sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
torchdistill
A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆26 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.
sc2-benchmark
[TMLR] "SC2 Benchmark: Supervised Compression for Split Computing"
small-object-detection-benchmark
icip2022 paper: sahi benchmark on visdrone and xview datasets using fcos, vfnet and tood detectors
https://github.com/amirzenoozi/yolo-tf2-object-detection
Object Detection on Image and Video Based on YOLO Model
https://github.com/ccomkhj/imagedatasetmanager
Simplify the process of managing datasets in computer vision tasks using Datumaro, by offering a GUI. Split, Merge, Filter Dataset (i.e. coco).
https://github.com/ccomkhj/cvops
Simplify COCO dataset management with an intuitive GUI for visualization, merging, splitting, and updating. Perfect for ML and computer vision projects.