wuwenhai
/
bev-project
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
bev-project/docker/Dockerfile

45 lines
1.4 KiB
Docker
Raw Permalink Normal View History

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 17:06:09 +08:00
FROM nvcr.io/nvidia/cuda:11.3.1-devel-ubuntu20.04
Add docker support (#145)
2022-09-27 06:51:16 +08:00
RUN apt-get update && apt-get install wget -yq
RUN apt-get install build-essential g++ gcc -y
ENV DEBIAN_FRONTEND noninteractive
RUN apt-get install libgl1-mesa-glx libglib2.0-0 -y
RUN apt-get install openmpi-bin openmpi-common libopenmpi-dev libgtk2.0-dev git -y
# Install miniconda
ENV CONDA_DIR /opt/conda
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 17:06:09 +08:00
RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-py38_4.12.0-Linux-x86_64.sh -O ~/miniconda.sh && \
Add docker support (#145)
2022-09-27 06:51:16 +08:00
/bin/bash ~/miniconda.sh -b -p /opt/conda
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 17:06:09 +08:00
Add docker support (#145)
2022-09-27 06:51:16 +08:00
# Put conda in path so we can use conda activate
ENV PATH=$CONDA_DIR/bin:$PATH
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 17:06:09 +08:00
#RUN conda config --add channels conda-forge
RUN conda config --add channels pytorch
RUN conda config --add channels nvidia
RUN conda config --set remote_connect_timeout_secs 60.0
RUN conda config --set remote_read_timeout_secs 120.0
RUN conda config --set remote_max_retries 5
RUN conda config --set show_channel_urls yes
RUN conda config --set channel_priority flexible
# <20><><EFBFBD><EFBFBD>ֱ<EFBFBD>Ӱ<EFBFBD>װpython<6F><6E><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>ʹ<EFBFBD><CAB9>conda-forge<67>İ<EFBFBD>
RUN conda install python=3.8 -y
#RUN conda install python=3.8 -y
RUN conda install pytorch==1.10.1 torchvision==0.11.2 torchaudio==0.10.1 cudatoolkit=11.3
Add docker support (#145)
2022-09-27 06:51:16 +08:00
RUN pip install Pillow==8.4.0
RUN pip install tqdm
RUN pip install torchpack
RUN pip install mmcv==1.4.0 mmcv-full==1.4.0 mmdet==2.20.0
RUN pip install nuscenes-devkit
RUN pip install mpi4py==3.0.3
RUN pip install numba==0.48.0