Large-scale ImageNet-1K experiments with NFNet analyzing data ordering, cumulative vs incremental learning, and continual learning dynamics using distributed PyTorch (DDP).
π Classify defects in Quick-View videos using deep learning with a complete pipeline for data extraction, model training, and reproducibility.
QV-Pipe multi-label classification (super-image Γγ°γ€3, timm, ASL/CB-Focal, OneCycle, EMA, 5-fold ensemble).. Inspired by Challenge Pipe 2022.
Production-ready time-series image classifier using EfficientNet/NFNet with PyTorch Lightning. Supports single-modal and multi-modal learning with F1-score optimization.
Add a description, image, and links to the nfnet topic page so that developers can more easily learn about it.
To associate your repository with the nfnet topic, visit your repo's landing page and select "manage topics."