# RegNet
> [Designing Network Design Spaces](https://arxiv.org/abs/2003.13678)
<!-- [BACKBONE] -->
## Abstract
In this work, we present a new network design paradigm. Our goal is to help advance the understanding of network design and discover design principles that generalize across settings. Instead of focusing on designing individual network instances, we design network design spaces that parametrize populations of networks. The overall process is analogous to classic manual design of networks, but elevated to the design space level. Using our methodology we explore the structure aspect of network design and arrive at a low-dimensional design space consisting of simple, regular networks that we call RegNet. The core insight of the RegNet parametrization is surprisingly simple: widths and depths of good networks can be explained by a quantized linear function. We analyze the RegNet design space and arrive at interesting findings that do not match the current practice of network design. The RegNet design space provides simple and fast networks that work well across a wide range of flop regimes. Under comparable training settings and flops, the RegNet models outperform the popular EfficientNet models while being up to 5x faster on GPUs.
<div align=center>
<img src="https://user-images.githubusercontent.com/40661020/143971942-da50f719-61e9-43bd-9468-0dbfbe80284e.png"/>
</div>
## Introduction
We implement RegNetX and RegNetY models in detection systems and provide their first results on Mask R-CNN, Faster R-CNN and RetinaNet.
The pre-trained models are converted from [model zoo of pycls](https://github.com/facebookresearch/pycls/blob/master/MODEL_ZOO.md).
## 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 400M 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 and Models
### Mask R-CNN
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
| :---------: | :-----: | :-----: | :------: | :------------: | :----: | :-----: | :------: | :--------: |
| [R-50-FPN](../mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py)| pytorch | 1x | 4.4 | 12.0 | 38.2 | 34.7 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205-d4b0c5d6.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205_050542.log.json) |
|[RegNetX-3.2GF-FPN](./mask_rcnn_regnetx-3.2GF_fpn_1x_coco.py)| pytorch | 1x |5.0 ||40.3|36.6|[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/regnet/mask_rcnn_regnetx-3.2GF_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-3.2GF_fpn_1x_coco/mask_rcnn_regnetx-3.2GF_fpn_1x_coco_20200520_163141-2a9d1814.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-3.2GF_fpn_1x_coco/mask_rcnn_regnetx-3.2GF_fpn_1x_coco_20200520_163141.log.json) |
|[RegNetX-4.0GF-FPN](./mask_rcnn_regnetx-4GF_fpn_1x_coco.py)| pytorch | 1x |5.5||41.5|37.4|[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/regnet/mask_rcnn_regnetx-4GF_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-4GF_fpn_1x_coco/mask_rcnn_regnetx-4GF_fpn_1x_coco_20200517_180217-32e9c92d.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-4GF_fpn_1x_coco/mask_rcnn_regnetx-4GF_fpn_1x_coco_20200517_180217.log.json) |
| [R-101-FPN](../mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py)| pytorch | 1x | 6.4 | 10.3 | 40.0 | 36.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r101_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r101_fpn_1x_coco/mask_rcnn_r101_fpn_1x_coco_20200204-1efe0ed5.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r101_fpn_1x_coco/mask_rcnn_r101_fpn_1x_coco_20200204_144809.log.json) |
|[RegNetX-6.4GF-FPN](./mask_rcnn_regnetx-6.4GF_fpn_1x_coco.py)| pytorch | 1x |6.1 ||41.0|37.1|[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/regnet/mask_rcnn_regnetx-6.4GF_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-6.4GF_fpn_1x_coco/mask_rcnn_regnetx-6.4GF_fpn_1x_coco_20200517_180439-3a7aae83.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-6.4GF_fpn_1x_coco/mask_rcnn_regnetx-6.4GF_fpn_1x_coco_20200517_180439.log.json) |
| [X-101-32x4d-FPN](../mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco.py) | pytorch | 1x | 7.6 | 9.4 | 41.9 | 37.5 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco/mask_rcnn_x101_32x4d_fpn_1x_coco_20200205-478d0b67.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_x101_32x4d_fpn_1x_coco/mask_rcnn_x101_32x4d_fpn_1x_coco_20200205_034906.log.json) |
|[RegNetX-8.0GF-FPN](./mask_rcnn_regnetx-8GF_fpn_1x_coco.py)| pytorch | 1x |6.4 ||41.7|37.5|[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/regnet/mask_rcnn_regnetx-8GF_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-8GF_fpn_1x_coco/mask_rcnn_regnetx-8GF_fpn_1x_coco_20200517_180515-09daa87e.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-8GF_fpn_1x_coco/mask_rcnn_regnetx-8GF_fpn_1x_coco_20200517_180515.log.json) |
|[RegNetX-12GF-FPN](./mask_rcnn_regnetx-12GF_fpn_1x_coco.py)| pytorch | 1x |7.4 ||42.2|38|[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/regnet/mask_rcnn_regnetx-12GF_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-12GF_fpn_1x_coco/mask_rcnn_regnetx-12GF_fpn_1x_coco_20200517_180552-b538bd8b.pth) | [log](https://download.openmmlab.com/mmdetection/v2.0/regnet/mask_rcnn_regnetx-12GF_fpn_1x_coco/mask_rcnn_regnetx-12GF_fpn_1x_coco_20200517_180552.log.json) |
|[RegNetX-3.2GF-FPN-DCN-C3-C5](./mask_rcnn_regnetx-3.2GF_fpn_mdconv_c3-c5_1x_coco.py)| pytorch | 1x |5.0 ||40.3|36.6|[config](https://github.com/open-mmlab/mmdetection/tre
没有合适的资源?快使用搜索试试~ 我知道了~
MMDetection实战:MMDetection训练与测试
共2000个文件
jpg:2571个
py:1474个
pyc:343个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
5星 · 超过95%的资源 19 下载量 147 浏览量
2022-05-09
21:20:23
上传
评论 1
收藏 749.6MB ZIP 举报
温馨提示
MMDetection是商汤和港中文大学针对目标检测任务推出的一个开源项目,它基于Pytorch实现了大量的目标检测算法,把数据集构建、模型搭建、训练策略等过程都封装成了一个个模块,通过模块调用的方式,我们能够以很少的代码量实现一个新算法,大大提高了代码复用率。 GitHub链接:https://github.com/open-mmlab/mmdetection。 Gitee链接:https://gitee.com/open-mmlab/mmdetection。 主分支代码目前支持 PyTorch 1.5 以上的版本。主要特性: 模块化设计 MMDetection 将检测框架解耦成不同的模块组件,通过组合不同的模块组件,用户可以便捷地构建自定义的检测模型 丰富的即插即用的算法和模型 MMDetection 支持了众多主流的和最新的检测算法,例如 Faster R-CNN,Mask R-CNN,RetinaNet 等。 速度快 基本的框和 mask 操作都实现了 GPU 版本,训练速度比其他代码库更快或者相当,包括 Detectron2, maskrcnn-benchm
资源推荐
资源详情
资源评论
收起资源包目录
MMDetection实战:MMDetection训练与测试 (2000个子文件)
make.bat 760B
make.bat 760B
CITATION.cff 273B
setup.cfg 640B
readthedocs.css 140B
readthedocs.css 140B
Dockerfile 1KB
Dockerfile 894B
mmdet-2.24.1-py3.7.egg 1.8MB
.gitignore 1KB
MANIFEST.in 205B
pytest.ini 293B
MMDet_InstanceSeg_Tutorial.ipynb 15.95MB
MMDet_Tutorial.ipynb 12.32MB
inference_demo.ipynb 1.02MB
zhihu_qrcode.jpg 388KB
result.jpg 335KB
36-57_270.jpg 334KB
36-57_90.jpg 332KB
36-57_180.jpg 330KB
36-57.jpg 328KB
36-37_270.jpg 321KB
36-37_90.jpg 318KB
36-37_180.jpg 315KB
36-37.jpg 314KB
36-19_270.jpg 304KB
36-19_90.jpg 299KB
36-19_180.jpg 297KB
36-19.jpg 295KB
36-35_270.jpg 294KB
36-17_270.jpg 293KB
36-35_90.jpg 291KB
36-17_90.jpg 289KB
36-36_270.jpg 288KB
36-35_180.jpg 287KB
36-17_180.jpg 287KB
36-35.jpg 287KB
36-17.jpg 286KB
36-36_90.jpg 285KB
36-34_270.jpg 284KB
36-24_270.jpg 284KB
2.jpg 284KB
36-24_180.jpg 283KB
36-25_90.jpg 283KB
36-34_90.jpg 283KB
36-18_270.jpg 283KB
36-36_180.jpg 283KB
36-25_270.jpg 283KB
36-36.jpg 282KB
36-25_180.jpg 282KB
36-24.jpg 281KB
50-1_90.jpg 281KB
36-18_90.jpg 281KB
36-34_180.jpg 281KB
36-34.jpg 280KB
36-25.jpg 280KB
50-1.jpg 278KB
36-18_180.jpg 278KB
36-41_270.jpg 278KB
36-18.jpg 278KB
36-41_90.jpg 275KB
36-41_180.jpg 273KB
36-41.jpg 273KB
36-22_270.jpg 271KB
36-22_90.jpg 270KB
36-23_90.jpg 269KB
36-38_90.jpg 269KB
36-22_180.jpg 268KB
36-39_90.jpg 268KB
36-23_270.jpg 268KB
36-22.jpg 268KB
36-38_180.jpg 268KB
36-23_180.jpg 268KB
36-38_270.jpg 267KB
36-23.jpg 267KB
36-39_180.jpg 266KB
36-20_270.jpg 266KB
36-38.jpg 266KB
36-39_270.jpg 266KB
36-39.jpg 264KB
36-20_90.jpg 263KB
144_90.jpg 261KB
36-20_180.jpg 261KB
144_270.jpg 261KB
36-20.jpg 260KB
31-2_270.jpg 260KB
50-3_270.jpg 258KB
144_180.jpg 258KB
31-2_90.jpg 258KB
144.jpg 257KB
50-3_90.jpg 257KB
36-26.jpg 256KB
50-3.jpg 255KB
31-2_180.jpg 255KB
31-2.jpg 254KB
demo.jpg 254KB
36-31_270.jpg 253KB
50-3_180.jpg 252KB
36-10_270.jpg 252KB
36-32_270.jpg 251KB
共 2000 条
- 1
- 2
- 3
- 4
- 5
- 6
- 20
AI浩
- 粉丝: 14w+
- 资源: 216
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
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
- 1
- 2
- 3
- 4
前往页