pesi
/

rtmo

Object Detection

Pose Estimation

Model card Files Files and versions Community

rtmo / convert_to_fp16.py

Commit History

Re-quantize models in FP16 in keep positional encoding in FP32 to avoid bad accuracy

f9a6075
verified

Luigi commited on Mar 27

Fix FP16 models having poor accuracy

25f1444

Luigi commited on Mar 8

RTMO ONNX Models from MMPOSE range from Tiny to Large

7ad7e4d
verified

Luigi commited on Mar 1