Maschinelles Lernen · GitHub

UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.

A Systems View of Efficient Machine Learning, from Silicon to Agents. Fourteen parts, from roofline analysis and vector units up through kernels, compilers, quantisation, compression, vision, on-device language models, robotics, profiling, serving and agents.

Build Custom Deep Neural Network Trainers in 2026: Open Source BuilT Guide

Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation

TinyML AI inference library

DeepDEM: Digital Elevation Model refinement using deep learning

A programmable distributed training system for PyTorch

Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application

Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.

PromptIR: Prompting for All-in-One Blind Image Restoration [NeurIPS 2023]

[CVPR 2026 Workshop] Official implementation of "BST: Badminton Stroke-type Transformer for Skeleton-based Action Recognition in Racket Sports"

Готовая база из 5 881 ответа по 21 тесту hh.ru - сдать с первой попытки

Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes

Fast and differentiable MS-SSIM and SSIM for pytorch.

A library for generating and evaluating synthetic tabular data for privacy, fairness and data augmentation.

• :key: Easy to extend pluginable architecture.
• :cyclone: Several evaluation metrics for correctness and privacy.

OmniRisk: omnidirectional trajectory-risk learning for agile quadrotor dynamic avoidance. One forward pass scores every maneuver onboard; real-world evasion at up to 15 m/s.