rtmo

3 contributors

History: 23 commits

Luigi

Add utility to convert ONNX model in FP32/16 mixed precision

9f60e86 8 months ago

video
Add a sample video 9 months ago
.gitattributes

1.66 kB

Add a sample video 9 months ago
README.md

1.47 kB

Update README.md 9 months ago
constant_folding.sh

337 Bytes

Apply constant folding 8 months ago
convert_to_fp16.py

1.11 kB

Fix FP16 models having poor accuracy 9 months ago
convert_to_fp16_all.py

1.36 kB

Bugfix: correct batch dimension fixation then regenerate ONNX models 8 months ago
convert_to_mixed.py

3.03 kB

Add utility to convert ONNX model in FP32/16 mixed precision 8 months ago
demo.sh

56 Bytes

Remove models with fixed batch size as dynamic batch is generally supported 8 months ago
demo_batch.sh

64 Bytes

Remove models with fixed batch size as dynamic batch is generally supported 8 months ago
rtmo-l.fp16.onnx

88 MB
LFS

Apply constant folding 8 months ago
rtmo-l.onnx

176 MB
LFS

Apply constant folding 8 months ago
rtmo-m.fp16.onnx

44.7 MB
LFS

Apply constant folding 8 months ago
rtmo-m.onnx

89.3 MB
LFS

Apply constant folding 8 months ago
rtmo-s.fp16.onnx

19.9 MB
LFS

Apply constant folding 8 months ago
rtmo-s.onnx

39.6 MB
LFS

Apply constant folding 8 months ago
rtmo-t.fp16.onnx

13.7 MB
LFS

Apply constant folding 8 months ago
rtmo-t.onnx

27.4 MB
LFS

Apply constant folding 8 months ago
rtmo_demo.py

2.18 kB

Add option --yolo_nas_pose, used to read YOLO NAS Pose model instead of RTMO 9 months ago
rtmo_demo_batch.py

3.15 kB

Bugfix for batch demo: add padding if remaning number of frames is not equal to batch size 9 months ago
rtmo_gpu.py

17.9 kB

Load ./libmmdeploy_tensorrt_ops.so for TensorRT EP if available 8 months ago
symbolic_shape_infer.py

138 kB

Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider 9 months ago
symbolic_shape_infer_all.sh

135 Bytes

Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider 9 months ago