2 GB

Ctrl+K

3 contributors

History: 14 commits

Luigi

Add option --yolo_nas_pose, used to read YOLO NAS Pose model instead of RTMO

1f0f5d8 about 2 years ago

video
Add a sample video about 2 years ago
.gitattributes

1.66 kB
Add a sample video about 2 years ago
README.md

640 Bytes
Update README.md about 2 years ago
convert_to_fp16.py

1.11 kB
Fix FP16 models having poor accuracy about 2 years ago
demo.sh

63 Bytes
Fix typo in model names mentioned in demo.sh demo_batch.sh about 2 years ago
demo_batch.sh

71 Bytes
Fix typo in model names mentioned in demo.sh demo_batch.sh about 2 years ago
fix_batch_dimension.py

1.4 kB
Repair DEMO to run with TRT EP about 2 years ago
fix_batch_dimension_all.sh

775 Bytes
Repair DEMO to run with TRT EP about 2 years ago
rtmo-l.fp16.onnx

88 MB
xet

Fix FP16 models having poor accuracy about 2 years ago
rtmo-l.fp16_batch1.onnx

88 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-l.fp16_batch2.onnx

88 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-l.fp16_batch4.onnx

88 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-l.onnx

176 MB
xet

Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider about 2 years ago
rtmo-l_batch1.onnx

176 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-l_batch2.onnx

176 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-l_batch4.onnx

176 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-m.fp16.onnx

44.7 MB
xet

Fix FP16 models having poor accuracy about 2 years ago
rtmo-m.fp16_batch1.onnx

44.7 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-m.fp16_batch2.onnx

44.7 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-m.fp16_batch4.onnx

44.7 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-m.onnx

89.3 MB
xet

Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider about 2 years ago
rtmo-m_batch1.onnx

89.3 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-m_batch2.onnx

89.3 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-m_batch4.onnx

89.3 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-s.fp16.onnx

19.9 MB
xet

Fix FP16 models having poor accuracy about 2 years ago
rtmo-s.fp16_batch1.onnx

19.9 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-s.fp16_batch2.onnx

19.9 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-s.fp16_batch4.onnx

19.9 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-s.onnx

39.7 MB
xet

Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider about 2 years ago
rtmo-s_batch1.onnx

39.7 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-s_batch2.onnx

39.7 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-s_batch4.onnx

39.7 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-t.fp16.onnx

13.7 MB
xet

Fix FP16 models having poor accuracy about 2 years ago
rtmo-t.fp16_batch1.onnx

13.7 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-t.fp16_batch2.onnx

13.7 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-t.fp16_batch4.onnx

13.7 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-t.onnx

27.4 MB
xet

Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider about 2 years ago
rtmo-t_batch1.onnx

27.4 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-t_batch2.onnx

27.4 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo-t_batch4.onnx

27.4 MB
xet

Repair DEMO to run with TRT EP about 2 years ago
rtmo_demo.py

2.18 kB
Add option --yolo_nas_pose, used to read YOLO NAS Pose model instead of RTMO about 2 years 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 about 2 years ago
rtmo_gpu.py

17.8 kB
Add option --yolo_nas_pose, used to read YOLO NAS Pose model instead of RTMO about 2 years ago
symbolic_shape_infer.py

138 kB
Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider about 2 years ago
symbolic_shape_infer_all.sh

135 Bytes
Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider about 2 years ago