# High-resolution networks (HRNets) for object detection
## Introduction
```
@inproceedings{SunXLW19,
title={Deep High-Resolution Representation Learning for Human Pose Estimation},
author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang},
booktitle={CVPR},
year={2019}
}
@article{SunZJCXLMWLW19,
title={High-Resolution Representations for Labeling Pixels and Regions},
author={Ke Sun and Yang Zhao and Borui Jiang and Tianheng Cheng and Bin Xiao
and Dong Liu and Yadong Mu and Xinggang Wang and Wenyu Liu and Jingdong Wang},
journal = {CoRR},
volume = {abs/1904.04514},
year={2019}
}
```
## Results and Models
### Faster R-CNN
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Download |
| :-------------: | :-----: | :-----: | :------: | :-------------:|:------:| :-------:|
| HRNetV2p-W18 | pytorch | 1x | 6.6 | 13.4 | 36.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/faster_rcnn_hrnetv2p_w18_1x_coco/faster_rcnn_hrnetv2p_w18_1x_coco_20200130-56651a6d.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/faster_rcnn_hrnetv2p_w18_1x_coco/faster_rcnn_hrnetv2p_w18_1x_coco_20200130_211246.log.json) |
| HRNetV2p-W18 | pytorch | 2x | | | | |
| HRNetV2p-W32 | pytorch | 1x | 9.0 | 12.4 | 40.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/faster_rcnn_hrnetv2p_w32_1x_coco/faster_rcnn_hrnetv2p_w32_1x_coco_20200130-6e286425.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/faster_rcnn_hrnetv2p_w32_1x_coco/faster_rcnn_hrnetv2p_w32_1x_coco_20200130_204442.log.json) |
| HRNetV2p-W32 | pytorch | 2x | | | | |
| HRNetV2p-W48 | pytorch | 1x | 10.4 | 10.5 | 41.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/faster_rcnn_hrnetv2p_w40_1x_coco/faster_rcnn_hrnetv2p_w40_1x_coco_20200210-95c1f5ce.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/faster_rcnn_hrnetv2p_w40_1x_coco/faster_rcnn_hrnetv2p_w40_1x_coco_20200210_125315.log.json) |
| HRNetV2p-W40 | pytorch | 2x | 10.4 | | 42.1 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/faster_rcnn_hrnetv2p_w40_2x_coco/faster_rcnn_hrnetv2p_w40_2x_coco_20200512_161033-0f236ef4.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/faster_rcnn_hrnetv2p_w40_2x_coco/faster_rcnn_hrnetv2p_w40_2x_coco_20200512_161033.log.json) |
### Mask R-CNN
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Download |
| :-------------: | :-----: | :-----: | :------: | :-------------:|:------:| :------:|:--------:|
| HRNetV2p-W18 | pytorch | 1x | 7.0 | 11.7 | 37.7 | 34.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w18_1x_coco/mask_rcnn_hrnetv2p_w18_1x_coco_20200205-1c3d78ed.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w18_1x_coco/mask_rcnn_hrnetv2p_w18_1x_coco_20200205_232523.log.json) |
| HRNetV2p-W18 | pytorch | 2x | 7.0 | - | 39.8 | 36.0 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w18_2x_coco/mask_rcnn_hrnetv2p_w18_2x_coco_20200212-b3c825b1.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w18_2x_coco/mask_rcnn_hrnetv2p_w18_2x_coco_20200212_134222.log.json) |
| HRNetV2p-W32 | pytorch | 1x | 9.4 | 11.3 | 41.2 | 37.1 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w32_1x_coco/mask_rcnn_hrnetv2p_w32_1x_coco_20200207-b29f616e.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w32_1x_coco/mask_rcnn_hrnetv2p_w32_1x_coco_20200207_055017.log.json) |
| HRNetV2p-W32 | pytorch | 2x | 9.4 | - | 42.5 | 37.8 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w32_2x_coco/mask_rcnn_hrnetv2p_w32_2x_coco_20200213-45b75b4d.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w32_2x_coco/mask_rcnn_hrnetv2p_w32_2x_coco_20200213_150518.log.json) |
| HRNetV2p-W40 | pytorch | 1x | 10.9 | | 42.1 | 37.5 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w40_1x_coco/mask_rcnn_hrnetv2p_w40_1x_coco_20200511_015646-66738b35.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w40_1x_coco/mask_rcnn_hrnetv2p_w40_1x_coco_20200511_015646.log.json) |
| HRNetV2p-W40 | pytorch | 2x | 10.9 | | 42.8 | 38.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w40_2x_coco/mask_rcnn_hrnetv2p_w40_2x_coco_20200512_163732-aed5e4ab.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/mask_rcnn_hrnetv2p_w40_2x_coco/mask_rcnn_hrnetv2p_w40_2x_coco_20200512_163732.log.json) |
### Cascade R-CNN
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Download |
| :-------------: | :-----: | :-----: | :------: | :-------------:|:------:| :-------:|
| HRNetV2p-W18 | pytorch | 20e | 7.0 | 11.0 | 41.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w18_20e_coco/cascade_rcnn_hrnetv2p_w18_20e_coco_20200210-434be9d7.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w18_20e_coco/cascade_rcnn_hrnetv2p_w18_20e_coco_20200210_105632.log.json) |
| HRNetV2p-W32 | pytorch | 20e | 9.4 | 11.0 | 43.3 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w32_20e_coco/cascade_rcnn_hrnetv2p_w32_20e_coco_20200208-928455a4.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w32_20e_coco/cascade_rcnn_hrnetv2p_w32_20e_coco_20200208_160511.log.json) |
| HRNetV2p-W40 | pytorch | 20e | 10.8 | | 43.8 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w40_20e_coco/cascade_rcnn_hrnetv2p_w40_20e_coco_20200512_161112-75e47b04.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/cascade_rcnn_hrnetv2p_w40_20e_coco/cascade_rcnn_hrnetv2p_w40_20e_coco_20200512_161112.log.json) |
### Cascade Mask R-CNN
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Download |
| :-------------: | :-----: | :-----: | :------: | :-------------:|:------:| :------:|:--------:|
| HRNetV2p-W18 | pytorch | 20e | | 8.5 | | | |
| HRNetV2p-W32 | pytorch | 20e | | 8.3 |44.3 |38.6 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e_coco/cascade_mask_rcnn_hrnetv2p_w32_20e_coco_20200512_154043-39d9cf7b.pth) | [log](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e_coco/cascade_mask_rcnn_hrnetv2p_w32_20e_coco_20200512_154043.log.json) |
| HRNetV2p-W40 | pytorch | 20e | | | | | |
### Hybrid Task Cascade (HTC)
| Backbone | Style | Lr
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
>>经历过配r3det环境时,包版本冲突的绝望吗?经历过r3det的dockerfile依旧包版本冲突的绝望吗?经历过r3det的dockerfile挑docker版本的绝望吗?<< (本压缩包内置了一张测试图片和预训练模型。) 【亮点】:开袋即食!开袋即食!开袋即食! 按照压缩包中写的使用说明,可以顺利的完成环境配置,跑通该项目。
资源推荐
资源详情
资源评论
收起资源包目录
r3det【避雷指南】pytorch版 (1110个子文件)
make.bat 795B
.isort.cfg 357B
deform_conv_cuda.cpp 28KB
roi_align_v2.cpp 15KB
nms_cpu.cpp 9KB
corner_pool.cpp 9KB
rnms_cpu.cpp 9KB
polygon_geo_cpu.cpp 8KB
deform_conv_ext.cpp 7KB
roi_align_ext.cpp 7KB
carafe_cuda.cpp 5KB
deform_pool_cuda.cpp 4KB
roi_pool_ext.cpp 3KB
deform_pool_ext.cpp 3KB
carafe_naive_cuda.cpp 3KB
masked_conv2d_cuda.cpp 3KB
sigmoid_focal_loss_ext.cpp 2KB
carafe_ext.cpp 2KB
masked_conv2d_ext.cpp 2KB
carafe_naive_ext.cpp 2KB
nms_ext.cpp 2KB
feature_refine_cuda.cpp 2KB
compiling_info.cpp 1KB
rbbox_geo_cuda.cpp 1KB
rnms_ext.cpp 773B
rnms_cuda.cpp 507B
nms_cuda.cpp 507B
deform_conv_cuda_kernel.cu 42KB
carafe_cuda_kernel.cu 20KB
deform_pool_cuda_kernel.cu 16KB
roi_align_kernel_v2.cu 13KB
rbbox_geo_kernel.cu 12KB
rnms_kernel.cu 11KB
roi_align_kernel.cu 11KB
feature_refine_kernel.cu 9KB
carafe_naive_cuda_kernel.cu 7KB
roi_pool_kernel.cu 7KB
sigmoid_focal_loss_cuda.cu 6KB
masked_conv2d_kernel.cu 5KB
nms_kernel.cu 5KB
Dockerfile 783B
mmdet-2.1.0+unknown-py3.7-linux-x86_64.egg 32.46MB
.gitignore 1KB
pytest.ini 293B
mmdet_inference_colab.ipynb 1.3MB
inference_demo.ipynb 1.02MB
vis3.jpg 1.25MB
vis1.jpg 1.12MB
vis2.jpg 875KB
demo.jpg 254KB
coco_test_12510.jpg 179KB
gray.jpg 38KB
color.jpg 35KB
LICENSE 11KB
Makefile 634B
config.md 30KB
getting_started.md 17KB
changelog.md 17KB
README.md 13KB
README.md 12KB
README.md 12KB
model_zoo.md 12KB
new_modules.md 11KB
new_dataset.md 10KB
README.md 10KB
README.md 9KB
README.md 8KB
README.md 7KB
README.md 7KB
compatibility.md 7KB
README.md 7KB
README.md 6KB
README.md 6KB
robustness_benchmarking.md 5KB
README.md 5KB
install.md 5KB
data_pipeline.md 5KB
README.md 5KB
README.md 4KB
README.md 4KB
projects.md 4KB
README.md 4KB
README.md 4KB
README.md 4KB
README.md 4KB
finetune.md 4KB
README.md 4KB
README.md 3KB
README.md 3KB
CODE_OF_CONDUCT.md 3KB
README.md 3KB
README.md 3KB
README.md 3KB
README.md 3KB
README.md 3KB
README.md 3KB
reimplementation_questions.md 3KB
README.md 3KB
README.md 2KB
README.md 2KB
共 1110 条
- 1
- 2
- 3
- 4
- 5
- 6
- 12
资源评论
- zhou_d_p2022-01-12没有任何作用
sysylar
- 粉丝: 60
- 资源: 8
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
- 笔记实验六,spark,大数据分析
- ####蓝桥杯python的详细的信息介绍
- 电子万年历软件仿真(经过多次修改,保证正确性)
- Unity XR 手势射击控制脚本(适用于任何可手势识别的设备)
- 机械设计全自动电表(NB和IC卡表)控制和上壳装配线sw16可编辑非常好的设计图纸100%好用.zip
- 基于matlab的EAN-13条形码识别系统GUI界面.zip代码53
- matlab基于bp神经网络交通信号标志识别GUI界面13个标志.zip代码54
- 电子万年历答辩实物展示视频mp4格式
- 基于python实现的程序,包括哈希感知算法cvHash,图像切割cvsplit,固定目标检测cvRec(附文档ppt)等
- 计算0-10000之间所有偶数的和
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