# Designing Network Design Spaces
## Introduction
<!-- [BACKBONE] -->
We implement RegNetX models in 3D detection systems and provide their first results with PointPillars on nuScenes and Lyft dataset.
The pre-trained modles are converted from [model zoo of pycls](https://github.com/facebookresearch/pycls/blob/master/MODEL_ZOO.md) and maintained in [mmcv](https://github.com/open-mmlab/mmcv).
```
@article{radosavovic2020designing,
title={Designing Network Design Spaces},
author={Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Dollár},
year={2020},
eprint={2003.13678},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
## Usage
To use a regnet model, there are two steps to do:
1. Convert the model to ResNet-style supported by MMDetection
2. Modify backbone and neck in config accordingly
### Convert model
We already prepare models of FLOPs from 800M to 12G in our model zoo.
For more general usage, we also provide script `regnet2mmdet.py` in the tools directory to convert the key of models pretrained by [pycls](https://github.com/facebookresearch/pycls/) to
ResNet-style checkpoints used in MMDetection.
```bash
python -u tools/model_converters/regnet2mmdet.py ${PRETRAIN_PATH} ${STORE_PATH}
```
This script convert model from `PRETRAIN_PATH` and store the converted model in `STORE_PATH`.
### Modify config
The users can modify the config's `depth` of backbone and corresponding keys in `arch` according to the configs in the [pycls model zoo](https://github.com/facebookresearch/pycls/blob/master/MODEL_ZOO.md).
The parameter `in_channels` in FPN can be found in the Figure 15 & 16 of the paper (`wi` in the legend).
This directory already provides some configs with their performance, using RegNetX from 800MF to 12GF level.
For other pre-trained models or self-implemented regnet models, the users are responsible to check these parameters by themselves.
**Note**: Although Fig. 15 & 16 also provide `w0`, `wa`, `wm`, `group_w`, and `bot_mul` for `arch`, they are quantized thus inaccurate, using them sometimes produces different backbone that does not match the key in the pre-trained model.
## Results
### nuScenes
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | mAP |NDS| Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
|[SECFPN](../pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d.py)|2x|16.4||35.17|49.7|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230725-0817d270.pth) | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230725.log.json)|
|[RegNetX-400MF-SECFPN](./hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d.py)| 2x |16.4||41.2|55.2|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230334-53044f32.pth) | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_nus-3d_20200620_230334.log.json)|
|[FPN](../pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|17.1||40.0|53.3|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405-2fa62f3d.pth) | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d_20200620_230405.log.json)|
|[RegNetX-400MF-FPN](./hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|17.3||44.8|56.4|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d_20200620_230239-c694dce7.pth) | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_nus-3d_20200620_230239.log.json)|
|[RegNetX-1.6gF-FPN](./hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d.py)|2x|24.0||48.2|59.3|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d_20200629_050311-dcd4e090.pth) | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d/hv_pointpillars_regnet-1.6gf_fpn_sbn-all_4x8_2x_nus-3d_20200629_050311.log.json)|
### Lyft
| Backbone | Lr schd | Mem (GB) | Inf time (fps) | Private Score | Public Score | Download |
| :---------: | :-----: | :------: | :------------: | :----: |:----: | :------: |
|[SECFPN](../pointpillars/hv_pointpillars_secfpn_sbn-all_2x8_2x_lyft-3d.py)|2x|12.2||13.9|14.1|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_secfpn_sbn-all_2x8_2x_lyft-3d_20210517_204807-2518e3de.pth) | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_secfpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_secfpn_sbn-all_2x8_2x_lyft-3d_20210517_204807.log.json)|
|[RegNetX-400MF-SECFPN](./hv_pointpillars_regnet-400mf_secfpn_sbn-all_4x8_2x_lyft-3d.py)| 2x |15.9||14.9|15.1|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d_20210524_092151-42513826.pth) | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_regnet-400mf_secfpn_sbn-all_2x8_2x_lyft-3d_20210524_092151.log.json)|
|[FPN](../pointpillars/hv_pointpillars_fpn_sbn-all_2x8_2x_lyft-3d.py)|2x|9.2||14.9|15.1|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_fpn_sbn-all_2x8_2x_lyft-3d_20210517_202818-fc6904c3.pth) | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/pointpillars/hv_pointpillars_fpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_fpn_sbn-all_2x8_2x_lyft-3d_20210517_202818.log.json)|
|[RegNetX-400MF-FPN](./hv_pointpillars_regnet-400mf_fpn_sbn-all_4x8_2x_lyft-3d.py)|2x|13.0||16.0|16.1|[model](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d_20210521_115618-823dcf18.pth) | [log](https://download.openmmlab.com/mmdetection3d/v0.1.0_models/regnet/hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d/hv_pointpillars_regnet-400mf_fpn_sbn-all_2x8_2x_lyft-3d_20210521_115618.log.json)|
没有合适的资源?快使用搜索试试~ 我知道了~
原公用机算法,公用机系统重装之前
共870个文件
py:342个
pyc:239个
bin:34个
需积分: 0 0 下载量 25 浏览量
2024-02-07
14:56:18
上传
评论
收藏 186.18MB ZIP 举报
温馨提示
原公用机算法,公用机系统重装之前
资源推荐
资源详情
资源评论
收起资源包目录
原公用机算法,公用机系统重装之前 (870个子文件)
features_data_6_32_88_160.bin 10.31MB
features_data_6_40_110_64.bin 6.45MB
features_data_6_32_88_80.bin 5.16MB
features_data_6_32_88_64.bin 4.13MB
features_data_6_16_44_160.bin 2.58MB
features_data_6_16_44_80.bin 1.29MB
features_data_6_16_44_64.bin 1.03MB
lut.bin 768KB
CMakeDetermineCompilerABI_CUDA.bin 728KB
CMakeDetermineCompilerABI_CXX.bin 16KB
CMakeDetermineCompilerABI_C.bin 16KB
projection_data_d9.bin 288B
projection_data_d40_110.bin 288B
projection_data_d32_88.bin 288B
projection_data_d16_44.bin 288B
projection_data.bin 288B
n_voxels_data_128_128_6.bin 12B
n_voxels_data_128_128_1.bin 12B
voxel_size_data_05_05_6.bin 12B
voxel_size_data_05_05_005.bin 12B
n_voxels_data_64_64_12.bin 12B
voxel_size_data_05_05_3.bin 12B
voxel_size_data_05_05_025.bin 12B
voxel_size_data_05_05_1.bin 12B
n_voxels_data_256_256_1.bin 12B
n_voxels_data_256_256_6.bin 12B
n_voxels_data_128_128_12.bin 12B
n_voxels_data_256_256_12.bin 12B
voxel_size_data_05_05_019.bin 12B
voxel_size_data_078_078_05.bin 12B
voxel_size_data_039_039_05.bin 12B
voxel_size_data_1_1_05.bin 12B
voxel_size_data_039_039_1.bin 12B
voxel_size_data_078_078_1.bin 12B
CMakeCCompilerId.c 20KB
CMakeCUDACompilerId.fatbin.c 4KB
a_dlink.fatbin.c 3KB
CMakeCUDACompilerId.cudafe1.c 1KB
CMakeCUDACompilerId.cudafe1.stub.c 740B
a_dlink.reg.c 32B
indice.cc 4KB
maxpool.cc 3KB
reordering.cc 2KB
all.cc 2KB
setup.cfg 609B
cmake.check_cache 85B
CMakeCXXCompiler.cmake 5KB
Makefile.cmake 3KB
CMakeCCompiler.cmake 2KB
cmake_install.cmake 2KB
CMakeCUDACompiler.cmake 2KB
DependInfo.cmake 2KB
cmake_install.cmake 1KB
DependInfo.cmake 828B
CMakeDirectoryInformation.cmake 710B
CMakeDirectoryInformation.cmake 710B
cmake_clean.cmake 508B
CMakeSystem.cmake 402B
cmake_clean.cmake 257B
CMakeCUDACompilerId.cudafe1.cpp 607KB
CMakeCXXCompilerId.cpp 20KB
view_transformer.cpp 17KB
iou3d.cpp 7KB
voxelization_cpu.cpp 6KB
roiaware_pool3d.cpp 6KB
interpolate.cpp 4KB
scatter_points_cpu.cpp 4KB
furthest_point_sample.cpp 3KB
group_points.cpp 2KB
points_in_boxes_cpu.cpp 2KB
gather_points.cpp 2KB
ball_query.cpp 2KB
tensor.cpp 1KB
knn.cpp 1KB
assign_score_withk.cpp 1KB
voxelization.cpp 510B
main.cpp 494B
maxpool_cuda.cu 18KB
iou3d_kernel.cu 15KB
roiaware_pool3d_kernel.cu 15KB
voxelization_cuda.cu 14KB
scatter_points_cuda.cu 11KB
furthest_point_sample_cuda.cu 11KB
assign_score_withk_cuda.cu 9KB
CMakeCUDACompilerId.cu 9KB
points_in_boxes_cuda.cu 8KB
indice_cuda.cu 7KB
reordering_cuda.cu 6KB
cuda_accelerated_functions_cu_project_v3.cu 4KB
group_points_cuda.cu 4KB
three_interpolate_cuda.cu 4KB
knn_cuda.cu 3KB
gather_points_cuda.cu 3KB
ball_query_cuda.cu 2KB
three_nn_cuda.cu 2KB
CMakeCUDACompilerId.sm_52.cubin 952B
a_dlink.sm_52.cubin 952B
furthest_point_sample_ext.cp38-win_amd64.exp 16KB
assign_score_withk_ext.cp38-win_amd64.exp 16KB
roiaware_pool3d_ext.cp38-win_amd64.exp 16KB
共 870 条
- 1
- 2
- 3
- 4
- 5
- 6
- 9
资源评论
weixin_52019990
- 粉丝: 0
- 资源: 70
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 软件开发-数据处理-富文本解析、折线图、MD5、Bluebird-编程工具-富文本解析,折线图,MD5,Bluebird.zip
- 《LEARNING Vue.js》是一本免费电子书,由Stack Overflow社区的贡献者们创建和编写
- centos:7 docker镜像
- 基于STM32微控制器的步进电机的S曲线库
- “人力资源+大数据+薪酬报告+涨薪调薪”
- “人力资源+大数据+薪酬报告+涨薪调薪”
- Atm Rush 银行柜员跑酷向上Unity益智休闲跑酷游戏项目源码C#
- 不需要登录就能用的简单代码生成器
- Visualstudio2012C指导教程pdf
- IGBT损耗模型-IGBT电热-IGBT建模-IPOSIM7-6b.zip
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功