bevfusion
f1f37a8d79
Initial commit
2025-11-21 02:50:51 +00:00
bevfusion
4c8ec7e5a8
feat: 完成项目目录整理和训练状态备份
...
- 整理项目目录结构，归档历史文档
- 备份Phase 4B训练状态快照
- 优化脚本目录组织
- 准备Git服务配置脚本
2025-11-14 13:36:35 +00:00
bevfusion
cd15f117c3
feat: 提交清理前的完整项目状态
...
- 包含Phase 4B RMT-PPAD集成完成状态
- 包含项目备份文件和清单
- 包含清理脚本和目录整理分析
- 为大规模目录整理做准备
时间: 2025-11-14 11:41:11
2025-11-14 11:41:11 +00:00
bevfusion
fcf3ae0ea9
Complete project state snapshot: Phase 4B RMT-PPAD Integration
...
🎯 Training Status:
- Current Epoch: 2/10 (13.3% complete)
- Segmentation Dice: 0.9594
- Detection IoU: 0.5742
- Training stable with 8 GPUs
🔧 Technical Achievements:
- ✅ RMT-PPAD Transformer segmentation decoder integrated
- ✅ Task-specific GCA architecture optimized
- ✅ Multi-scale feature fusion (180×180, 360×360, 600×600)
- ✅ Adaptive scale weight learning implemented
- ✅ BEVFusion multi-task framework enhanced
📊 Performance Highlights:
- Divider segmentation: 0.9793 Dice (excellent)
- Pedestrian crossing: 0.9812 Dice (excellent)
- Stop line: 0.9812 Dice (excellent)
- Carpark area: 0.9802 Dice (excellent)
- Walkway: 0.9401 Dice (good)
- Drivable area: 0.8959 Dice (good)
🛠️ Code Changes Included:
- Enhanced BEVFusion model (bevfusion.py)
- RMT-PPAD integration modules (rmtppad_integration.py)
- Transformer segmentation head (enhanced_transformer.py)
- GCA module optimizations (gca.py)
- Configuration updates (Phase 4B configs)
- Training scripts and automation tools
- Comprehensive documentation and analysis reports
📅 Snapshot Date: Fri Nov 14 09:06:09 UTC 2025
📍 Environment: Docker container
🎯 Phase: RMT-PPAD Integration Complete
2025-11-14 09:06:09 +00:00
326653dc06
[ROCm] add support for ROCm/HIP ( #509 )
...
* [ROCm] add support for ROCm/HIP
- do not use THC.h or THH.h or THCState
- rename files to avoid collisions at build time due to hipify
- HIP host device definitions in tensorview.h
- use HIP atomicAdd() in scatter_points_cuda.cu
- add WITH_ROCM anywhere WITH_CUDA was used
- update setup.py for renamed files and ROCm/HIP torch
* enforce c++17 since pytorch requires it
2024-07-31 00:04:51 -04:00
5b08cc8cee
Update the instruction of the -np flag. ( #489 )
...
Co-authored-by: Qinru Li <q4li@eng.ucsd.edu>
2024-07-25 15:16:39 -04:00
4d1ab76686
Update README.md
2024-07-11 17:09:07 -04:00
7fb85c701c
Update README.md
2024-07-11 17:07:10 -04:00
eccb6f1bee
Update README.md
2024-07-11 17:06:57 -04:00
370ea35f50
Update README.md
2024-07-11 17:06:29 -04:00
3419a37343
Update README.md
2024-07-11 17:00:50 -04:00
4dbf4dd7b4
Update README.md
2024-07-11 16:58:39 -04:00
453161759b
Update README.md
2024-07-11 16:58:01 -04:00
ef34e0eeca
Update README.md
2024-07-11 16:39:27 -04:00
cfa9f23474
Update README.md
2024-07-11 15:48:21 -04:00
2aa9e4f2fa
Update README.md
2024-07-11 15:47:32 -04:00
cba12aa5ed
Update README.md
2024-07-11 15:45:10 -04:00
f82d001d12
Update README.md
2024-07-11 15:33:00 -04:00
5d70fdf579
Update download_pretrained.sh
2024-03-28 20:41:58 -04:00
1be20e5132
Update README.md
2024-03-28 20:34:23 -04:00
531bf67dd5
Update checkpoint links
2023-09-29 15:42:39 -04:00
601961a903
Add deployment to README ( #462 )
2023-08-11 17:06:12 -04:00
cfc1acb42a
Fix the circular import ( #466 )
2023-07-23 00:15:42 -04:00
d0152cf97c
Add BEVFusion-R ( #443 )
2023-07-07 22:53:36 -04:00
db75150717
Update README.md
2023-02-09 16:02:55 -05:00
3d91980d21
Release training configurations for fusion models ( #257 )
...
* [Major] Add fusion model configs.
* [Minor] Update training instructions.
2022-12-04 22:47:29 -05:00
da751a2c9f
Update results on nuScenes and Waymo test set ( #222 )
2022-11-06 12:26:38 -05:00
0e5b9edbc1
[debug] fix bug for nuscenes dataset ( #156 )
...
* [debug] fix bug for nuscenes dataset
* [debug] fix bug for nuscenes dataset
[debug] fix bug for nuscenes dataset
2022-10-10 12:12:10 -04:00
2bf96604fe
Add docker support ( #145 )
2022-09-26 18:51:16 -04:00
f39a4a0752
Add training details ( #150 )
...
* [Major] Update training details.
* [Minor] Update README.md.
* [Minor] Remove comment.
2022-09-26 18:24:38 -04:00
e4d599edd5
Merge pull request #125 from kevincao91/main
...
[debug] fix bug for create data
2022-09-05 09:52:50 -04:00
00722ce2f8
[debug] fix bug for create data
...
[debug] fix bug for create data
2022-09-02 15:26:29 +08:00
6908c57b78
[Minor] Remove mono3d files in README.
2022-08-29 22:29:06 -07:00
09a59c9645
[Minor] Update README.md.
2022-08-24 13:43:34 -07:00
c53e2283b0
[Minor] Update requirements.
2022-07-27 10:30:05 -04:00
008b4a8b32
[Major] Update important requirement.
2022-07-16 10:30:21 -04:00
98319eeaeb
Merge pull request #70 from JoeyforJoy/debug_jfj
...
[debug] fix bug for benchmark
2022-07-12 09:28:26 -04:00
ae7f54a3e5
[debug] fix bug for benchmark
2022-07-12 12:05:47 +08:00
36d34b73eb
[Major] Add device guard.
2022-07-11 11:05:49 -04:00
cb6cd789d1
Merge pull request #46 from zhiqi-li/a100_cuda
...
support A100 GPU
2022-06-27 12:42:28 -04:00
395fccbc23
support A100 GPU
2022-06-27 21:20:56 +08:00
0691e1b871
Add the badge of 3D object tracking
2022-06-26 10:09:57 -04:00
5065d4fb13
[Minor] Fix config links.
2022-06-21 10:21:54 -04:00
6847d45f65
Merge pull request #30 from JoeyforJoy/debug_jfj
...
[fix] fix bug for issue#29
2022-06-18 11:03:30 -04:00
4d8b4757a8
[fix] change the function signature of BaseTransform's forward() function, to successfully run tools/visualize.py for camera-only model
2022-06-18 21:57:40 +08:00
24502fe097
[Minor] Fix dependencies.
2022-06-16 23:23:42 +00:00
d16e937596
[Minor] Update requirements.
2022-06-10 11:37:16 -04:00
93d99697ee
Merge pull request #16 from xczhanjun/truck
...
Fix create data problem : missing sample_index and camera_intrinsics …
2022-06-10 00:07:01 -04:00
408b645179
Fix create data problem : missing sample_index and camera_intrinsics keys in get_data_info [ #11 ]
2022-06-10 11:15:52 +08:00
6bce86a53c
[Minor] Fix some bugs.
2022-06-09 15:29:52 +00:00
bevfusion
Jeff Daily
Daniel Li
Zhijian Liu
Zhijian Liu
HopeJW
Kevin Shao
Haotian (Ken) Tang
kevin
JoeyforJoy
lizhiqi
Haotian Tang
zhanjun