uoftcprg/pokerkit 510 +1 today
uncomplicate/deep-diamond 467
Deep Diamond ships six modules and a README that stops before the coordinates
TorchSpatiotemporal/tsl 388
tsl wraps PyG and Lightning with pinned version ceilings and one compile switch
Thinklab-SJTU/pygmtools 352
Graph matching means node correspondence, and pygmtools wraps the solvers
theislab/scarches 414
scArches maps query cells into a reference atlas instead of refitting the model
tensorgi/TPA 464
TPA is nanoGPT with an attention swap and an eight-GPU bill
Tencent-Hunyuan/AuK 1,435
AuK: a 1.5B speech model whose Performance and Model Architecture sections are empty headings
taufeeque9/HumanFallDetection 354
HumanFallDetection reduces a fall to five pose features and an LSTM verdict
tabularis-ai/be_great 371
be_great generates tables with a 0.3B language model and a list of knobs
sugarme/tokenizer 341
sugarme/tokenizer: Hugging Face tokenizer configs in pure Go
sozykin/dlpython_course 321
dlpython_course, ten numbered notebook folders and not one pinned dependency
smousavi05/EQTransformer 420
EQTransformer gives you two models and one threshold to choose
slideflow/slideflow 376
Slideflow: digital pathology tooling where the foundation models are a separate license
SimplexLab/TorchJD 400
TorchJD routes a multi-loss PyTorch loop through a scalarizer or an aggregator
shoumikchow/bbox-visualizer 412
bbox-visualizer draws labeled boxes from VOC, COCO or YOLO coordinates
seisbench/seisbench 427
SeisBench splits seismology machine learning into data, models and generate
Seeed-Studio/ModelAssistant 449
ModelAssistant: computer vision squeezed onto a microcontroller
sb-ai-lab/RePlay 416
polars for the data, PySpark for the models, extras for everything else
sarulab-speech/UTMOSv2 375
UTMOSv2 predicts speech naturalness from a backbone borrowed from image classification
rwth-i6/returnn 377