Hugging Face's logo

pesi
/
rtmo

Object Detection
ONNX
Pose Estimation
Model card Files
xet
Community
rtmo / rtmo_gpu.py

Commit History

adjust visualisation style, allow draw_bbox() to show person id
a9e21bc

Luigi commited on

Add method to free buffers
b79a8af

Luigi commited on

Implement pycuda backend for inference with TensorRT engine
889281f

Luigi commited on

Add 'get_model_format_and_input_shape' helper function
2f2f685

Luigi commited on

Return and show bounding box confidence
634d4ff

Luigi commited on

Deal with multiple cameras
98d66d4

Luigi commited on

Show bounding box on screen too
0bf1eb7

Luigi commited on

Internalize input frame buffer
846e714

Luigi commited on

Unify batched and non-batched versions
42892de

Luigi commited on

Support Inference over batch with TensorRT Engine Model
0cdc9a7

Luigi commited on

Use ONNXruntime instead of ONNX.checker.check_model to detect ONNX model
57a8c6b

Luigi commited on

Resize in keeping aspect ratio in visualization
35b2a45

Luigi commited on

fix postprocess_batch method in RTMO_GPU_Batch class
6008f96

Luigi commited on

Add model format (ONNX/Engine) & input size detection (based on file header, not on filename) for RTMO
58a44cf

Luigi commited on

Add support TensorRT engine support for RTMO
bbf20b6

Luigi commited on

Load ./libmmdeploy_tensorrt_ops.so for TensorRT EP if available
1c5dc58

Luigi commited on

Add option --yolo_nas_pose, used to read YOLO NAS Pose model instead of RTMO
1f0f5d8

Luigi commited on

Make ONNX models compatible with ONNXruntime's TensorrtExecutionProvider
b75f05d

Luigi commited on

Add new class 'RTMO_GPU_Batch' that can perform inference on batch of images
8072759

Luigi commited on

Optimization for CUDAExecutionProvider
43a489d

Luigi commited on

RTMO ONNX Models from MMPOSE range from Tiny to Large
7ad7e4d
verified

Luigi commited on