BEVDet implemented by TensorRT, C++； Achieving real-time performance on Orin
active 2023-08-15 → 2026-01-30 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 900 days from 2023-08-15 to 2026-01-30. Pushes: 2 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 13 total, peak 2 in a day. Comments: 31 total, peak 7 in a day. Stars: 129 total, peak 4 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| LCH1238 | 10 | 2 | 0 | 8 |
| yhwang-hub | 4 | 0 | 0 | 4 |
| persuelx | 4 | 0 | 0 | 4 |
| TGpastor | 3 | 0 | 0 | 1 |
| vilon888 | 2 | 0 | 0 | 2 |
| YoushaaMurhij | 2 | 0 | 0 | 1 |
| next-gen-machine | 2 | 0 | 0 | 1 |
| linClubs | 2 | 0 | 0 | 1 |
| lucianzhong | 2 | 0 | 0 | 1 |
| warbrain | 2 | 0 | 0 | 1 |
| pjpanadas | 1 | 0 | 0 | 0 |
| CN-Antonio | 1 | 0 | 0 | 1 |
| taoxunqiang | 1 | 0 | 0 | 1 |
| FengD | 1 | 0 | 0 | 1 |
| CXT-666 | 1 | 0 | 0 | 1 |
| scuizhibin | 1 | 0 | 0 | 0 |
| Elaine-Blue | 1 | 0 | 0 | 0 |
| zbl-96 | 1 | 0 | 0 | 1 |
| tyomj | 1 | 0 | 0 | 0 |
| lyxbyr | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#28persuelx2025-03-11 02:29自定义数据集使用单阶段模型进行推理时，如何完成从pth到onnx模型的转换
- Issue comment#25persuelx2025-03-11 01:47Failed to convert .pth model to .onnx
- Issue comment#31CN-Antonio2025-02-08 17:47Error Code 3: API Usage Error 报错
- Issue#30Elaine-Blue2024-12-17 07:48A question about inference speed
- Issue#29Xiao-Hu-Z2024-12-13 04:08orin libjpeg
- Issue comment#6persuelx2024-11-27 02:42nusence-mini data_infos
- Issue comment#6persuelx2024-11-27 01:57nusence-mini data_infos
- Issue comment#18FengD2024-10-16 06:19CMake Error at bevdemo_generated_iou3d_nms.cu
- Issue comment#21vilon8882024-08-21 02:42目前模型fp32和fp16效果正常，int8下效果下降很多，这个正常么
- Issue comment#27lyxbyr2024-04-30 05:20export_onx_onnx.py导出的合一版本onnx，转换tensorrt后推理，只检测出了2个object，实际上应该是100个左右
- Issue comment#27vilon8882024-04-30 01:12export_onx_onnx.py导出的合一版本onnx，转换tensorrt后推理，只检测出了2个object，实际上应该是100个左右
- Issue#26scuizhibin2024-04-19 03:37bevdet4d tensorrt推理时间是多少？
- Issue comment#19taoxunqiang2024-03-29 02:36How to do quantization to int8 model of img_stage_lt_d.onnx and bev_stage_lt_d.onnx?
- Issue comment#12zbl-962024-03-28 03:14请问关于算法输入是RGB格式还是BGR格式？
- Issue comment#22warbrain2023-12-13 03:39TypeError: tuple indices must be integers or slices, not tuple
- Issue#22warbrain2023-12-13 03:39TypeError: tuple indices must be integers or slices, not tuple
- Issue comment#17ou5252023-11-09 06:01Want to infer using real time camera
- Issue#21pjpanadas2023-10-19 03:52目前模型fp32和fp16效果正常，int8下效果下降很多，这个正常么
- Issue comment#20LCH12382023-10-08 16:37one分支导模型出现问题`BEVDepth4DTRT is not in the models registry`
- Issue comment#20linClubs2023-09-15 02:19one分支导模型出现问题`BEVDepth4DTRT is not in the models registry`
- Issue#20linClubs2023-09-15 01:55one分支导模型出现问题`BEVDepth4DTRT is not in the models registry`
- Issue comment#19LCH12382023-09-13 08:46How to do quantization to int8 model of img_stage_lt_d.onnx and bev_stage_lt_d.onnx?
- Issue#19avBuffer2023-09-09 07:24How to do quantization to int8 model of img_stage_lt_d.onnx and bev_stage_lt_d.onnx?
- Issue comment#18YoushaaMurhij2023-09-04 09:56CMake Error at bevdemo_generated_iou3d_nms.cu
- Issue#18YoushaaMurhij2023-09-04 09:56CMake Error at bevdemo_generated_iou3d_nms.cu
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 129 stars here means stars gained during the window, not the repo's star count.