Object Detection
PyTorch
ONNX
TensorRT
3d-object-detection
autonomous-driving
streampetr
carla
nuscenes
bev
Instructions to use heliosink/StreamPETR_nuCarla with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use heliosink/StreamPETR_nuCarla with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Commit History
-
feat(7cam): add matching FOV30 model config
Lương Ngọc HuyVerified signatureConfiguration paired with the seven-camera iter-14000 checkpoint.b252db5 -
feat(7cam): add best FOV30 checkpoint at iter 14000
Lương Ngọc HuyVerified signatureSeven-camera StreamPETR checkpoint: six nuCarla surround cameras plus a co-located 30-degree front narrow camera. Validation NuCarla mAP 0.7188, NDS 0.7605.3793f4b
-
feat: add best full-town epoch-50 StreamPETR checkpoint
Lương Ngọc HuyVerified signatureBest full official nuCarla checkpoint at iter 116650 (virtual epoch 50). NuCarla mAP 0.7246, NDS 0.7633. SHA-256 d46ad8305381fc53cc99581e6548e75e9ce771612e49065d49f4f05bd441544f.2cc2d25
-
feat(streampetr): nuCarla six-camera 3D detection model with TensorRT deployment
Lương Ngọc HuyVerified signature54d55df -
initial commit
Lương Ngọc HuyVerified signature12b3e8d