self-supervised-learning

lightly-train

+8

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

geti

+4

Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intel® XPU (CUDA also supported).

pytorch-metric-learning

+3

Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.

lightly

+3

A python library for self-supervised learning and latent world models on images.

PaddleSpeech

+3

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.