🔥 Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

Masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner.

Github: https://github.com/microsoft/unilm/tree/master/beit

Paper: https://arxiv.org/abs/2208.10442v1

Datasets: https://paperswithcode.com/dataset/visual-genome

@ai_machinelearning_big_data

✅ Awesome-Dataset-Distillation

Github: https://github.com/Guang000/Awesome-Dataset-Distillation

Awesome Computer Vision: https://github.com/jbhuang0604/awesome-computer-vision

Paper: https://arxiv.org/abs/2208.11311v1

Datasets: https://paperswithcode.com/dataset/cifar-10

@ai_machinelearning_big_data

🥇 The Complete Data Science Study Roadmap

➡️ Read
🎲 Statistics Fundamental by Josh Starmer
👨‍🎓 CS229 machine learning Stanford

@ai_machinelearning_big_data

⭐️ YOLOX-PAI: An Improved YOLOX Version by PAI

Github: https://github.com/alibaba/EasyCV

Paper: https://arxiv.org/abs/2208.13040v1

Datasets: https://paperswithcode.com/dataset/coco

@ai_machinelearning_big_data

🔋 Self-Supervised Pyramid Representation Learning
for Multi-Label Visual Analysis and Beyond

Github: https://github.com/wesleyhsieh0806/ss-prl

Paper: https://arxiv.org/abs/2208.14439v1

Datasets: https://github.com/wesleyhsieh0806/ss-prl#books-prepare-dataset

Downstream: http://host.robots.ox.ac.uk/pascal/VOC/

@ai_machinelearning_big_data

🖼 PyTorch Image Quality (PIQ) is a collection of measures and metrics for image quality assessment.

$ pip install piq

Github: https://github.com/photosynthesis-team/piq

Paper: https://arxiv.org/abs/2208.14818v1

Docs: https://piq.readthedocs.io.

Datasets: https://paperswithcode.com/dataset/kadid-10k

@ai_machinelearning_big_data

Как организовать потоковую обработку данных. Часть 2!

В первой части Евгений Ненахов из центра Big Data МТС Digital рассказал об основных компонентах методологии, а сейчас — о том, как ими пользоваться.

Из новой статьи вы узнаете:

➖ где хранить конфигурации
➖ как настроить Kafka и Spark Streaming
➖ как снизить нагрузку на GC и многое другое

О том, как создать универсальный инструмент потоковой обработки данных и построить с его помощью мощную систему стриминга, способную обрабатывать 7 млн событий в пике, читайте в блоге МТС на Хабре.

🏙 2BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC Videos

Github: https://github.com/atelili/2bivqa

Paper: https://arxiv.org/abs/2208.14774v1

Dataset: https://paperswithcode.com/dataset/live-vqc

Tasks: https://paperswithcode.com/task/video-quality-assessment

@ai_machinelearning_big_data

@python_job_interview - здесь собраны все возможные вопросы и ответы с реальных Python собеседований.

@golang_interview - пройти Golang собеседование.

@machinelearning_interview - канал подготовит к собеседованию по машинному обучению и алгоритмам .

@data_analysis_ml - самая востребованная Python профессия.

🤖 Transformers are Sample Efficient World Models

New state of the art for methods without lookahead search, and even surpasses MuZero.

⚙️ Github
➡️ Paper
💻Dataset

@ai_machinelearning_big_data

🔵 Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces

The library features (approximate) computational techniques for heat and Matérn kernels on compact Lie groups.

⚙️ Github
➡️ Paper
⚪ SphericalHarmonics

@ai_machinelearning_big_data

🧬 Genomepy: genes and genomes at your fingertips

genomepy, which can search, download, and preprocess the right genomic data for your analysis.

$ pip install genomepy

⚙️ Github
➡️ Paper
📄 Documentation

@ai_machinelearning_big_data

🦾 XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation

⚙️ Github
➡️ Paper
💻 Tutorial page
📄 Dataset

@ai_machinelearning_big_data

🔥 YOLOv6

YOLOv6-N hits 35.9% AP on COCO dataset with 1234 FPS on T4. YOLOv6-S strikes 43.5% AP with 495 FPS, and the quantized YOLOv6-S model achieves 43.3% AP at a accelerated speed of 869 FPS on T4.

git clone https://github.com/meituan/YOLOv6
cd YOLOv6
pip install -r requirements.txt

⚙️ Github
➡️ Paper
✔️ Colab
💻 Quantization Tutorial
📄 Dataset

@ai_machinelearning_big_data

🧬 Uni-Mol: A Universal 3D Molecular Representation Learning Framework

⚙️ Github
➡️ Paper
🎞 Colab
📄 Dataset

@ai_machinelearning_big_data

🦾 OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning

open-source all-in-one toolbox for supervised, semi-, and self-supervised visual representation learning with mixup

conda create -n openmixup python=3.8 pytorch=1.12 cudatoolkit=11.3 torchvision -c pytorch -y
conda activate openmixup
pip install openmim
mim install mmcv-full
git clone https://github.com/Westlake-AI/openmixup.git
cd openmixup
python setup.py develop

⚙️ Github
➡️ Paper
🛠 Installation
📄 Dataset

@ai_machinelearning_big_data

👁‍🗨 Patch Similarity Aware Data-Free Quantization for Vision Transformers

PSAQ-ViT V2, a more accurate and general data-free quantization framework for ViTs, built on top of PSAQ-ViT.

git clone https://github.com/zkkli/PSAQ-ViT.git
cd PSAQ-ViT

⚙️ Github
➡️ Paper
📄 Dataset

@ai_machinelearning_big_data

🚀 StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation

⚙️ Github
➡️ Paper
🛠 Demo
📄 Dataset

@ai_machinelearning_big_data

🤖 DAMO ConvAI

The official repository which contains the codebase for Alibaba DAMO Conversational AI.

⚙️ Github
➡️ Paper
📎 Tasks
🗒 Text-to-SQL Parsing

@ai_machinelearning_big_data