5 Commits

Author	SHA1	Message	Date
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
Jeff Daily	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
lizhiqi	395fccbc23	support A100 GPU	2022-06-27 21:20:56 +08:00
Haotian Tang	6bce86a53c	[Minor] Fix some bugs.	2022-06-09 15:29:52 +00:00
Haotian Tang	da93b27d0f	[Major] Code release.	2022-06-03 04:21:18 +00:00