lightly-train
+8All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
Chủ đề #contrastive-learning trên GitHub — repository trong kho Beeknoee có gắn topic này.
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
Item-to-item music recommendation system, training on Spotify 45M tracks & 1.8M playlists. (Spotify track ID / ISRC in, similar songs out)
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
A python library for self-supervised learning and latent world models on images.
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
Các chủ đề phổ biến khác trong kho Beeknoee