.

Руководство содСрТит ΠΏΠΎΡˆΠ°Π³ΠΎΠ²Ρ‹Π΅ инструкции ΠΈ ΠΏΡ€ΠΈΠΌΠ΅Ρ€Ρ‹ ΠΊΠΎΠ΄Π°, Ρ‡Ρ‚ΠΎ Π΄Π΅Π»Π°Π΅Ρ‚ Π΅Π³ΠΎ Ρ†Π΅Π½Π½Ρ‹ΠΌ рСсурсом, Ссли Π²Ρ‹ Ρ…ΠΎΡ‚ΠΈΡ‚Π΅ Π½Π°ΡƒΡ‡ΠΈΡ‚ΡŒΡΡ ΠΎΠΏΡ‚ΠΈΠΌΠΈΠ·ΠΈΡ€ΠΎΠ²Π°Ρ‚ΡŒ свои ΠΌΠΎΠ΄Π΅Π»ΠΈ для использования Π² срСдах с ΠΎΠ³Ρ€Π°Π½ΠΈΡ‡Π΅Π½Π½Ρ‹ΠΌΠΈ рСсурсами.

β–ͺБсылка

3. Jetson Introduction to Knowledge Distillation ΠΎΡ‚ Nvidia πŸ–₯

Π’ Π΄Π°Π½Π½ΠΎΠΌ руководствС рассматриваСтся процСсс ΠΏΠ΅Ρ€Π΅Π΄Π°Ρ‡ΠΈ Π·Π½Π°Π½ΠΈΠΉ ΠΎΡ‚ ΠΌΠΎΠ΄Π΅Π»ΠΈ OpenCLIP (vision-language model) ΠΊ ΠΌΠΎΠ΄Π΅Π»ΠΈ ResNet18 для классификации Π½Π° Π½Π°Π±ΠΎΡ€Π΅ Π΄Π°Π½Π½Ρ‹Ρ… STL10.

ОсобоС Π²Π½ΠΈΠΌΠ°Π½ΠΈΠ΅ удСляСтся Ρ‚ΠΎΠΌΡƒ, ΠΊΠ°ΠΊ Π²Ρ‹Π±ΠΎΡ€ Π΄Π°Π½Π½Ρ‹Ρ…, ΠΌΠ΅Ρ‚ΠΎΠ΄Ρ‹ дистилляции ΠΈ Π°Ρ€Ρ…ΠΈΡ‚Π΅ΠΊΡ‚ΡƒΡ€Π° ΠΌΠΎΠ΄Π΅Π»ΠΈ, Π²Π»ΠΈΡΡŽΡ‚ Π½Π° ΠΈΡ‚ΠΎΠ³ΠΎΠ²ΡƒΡŽ Ρ‚ΠΎΡ‡Π½ΠΎΡΡ‚ΡŒ.

ΠšΡ€ΠΎΠΌΠ΅ Ρ‚ΠΎΠ³ΠΎ, ΠΎΠ±ΡΡƒΠΆΠ΄Π°ΡŽΡ‚ΡΡ ΠΌΠ΅Ρ‚ΠΎΠ΄Ρ‹ профилирования ΠΈ ΠΎΠΏΡ‚ΠΈΠΌΠΈΠ·Π°Ρ†ΠΈΠΈ ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ для ΠΈΡ… развёртывания Π½Π° устройствах NVIDIA Jetson Orin Nano.

πŸ”— Бсылка

4. Π£Ρ‡Π΅Π±Π½ΠΈΠΊ ΠΏΠΎ дистилляции Π·Π½Π°Π½ΠΈΠΉ ΠΎΡ‚ Keras ⭐️

ΠŸΠΎΠ΄Ρ€ΠΎΠ±Π½ΠΎ описываСтся концСпция дистилляции Π·Π½Π°Π½ΠΈΠΉ ΠΈ Π΅Π΅ ΠΏΡ€ΠΈΠΌΠ΅Π½Π΅Π½ΠΈΠ΅ Π² ΠΎΠ±Ρ€Π°Π±ΠΎΡ‚ΠΊΠ΅ мСдицинских ΠΈΠ·ΠΎΠ±Ρ€Π°ΠΆΠ΅Π½ΠΈΠΉ.

πŸ”—Github
πŸ”—Π£Ρ‡Π΅Π±Π½ΠΈΠΊ Keras

5. Руководство ΠΏΠΎ дистилляции ΠΎΡ‚
huggingface
πŸ€—

Π—Π΄Π΅ΡΡŒ ΠΏΠΎΠΊΠ°Π·Π°Π½ΠΎ, ΠΊΠ°ΠΊ Π²Ρ‹ΠΏΠΎΠ»Π½ΡΡ‚ΡŒ Π΄ΠΈΡΡ‚ΠΈΠ»Π»ΡΡ†ΠΈΡŽ Π·Π½Π°Π½ΠΈΠΉ шаг Π·Π° шагом Π½Π° ΠΊΠΎΠ½ΠΊΡ€Π΅Ρ‚Π½ΠΎΠΌ ΠΏΡ€ΠΈΠΌΠ΅Ρ€Π΅.

πŸ”— Бсылка

6. Дистилляция Π·Π½Π°Π½ΠΈΠΉ для Π·Π°Π΄Π°Ρ‡ ΠΊΠΎΠΌΠΏΡŒΡŽΡ‚Π΅Ρ€Π½ΠΎΠ³ΠΎ зрСния ΠΎΡ‚ huggingface πŸ‘

Π—Π΄Π΅ΡΡŒ рассматриваСтся, ΠΊΠ°ΠΊ ΡΠ΄Π΅Π»Π°Ρ‚ΡŒ Ρ„Π°ΠΉΠ½Ρ‚ΡŽΠ½ ViT-ΠΌΠΎΠ΄Π΅Π»ΠΈ Π² MobileNet с ΠΏΠΎΠΌΠΎΡ‰ΡŒΡŽ API Trainer ΠΈΠ· Transformers.

πŸ”—Π‘ΡΡ‹Π»ΠΊΠ°

#KnowledgeDistillation #Distillation #openai #keras #tutorial #course #freecourses #huggingface #Nvidia #pytorch
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM