Skip to content

GitLab

"...src/kernels/kCalculateAmoebaCudaPmeMutualInducedField.cu" did not exist on "25ce16644f9a55e2f74ffb8a92b34d5f3b38c651"
Commit 19472568 authored by 雍大凯's avatar 雍大凯
Browse files

将子模块转换为普通目录

parent 51e55208
Show whitespace changes
Inline Side-by-side
Showing with 987 additions and 1 deletion
MapTR @ e03f097a
Subproject commit e03f097abef19e1ba3fed5f471a8d80fbfa0a064
docker-hub/MapTRv2/MapTR/.gitignore 0 → 100644
View file @ 19472568
/*.sh
change_submit.py
cluster_submit.yaml
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
work_dirs
test
val
ckpts
data
.Python
build/
ckpts/
data/
ckpts
data
test/
val/
work_dirs/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
pip-wheel-metadata/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
.python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
cluster.sh
docker-hub/MapTRv2/MapTR/LICENSE 0 → 100644
View file @ 19472568
MIT License
Copyright (c) 2022 Hust Vision Lab
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
docker-hub/MapTRv2/MapTR/README.md 0 → 100644
View file @ 19472568
<div align="center">
<h1>MapTR <img src="assets/map.png" width="30"></h1>
<h3>An End-to-End Framework for Online Vectorized HD Map Construction</h3>
[Bencheng Liao](https://github.com/LegendBC)<sup>1,2,3</sup> \*, [Shaoyu Chen](https://scholar.google.com/citations?user=PIeNN2gAAAAJ&hl=en&oi=sra)<sup>1,3</sup> \*, Yunchi Zhang<sup>1,3</sup> \*, [Bo Jiang](https://github.com/rb93dett)<sup>1,3</sup> \*,[Tianheng Cheng](https://scholar.google.com/citations?user=PH8rJHYAAAAJ&hl=zh-CN)<sup>1,3</sup>, [Qian Zhang](https://scholar.google.com/citations?user=pCY-bikAAAAJ&hl=zh-CN)<sup>3</sup>, [Wenyu Liu](http://eic.hust.edu.cn/professor/liuwenyu/)<sup>1</sup>, [Chang Huang](https://scholar.google.com/citations?user=IyyEKyIAAAAJ&hl=zh-CN)<sup>3</sup>, [Xinggang Wang](https://xinggangw.info/)<sup>1 :email:</sup>
<sup>1</sup> School of EIC, HUST, <sup>2</sup> Institute of Artificial Intelligence, HUST, <sup>3</sup> Horizon Robotics
(\*) equal contribution, (<sup>:email:</sup>) corresponding author.
ArXiv Preprint ([arXiv 2208.14437](https://arxiv.org/abs/2208.14437))
[openreview ICLR'23](https://openreview.net/forum?id=k7p_YAO7yE), accepted as **ICLR Spotlight**
extended ArXiv Preprint MapTRv2 ([arXiv 2308.05736](https://arxiv.org/abs/2308.05736))
</div>
#
### News
* **`Aug. 31th, 2023`:** initial MapTRv2 is released at ***maptrv2*** branch. Please run `git checkout maptrv2` to use it.
* **`Aug. 14th, 2023`:** As required by many researchers, the code of MapTR-based map annotation framework (VMA) will be released at https://github.com/hustvl/VMA recently.
* **`Aug. 10th, 2023`:** We release [MapTRv2](https://arxiv.org/abs/2308.05736) on Arxiv. MapTRv2 demonstrates much stronger performance and much faster convergence. To better meet the requirement of the downstream planner (like [PDM](https://github.com/autonomousvision/nuplan_garage)), we introduce an extra semantic——centerline (using path-wise modeling proposed by [LaneGAP](https://github.com/hustvl/LaneGAP)). Code & model will be released in late August. Please stay tuned!
* **`May. 12th, 2023`:** MapTR now support various bevencoder, such as [BEVFormer encoder](projects/configs/maptr/maptr_tiny_r50_24e_bevformer.py) and [BEVFusion bevpool](projects\configs\maptr\maptr_tiny_r50_24e_bevpool.py). Check it out!
* **`Apr. 20th, 2023`:** Extending MapTR to a general map annotation framework ([paper](https://arxiv.org/pdf/2304.09807.pdf), [code](https://github.com/hustvl/VMA)), with high flexibility in terms of spatial scale and element type.
* **`Mar. 22nd, 2023`:** By leveraging MapTR, VAD ([paper](https://arxiv.org/abs/2303.12077), [code](https://github.com/hustvl/VAD)) models the driving scene as fully vectorized representation, achieving SoTA end-to-end planning performance!
* **`Jan. 21st, 2023`:** MapTR is accepted to ICLR 2023 as **Spotlight Presentation**!
* **`Nov. 11st, 2022`:** We release an initial version of MapTR.
* **`Aug. 31st, 2022`:** We released our paper on Arxiv. Code/Models are coming soon. Please stay tuned! ☕️
## Introduction
<div align="center"><h4>MapTR/MapTRv2 is a simple, fast and strong online vectorized HD map construction framework.</h4></div>
![framework](assets/teaser.png "framework")
High-definition (HD) map provides abundant and precise static environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system. In this paper, we present **Map** **TR**ansformer, an end-to-end framework for online vectorized HD map construction. We propose a unified permutation-equivalent modeling approach, i.e., modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process. We design a hierarchical query embedding scheme to flexibly encode structured map information and perform hierarchical bipartite matching for map element learning. To speed up convergence, we further introduce auxiliary one-to-many matching and dense supervision. The proposed method well copes with various map elements with arbitrary shapes. It runs at real-time inference speed and achieves state-of-the-art performance on both nuScenes and Argoverse2 datasets. Abundant qualitative results show stable and robust map construction quality in complex and various driving scenes.
## Models
> Results from the [MapTRv2 paper](https://arxiv.org/abs/2308.05736)
![comparison]()
| Method | Backbone | Lr Schd | mAP| FPS|
| :---: | :---: | :---: | :---: | :---:
| MapTR | R18 | 110ep | 45.9 | 35.0|
| MapTR | R50 | 24ep | 50.3 | 15.1|
| MapTR | R50 | 110ep | 58.7|15.1|
| MapTRv2 | R18 | 110ep | 52.3 | 33.7|
| MapTRv2 | R50 | 24ep | 61.5 | 14.1|
| MapTRv2 | R50 | 110ep | 68.7 | 14.1|
| MapTRv2 | V2-99 | 110ep | 73.4 | 9.9|
**Notes**:
- FPS is measured on NVIDIA RTX3090 GPU with batch size of 1 (containing 6 view images).
- All the experiments are performed on 8 NVIDIA GeForce RTX 3090 GPUs.
> Results from this repo.
### MapTR
<div align="center"><h4> nuScenes dataset</h4></div>
| Method | Backbone | BEVEncoder |Lr Schd | mAP| FPS|memory | Config | Download |
| :---: | :---: | :---: | :---: | :---: | :---:|:---:| :---: | :---: |
| MapTR-nano | R18 |GKT | 110ep |46.3 |35.0| 11907M (bs 24) |[config](projects/configs/maptr/maptr_nano_r18_110e.py) |[model](https://drive.google.com/file/d/1-wVO1pZhFif2igJoz-s451swQvPSto2m/view?usp=sharing) / [log](https://drive.google.com/file/d/1Hd25seDQKn8Vv6AQxPfSoiu-tY2i4Haa/view?usp=sharing) |
| MapTR-tiny | R50 | GKT |24ep | 50.0 |15.1| 10287M (bs 4) | [config](projects/configs/maptr/maptr_tiny_r50_24e.py)|[model](https://drive.google.com/file/d/1n1FUFnRqdskvmpLdnsuX_VK6pET19h95/view?usp=share_link) / [log](https://drive.google.com/file/d/1nvPkk0EMHV8Q82E9usEKKYx7P38bCx1U/view?usp=share_link) |
| MapTR-tiny | R50 |GKT | 110ep | 59.3 |15.1| 10287M (bs 4)|[config](projects/configs/maptr/maptr_tiny_r50_110e.py) |[model](https://drive.google.com/file/d/1SCF93LEEmXU0hMwPiUz9p2CWbL1FpB1h/view?usp=share_link) / [log](https://drive.google.com/file/d/1TQ4j_0Sf2ipzeYsEZZAHYzX4dCUaBqyp/view?usp=share_link) |
| MapTR-tiny | Camera & LiDAR | GKT |24ep | 62.7 | 6.0 | 11858M (bs 4)|[config](projects/configs/maptr/maptr_tiny_fusion_24e.py) |[model](https://drive.google.com/file/d/1CFlJrl3ZDj3gIOysf5Cli9bX5LEYSYO4/view?usp=share_link) / [log](https://drive.google.com/file/d/1rb3S4oluxdZjNm2aJ5lBH23jrkYIaJbC/view?usp=share_link) |
| MapTR-tiny | R50 | bevpool |24ep | 50.1 | 14.7 | 9817M (bs 4)|[config](projects/configs/maptr/maptr_tiny_r50_24e_bevpool.py) |[model](https://drive.google.com/file/d/16PK9XohV55_3qPVDtpXIl4_Iumw9EnfA/view?usp=sharing) / [log](https://drive.google.com/file/d/14nioV3_VV9KehmxK7XcAHxM8X6JH5WIr/view?usp=sharing) |
| MapTR-tiny | R50 | bevformer |24ep | 48.7 | 15.0 | 10219M (bs 4)|[config](projects/configs/maptr/maptr_tiny_r50_24e_bevformer.py) |[model](https://drive.google.com/file/d/1y-UBwGBSb2xiV40AuQEBhB-xJyV7VusX/view?usp=sharing) / [log](https://drive.google.com/file/d/1r35bRhTGVtyZTP8drXBTOIhLYGCzjEaF/view?usp=sharing) |
### MapTRv2
Please `git checkout maptrv2` and follow the install instruction to use following checkpoint
<div align="center"><h4> nuScenes dataset</h4></div>
| Method | Backbone | BEVEncoder |Lr Schd | mAP| FPS|memory | Config | Download |
| :---: | :---: | :---: | :---: | :---: | :---:|:---:| :---: | :---: |
| MapTRv2| R50 |bevpool | 24ep | WIP |14.1| WIP (bs 24) |[config](https://github.com/hustvl/MapTR/blob/maptrv2/projects/configs/maptrv2/maptrv2_nusc_r50_24ep.py) |model / log |
| MapTRv2*| R50 |bevpool | 24ep | WIP |WIP| WIP (bs 24) |[config](https://github.com/hustvl/MapTR/blob/maptrv2/projects/configs/maptrv2/maptrv2_nusc_r50_24ep_w_centerline.py) |model / log |
<div align="center"><h4> Argoverse2 dataset</h4></div>
**Notes**:
- \* means that we introduce an extra semantic——centerline (using path-wise modeling proposed by [LaneGAP](https://github.com/hustvl/LaneGAP)).
## Qualitative results on nuScenes val split and Argoverse2 val split
<div align="center"><h4> MapTR/MapTRv2 maintains stable and robust map construction quality in various driving scenes.</h4></div>
![visualization](assets/MapTRv2_av2_visualizations.png "visualization")
### *MapTRv2 on whole nuScenes val split*
[**Youtube**](https://www.youtube.com/watch?v=s7McToPNlJ4)
### *MapTRv2 on whole Argoverse2 val split*
[**Youtube**](https://www.youtube.com/watch?v=nC8W_2BZuys)
<!-- ### *Sunny&Cloudy*
https://user-images.githubusercontent.com/31960625/187059686-11e4dd4b-46db-4411-b680-17ed6deebda2.mp4
### *Rainy*
https://user-images.githubusercontent.com/31960625/187059697-94622ddb-e76a-4fa7-9c44-a688d2e439c0.mp4
### *Night*
https://user-images.githubusercontent.com/31960625/187059706-f7f5a7d8-1d1d-46e0-8be3-c770cf96d694.mp4 -->
### *End-to-end Planning based on MapTR*
https://user-images.githubusercontent.com/26790424/229679664-0e9ba5e8-bf2c-45e0-abbc-36d840ee5cc9.mp4
## Getting Started
- [Installation](docs/install.md)
- [Prepare Dataset](docs/prepare_dataset.md) (Notes: annotation generation of MapTRv2 is different from MapTR )
- [Train and Eval](docs/train_eval.md)
- [Visualization](docs/visualization.md)
## Catalog
- [ ] centerline detection & topology support
- [x] multi-modal checkpoints
- [x] multi-modal code
- [ ] lidar modality code
- [x] argoverse2 dataset
- [x] Nuscenes dataset
- [x] MapTR checkpoints
- [x] MapTR code
- [x] Initialization
## Acknowledgements
MapTR is based on [mmdetection3d](https://github.com/open-mmlab/mmdetection3d). It is also greatly inspired by the following outstanding contributions to the open-source community: [BEVFusion](https://github.com/mit-han-lab/bevfusion), [BEVFormer](https://github.com/fundamentalvision/BEVFormer), [HDMapNet](https://github.com/Tsinghua-MARS-Lab/HDMapNet), [GKT](https://github.com/hustvl/GKT), [VectorMapNet](https://github.com/Mrmoore98/VectorMapNet_code).
## Citation
If you find MapTR is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.
```bibtex
@inproceedings{MapTR,
title={MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction},
author={Liao, Bencheng and Chen, Shaoyu and Wang, Xinggang and Cheng, Tianheng, and Zhang, Qian and Liu, Wenyu and Huang, Chang},
booktitle={International Conference on Learning Representations},
year={2023}
}
```
```bibtex
@inproceedings{MapTRv2,
title={MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction},
author={Liao, Bencheng and Chen, Shaoyu and Zhang, Yunchi and Jiang, Bo and Zhang, Qian and Liu, Wenyu and Huang, Chang and Wang, Xinggang},
booktitle={arXiv preprint arXiv: 2308.05736},
year={2023}
}
```
docker-hub/MapTRv2/MapTR/docs/install.md 0 → 100644
View file @ 19472568
# Step-by-step installation instructions
Following https://mmdetection3d.readthedocs.io/en/latest/getting_started.html#installation
**a. Create a conda virtual environment and activate it.**
```shell
conda create -n maptr python=3.8 -y
conda activate maptr
```
**b. Install PyTorch and torchvision following the [official instructions](https://pytorch.org/).**
```shell
pip install torch==1.9.1+cu111 torchvision==0.10.1+cu111 torchaudio==0.9.1 -f https://download.pytorch.org/whl/torch_stable.html
# Recommended torch>=1.9
```
**c. Install gcc>=5 in conda env (optional).**
```shell
conda install -c omgarcia gcc-5 # gcc-6.2
```
**c. Install mmcv-full.**
```shell
pip install mmcv-full==1.4.0
# pip install mmcv-full==1.4.0 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.9.0/index.html
```
**d. Install mmdet and mmseg.**
```shell
pip install mmdet==2.14.0
pip install mmsegmentation==0.14.1
```
**e. Install timm.**
```shell
pip install timm
```
**f. Clone MapTR.**
```
git clone https://github.com/hustvl/MapTR.git
```
**g. Install mmdet3d and GKT**
```shell
cd /path/to/MapTR/mmdetection3d
python setup.py develop
cd /path/to/MapTR/projects/mmdet3d_plugin/maptr/modules/ops/geometric_kernel_attn
python setup.py build install
```
**h. Install other requirements.**
```shell
cd /path/to/MapTR
pip install -r requirement.txt
```
**i. Prepare pretrained models.**
```shell
cd /path/to/MapTR
mkdir ckpts
cd ckpts
wget https://download.pytorch.org/models/resnet50-19c8e357.pth
wget https://download.pytorch.org/models/resnet18-f37072fd.pth
```
docker-hub/MapTRv2/MapTR/docs/prepare_dataset.md 0 → 100644
View file @ 19472568
## NuScenes
Download nuScenes V1.0 full dataset data and CAN bus expansion data [HERE](https://www.nuscenes.org/download). Prepare nuscenes data by running
**Download CAN bus expansion**
```
# download 'can_bus.zip'
unzip can_bus.zip
# move can_bus to data dir
```
**Prepare nuScenes data**
*We genetate custom annotation files which are different from mmdet3d's*
```
python tools/maptrv2/custom_nusc_map_converter.py --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes --version v1.0 --canbus ./data
```
Using the above code will generate `nuscenes_map_infos_temporal_{train,val}.pkl`, which contain local vectorized map annotations.
**Folder structure**
```
MapTR
├── mmdetection3d/
├── projects/
├── tools/
├── configs/
├── ckpts/
│ ├── r101_dcn_fcos3d_pretrain.pth
├── data/
│ ├── can_bus/
│ ├── nuscenes/
│ │ ├── maps/
│ │ ├── samples/
│ │ ├── sweeps/
│ │ ├── v1.0-test/
| | ├── v1.0-trainval/
| | ├── nuscenes_infos_temporal_train.pkl
| | ├── nuscenes_infos_temporal_val.pkl
```
## Argoverse2
Download the Argoverse2 Sensor Dataset [here](https://www.argoverse.org/av2.html#download-link).
**Folder structure**
```
MapTR
├── mmdetection3d/
├── projects/
├── tools/
├── configs/
├── ckpts/
│ ├── r101_dcn_fcos3d_pretrain.pth
├── data/
│ ├── can_bus/
│ ├── nuscenes/
│ ├── argoverse2/
│ │ ├── sensor/
| | | |—— train/
| | | |—— val/
| | | |—— test/
```
**Prepare Argoverse2 data**
*We genetate custom annotation files which are different from mmdet3d's*
```
python tools/maptrv2/custom_av2_map_converter.py --data-root ./data/argoverse2/sensor/
```
Using the above code will generate `av2_map_infos_{train,val}.pkl`, which contain local vectorized map annotations.
docker-hub/MapTRv2/MapTR/docs/train_eval.md 0 → 100644
View file @ 19472568
# Prerequisites
**Please ensure you have prepared the environment and the nuScenes dataset.**
# Train and Test
Train MapTR with 8 GPUs
```
./tools/dist_train.sh ./projects/configs/maptr/maptr_tiny_r50_24e.py 8
```
Eval MapTR with 8 GPUs
```
./tools/dist_test_map.sh ./projects/configs/maptr/maptr_tiny_r50_24e.py ./path/to/ckpts.pth 8
```
# Visualization
we provide tools for visualization and benchmark under `path/to/MapTR/tools/maptr`
\ No newline at end of file
docker-hub/MapTRv2/MapTR/docs/visualization.md 0 → 100644
View file @ 19472568
# Visualization
We provide all the visualization scripts under `/path/to/MapTR/tools/maptr/`
## Visualize prediction
```shell
cd /path/to/MapTR/
export PYTHONPATH="/path/to/MapTR/"
# visualize nuscenes dataset
python tools/maptrv2/nusc_vis_pred.py /path/to/experiment/config /path/to/experiment/ckpt
#visualize argoverse2 dataset
python tools/maptrv2/av2_vis_pred.py /path/to/experiment/config /path/to/experiment/ckpt
```
**Notes**:
- All the visualization samples will be saved in `/path/to/MapTR/work_dirs/experiment/vis_pred/` automatically. If you want to customize the saving path, you can add `--show-dir /customized_path`.
- The score threshold is set to 0.3 by default. For better visualization, you can adjust the threshold by adding `--score-thresh customized_thresh`
- The GT is visualized in fixed_num_pts format by default, we provide multiple formats to visualize GT at the same time by setting `--gt-format`: `se_pts` means the start and end points of GT, `bbox` means the bounding box envelops the GT, `polyline_pts` means the original annotated GT (you can use Douglas-Peucker algorithm to simplify the redundant annotated points).
## Merge them into video
We also provide the script to merge the input, output and GT into video to benchmark the performance qualitatively.
```shell
python tools/maptr/generate_video.py /path/to/visualization/directory
```
**Notes**:
- The video will be saved in `/path/to/MapTR/work_dirs/experiment/`
\ No newline at end of file
docker-hub/MapTRv2/MapTR/projects/configs/_base_/datasets/coco_instance.py 0 → 100644
View file @ 19472568
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_train2017.json',
img_prefix=data_root + 'train2017/',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/instances_val2017.json',
img_prefix=data_root + 'val2017/',
pipeline=test_pipeline))
evaluation = dict(metric=['bbox', 'segm'])
docker-hub/MapTRv2/MapTR/projects/configs/_base_/datasets/kitti-3d-3class.py 0 → 100644
View file @ 19472568
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Pedestrian', 'Cyclist', 'Car']
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(Car=5, Pedestrian=10, Cyclist=10)),
classes=class_names,
sample_groups=dict(Car=12, Pedestrian=6, Cyclist=6))
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# file_client_args = dict(
# backend='petrel', path_mapping=dict(data='s3://kitti_data/'))
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='LoadAnnotations3D',
with_bbox_3d=True,
with_label_3d=True,
file_client_args=file_client_args),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
translation_std=[1.0, 1.0, 0.5],
global_rot_range=[0.0, 0.0],
rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.78539816, 0.78539816],
scale_ratio_range=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False,
# we use box_type_3d='LiDAR' in kitti and nuscenes dataset
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR')),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True,
box_type_3d='LiDAR'),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True,
box_type_3d='LiDAR'))
evaluation = dict(interval=1, pipeline=eval_pipeline)
docker-hub/MapTRv2/MapTR/projects/configs/_base_/datasets/kitti-3d-car.py 0 → 100644
View file @ 19472568
# dataset settings
dataset_type = 'KittiDataset'
data_root = 'data/kitti/'
class_names = ['Car']
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
input_modality = dict(use_lidar=True, use_camera=False)
db_sampler = dict(
data_root=data_root,
info_path=data_root + 'kitti_dbinfos_train.pkl',
rate=1.0,
prepare=dict(filter_by_difficulty=[-1], filter_by_min_points=dict(Car=5)),
classes=class_names,
sample_groups=dict(Car=15))
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# file_client_args = dict(
# backend='petrel', path_mapping=dict(data='s3://kitti_data/'))
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='LoadAnnotations3D',
with_bbox_3d=True,
with_label_3d=True,
file_client_args=file_client_args),
dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='ObjectNoise',
num_try=100,
translation_std=[1.0, 1.0, 0.5],
global_rot_range=[0.0, 0.0],
rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.78539816, 0.78539816],
scale_ratio_range=[0.95, 1.05]),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=file_client_args),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=6,
workers_per_gpu=4,
train=dict(
type='RepeatDataset',
times=2,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_train.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=train_pipeline,
modality=input_modality,
classes=class_names,
test_mode=False,
# we use box_type_3d='LiDAR' in kitti and nuscenes dataset
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR')),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True,
box_type_3d='LiDAR'),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'kitti_infos_val.pkl',
split='training',
pts_prefix='velodyne_reduced',
pipeline=test_pipeline,
modality=input_modality,
classes=class_names,
test_mode=True,
box_type_3d='LiDAR'))
evaluation = dict(interval=1, pipeline=eval_pipeline)
docker-hub/MapTRv2/MapTR/projects/configs/_base_/datasets/lyft-3d.py 0 → 100644
View file @ 19472568
# If point cloud range is changed, the models should also change their point
# cloud range accordingly
point_cloud_range = [-80, -80, -5, 80, 80, 3]
# For Lyft we usually do 9-class detection
class_names = [
'car', 'truck', 'bus', 'emergency_vehicle', 'other_vehicle', 'motorcycle',
'bicycle', 'pedestrian', 'animal'
]
dataset_type = 'LyftDataset'
data_root = 'data/lyft/'
# Input modality for Lyft dataset, this is consistent with the submission
# format which requires the information in input_modality.
input_modality = dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False)
file_client_args = dict(backend='disk')
# Uncomment the following if use ceph or other file clients.
# See https://mmcv.readthedocs.io/en/latest/api.html#mmcv.fileio.FileClient
# for more details.
# file_client_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/lyft/': 's3://lyft/lyft/',
# 'data/lyft/': 's3://lyft/lyft/'
# }))
train_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.3925, 0.3925],
scale_ratio_range=[0.95, 1.05],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
test_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
# construct a pipeline for data and gt loading in show function
# please keep its loading function consistent with test_pipeline (e.g. client)
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=file_client_args),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
data = dict(
samples_per_gpu=2,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'lyft_infos_train.pkl',
pipeline=train_pipeline,
classes=class_names,
modality=input_modality,
test_mode=False),
val=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'lyft_infos_val.pkl',
pipeline=test_pipeline,
classes=class_names,
modality=input_modality,
test_mode=True),
test=dict(
type=dataset_type,
data_root=data_root,
ann_file=data_root + 'lyft_infos_test.pkl',
pipeline=test_pipeline,
classes=class_names,
modality=input_modality,
test_mode=True))
# For Lyft dataset, we usually evaluate the model at the end of training.
# Since the models are trained by 24 epochs by default, we set evaluation
# interval to be 24. Please change the interval accordingly if you do not
# use a default schedule.
evaluation = dict(interval=24, pipeline=eval_pipeline)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment