Tag: PyTorch

serengil/deepface is a lightweight Python library wrapping 10+ state-of-the-art face recognition models. It provides one-line APIs for verification, identification, attribute analysis, and real-time streaming, with 23,112 GitHub stars and active maintenance through 2026.

wangzhiyaoo/SVFR is a unified framework for video face restoration supporting BFR, colorization, and inpainting tasks in a single diffusion-based pipeline. Built on Stable Video Diffusion, it offers both local inference and Hugging Face demo access.

VisionFusion AI unifies OpenCV and YOLOv8 into a single real-time perception pipeline with face detection, motion analysis, multi-object tracking, and CNN classification. This complete guide covers installation, code examples, and production deployment strategies.

MonoArt from NTU's S-Lab reconstructs complete articulated 3D models from single images using progressive structural reasoning. Discover how this open-source breakthrough eliminates multi-camera setups and accelerates game development, robotics, and AR workflows.

Discover why top engineers are abandoning custom 3D ML pipelines for Open3D-ML. This comprehensive guide covers installation, real code examples for semantic segmentation and object detection, and production-ready workflows with PyTorch and TensorFlow.

Discover BackgroundRemover, the free AI-powered CLI tool that removes backgrounds from images and videos. Learn installation, advanced features, Python integration, and why developers are abandoning paid alternatives for this open-source powerhouse.

Discover insanely-fast-whisper, the open-source CLI that transcribes 150 minutes of audio in just 98 seconds using OpenAI's Whisper Large v3 with Flash Attention 2. Complete installation guide, real code examples, benchmarks, and advanced usage patterns included.

Pocket TTS from Kyutai Labs delivers voice cloning and streaming text-to-speech on CPU only—no GPU required. 100M parameters, 6x real-time speed, 200ms latency. Complete guide with real code examples.

CatVTON is an ICLR 2025 virtual try-on diffusion model achieving 1024×768 inference under 8GB VRAM through elegant concatenation-based design. With only 49.57M trainable parameters, it democratizes fashion AI for developers and researchers.

Master GPU optimization with the Infatoshi CUDA course. Learn kernel programming, Triton, and PyTorch extensions through 11 structured modules—from first kernels to production-ready extensions. Free, comprehensive, and deep learning-native.

TurboQuant-GPU achieves 5.02x KV cache compression for LLM inference with 0.98 cosine similarity. Learn how this open-source tool outperforms NVIDIA's FP4 formats, works on any GPU, and installs in seconds.

NVIDIA's DreamZero achieves #1 robot benchmark rankings with zero-shot generalization using world action models. Learn how to deploy, fine-tune, and extend this open-source robotics breakthrough.

Discover how AgentGym-RL trains 7B parameter LLM agents to surpass GPT-4o on real-world multi-turn tasks using progressive horizon scaling reinforcement learning. Complete setup guide, code examples, and performance benchmarks included.

OmniVoice is an open-source TTS model supporting 600+ languages with zero-shot voice cloning, 40x real-time inference speed, and voice design from text attributes. Built on a novel diffusion language model architecture.

Discover PanelCleaner, the AI-powered open-source tool revolutionizing manga text removal. Learn installation, advanced features, and real code examples to automate tedious cleaning workflows.

Discover how to train your own 9M-parameter language model from scratch in just 5 minutes using GuppyLM. This complete guide covers architecture, code examples, deployment, and why this tiny fish represents a revolution in AI accessibility.

LeJEPA eliminates heuristics from self-supervised learning with provable SIGReg regularization. Co-authored by Yann LeCun, it achieves SOTA results in 100 epochs with ~50 lines of core code. Learn how to stop babysitting training runs.

Discover why mrdbourke/pytorch-deep-learning is the most comprehensive free PyTorch course available. With 321 videos, 10 complete sections, and a code-first philosophy, this repository takes you from tensor basics to production deployment through real milestone projects.