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
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
36d34b73eb
[Major] Add device guard.
2022-07-11 11:05:49 -04:00
da93b27d0f
[Major] Code release.
2022-06-03 04:21:18 +00:00
bevfusion
Jeff Daily
Kevin Shao
Haotian (Ken) Tang
Haotian Tang