Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
enlin e5dd57508b | 2 years ago | |
---|---|---|
.. | ||
.idea | 2 years ago | |
checkpoints/fpn_resnet_18 | 2 years ago | |
sfa | 2 years ago | |
.DS_Store | 2 years ago | |
.gitignore | 2 years ago | |
LICENSE | 2 years ago | |
README.md | 2 years ago | |
Technical_details.md | 2 years ago | |
requirements.txt | 2 years ago |
The instructions for setting up a virtual environment is here.
cd SFA3D/
pip install -r requirements.txt
Download the 3D KITTI detection dataset from here.
The downloaded data includes:
Please make sure that you construct the source code & dataset directories structure as below.
The pre-trained model was pushed to this repo.
python inference.py --no_cuda=True
python inference.py
Label of inference
python train.py --no_cuda=True
python train.py --gpu_idx 0
python train.py --multiprocessing-distributed --world-size 1 --rank 0 --batch_size 64 --num_workers 8
Two machines (two nodes), multiple GPUs
python train.py --dist-url 'tcp://IP_OF_NODE1:FREEPORT' --multiprocessing-distributed --world-size 2 --rank 0 --batch_size 64 --num_workers 8
python train.py --dist-url 'tcp://IP_OF_NODE2:FREEPORT' --multiprocessing-distributed --world-size 2 --rank 1 --batch_size 64 --num_workers 8
[1] SFA3D: PyTorch Implementation
└── kitti/
├── image_2/ (left color camera,非必须)
├── calib/ (非必须)
├── label_2/ (标注结果/标签,非必须)
└── velodyne/ (点云文件,必须)
${ROOT}
└── checkpoints/
├── fpn_resnet_18/
├── fpn_resnet_18_epoch_300.pth (点云目标检测标注模型)
└── sfa/ (点云标注算法)
├── config/
├── data_process/
├── models/
├── utils/
├── inference.py
└── train.py
├── README.md
├── LICENSE
└── requirements.txt
一站式算法开发平台、高性能分布式深度学习框架、先进算法模型库、视觉模型炼知平台、数据可视化分析平台等一系列平台及工具,在模型高效分布式训练、数据处理和可视分析、模型炼知和轻量化等技术上形成独特优势,目前已在产学研等各领域近千家单位及个人提供AI应用赋能
Java Vue Python Text JavaScript other