detr3d-exp
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.1%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: ZitengXue
- License: apache-2.0
- Language: Python
- Default Branch: master
- Size: 5.31 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Installation
- Environment Setup ```bash conda create -n detr python=3.8 -y
pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html pip install -U openmim mim install 'mmengine==0.8.4' mim install 'mmcv==2.0.0rc4' mim install 'mmdet==3.0.0rc5' pip install setuptools==59.5.0 pip install -v -e . ``` 2. Downloads the pretrained backbone weights to pretrained/
Downloads the language model and config to /text
Get Started
Please Download nuScenes dataset to data/nuscnes and run
bash python tools/create_data.py nuscenes --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nusceneswhich should look like: |--nuscnes |--maps |--samples |--sweeps |--v1.0-test |--v1.0-trainval |--nuscenesgtdatabase |--nuscenesdbinfostrain.pkl |--nuscenesinfostest.pkl |--nuscenesinfosval.pkl |--nuscenesinfostrain.pklFor example, to train DETR3D on 2 GPUs with bert encoder and half data, please use
bash
bash tools/dist_train.sh projects/DETR3D/configs/detr3d_r50_bert_gridmask_halfdata.py 2 --cfg-options load_from=pretrained/fcos3d.pth
Owner
- Name: indigo
- Login: ZitengXue
- Kind: user
- Repositories: 1
- Profile: https://github.com/ZitengXue
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - name: "MMDetection3D Contributors" title: "OpenMMLab's Next-generation Platform for General 3D Object Detection" date-released: 2020-07-23 url: "https://github.com/open-mmlab/mmdetection3d" license: Apache-2.0