# PointRend: Image Segmentation as Rendering
Alexander Kirillov, Yuxin Wu, Kaiming He, Ross Girshick
[[`arXiv`](https://arxiv.org/abs/1912.08193)] [[`BibTeX`](#CitingPointRend)]
<div align="center">
<img src="https://alexander-kirillov.github.io/images/kirillov2019pointrend.jpg"/>
</div><br/>
In this repository, we release code for PointRend in Detectron2. PointRend can be flexibly applied to both instance and semantic segmentation tasks by building on top of existing state-of-the-art models.
## Installation
Install Detectron2 following [the instructions](https://detectron2.readthedocs.io/tutorials/install.html). You are ready to go!
## Quick start and visualization
This [Colab Notebook](https://colab.research.google.com/drive/1isGPL5h5_cKoPPhVL9XhMokRtHDvmMVL) tutorial contains examples of PointRend usage and visualizations of its point sampling stages.
## Training
To train a model with 8 GPUs run:
```bash
cd /path/to/detectron2/projects/PointRend
python train_net.py --config-file configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco.yaml --num-gpus 8
```
## Evaluation
Model evaluation can be done similarly:
```bash
cd /path/to/detectron2/projects/PointRend
python train_net.py --config-file configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco.yaml --eval-only MODEL.WEIGHTS /path/to/model_checkpoint
```
# Pretrained Models
## Instance Segmentation
#### COCO
<table><tbody>
<!-- START TABLE -->
<!-- TABLE HEADER -->
<th valign="bottom">Mask<br/>head</th>
<th valign="bottom">Backbone</th>
<th valign="bottom">lr<br/>sched</th>
<th valign="bottom">Output<br/>resolution</th>
<th valign="bottom">mask<br/>AP</th>
<th valign="bottom">mask<br/>AP*</th>
<th valign="bottom">model id</th>
<th valign="bottom">download</th>
<!-- TABLE BODY -->
<tr><td align="left"><a href="configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco.yaml">PointRend</a></td>
<td align="center">R50-FPN</td>
<td align="center">1×</td>
<td align="center">224×224</td>
<td align="center">36.2</td>
<td align="center">39.7</td>
<td align="center">164254221</td>
<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/PointRend/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco/164254221/model_final_88c6f8.pkl">model</a> | <a href="https://dl.fbaipublicfiles.com/detectron2/PointRend/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_coco/164254221/metrics.json">metrics</a></td>
</tr>
<tr><td align="left"><a href="configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_3x_coco.yaml">PointRend</a></td>
<td align="center">R50-FPN</td>
<td align="center">3×</td>
<td align="center">224×224</td>
<td align="center">38.3</td>
<td align="center">41.6</td>
<td align="center">164955410</td>
<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/PointRend/InstanceSegmentation/pointrend_rcnn_R_50_FPN_3x_coco/164955410/model_final_3c3198.pkl">model</a> | <a href="https://dl.fbaipublicfiles.com/detectron2/PointRend/InstanceSegmentation/pointrend_rcnn_R_50_FPN_3x_coco/164955410/metrics.json">metrics</a></td>
</tr>
</tbody></table>
AP* is COCO mask AP evaluated against the higher-quality LVIS annotations; see the paper for details. Run `python detectron2/datasets/prepare_cocofied_lvis.py` to prepare GT files for AP* evaluation. Since LVIS annotations are not exhaustive `lvis-api` and not `cocoapi` should be used to evaluate AP*.
#### Cityscapes
Cityscapes model is trained with ImageNet pretraining.
<table><tbody>
<!-- START TABLE -->
<!-- TABLE HEADER -->
<th valign="bottom">Mask<br/>head</th>
<th valign="bottom">Backbone</th>
<th valign="bottom">lr<br/>sched</th>
<th valign="bottom">Output<br/>resolution</th>
<th valign="bottom">mask<br/>AP</th>
<th valign="bottom">model id</th>
<th valign="bottom">download</th>
<!-- TABLE BODY -->
<tr><td align="left"><a href="configs/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_cityscapes.yaml">PointRend</a></td>
<td align="center">R50-FPN</td>
<td align="center">1×</td>
<td align="center">224×224</td>
<td align="center">35.9</td>
<td align="center">164255101</td>
<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/PointRend/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_cityscapes/164255101/model_final_318a02.pkl">model</a> | <a href="https://dl.fbaipublicfiles.com/detectron2/PointRend/InstanceSegmentation/pointrend_rcnn_R_50_FPN_1x_cityscapes/164255101/metrics.json">metrics</a></td>
</tr>
</tbody></table>
## Semantic Segmentation
#### Cityscapes
Cityscapes model is trained with ImageNet pretraining.
<table><tbody>
<!-- START TABLE -->
<!-- TABLE HEADER -->
<th valign="bottom">Method</th>
<th valign="bottom">Backbone</th>
<th valign="bottom">Output<br/>resolution</th>
<th valign="bottom">mIoU</th>
<th valign="bottom">model id</th>
<th valign="bottom">download</th>
<!-- TABLE BODY -->
<tr><td align="left"><a href="configs/SemanticSegmentation/pointrend_semantic_R_101_FPN_1x_cityscapes.yaml">SemanticFPN + PointRend</a></td>
<td align="center">R101-FPN</td>
<td align="center">1024×2048</td>
<td align="center">78.6</td>
<td align="center">186480235</td>
<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/PointRend/SemanticSegmentation/pointrend_semantic_R_101_FPN_1x_cityscapes/186480235/model_final_5f3665.pkl">model</a> | <a href="https://dl.fbaipublicfiles.com/detectron2/PointRend/SemanticSegmentation/pointrend_semantic_R_101_FPN_1x_cityscapes/186480235/metrics.json">metrics</a></td>
</tr>
</tbody></table>
## <a name="CitingPointRend"></a>Citing PointRend
If you use PointRend, please use the following BibTeX entry.
```BibTeX
@InProceedings{kirillov2019pointrend,
title={{PointRend}: Image Segmentation as Rendering},
author={Alexander Kirillov and Yuxin Wu and Kaiming He and Ross Girshick},
journal={ArXiv:1912.08193},
year={2019}
}
```
没有合适的资源?快使用搜索试试~ 我知道了~
detectron2-maskrcnn
共974个文件
py:362个
yaml:314个
pyc:113个
需积分: 45 2 下载量 197 浏览量
2022-04-10
18:29:13
上传
评论
收藏 657.86MB RAR 举报
温馨提示
detectron2训练自己的图像集
资源详情
资源评论
资源推荐
收起资源包目录
detectron2-maskrcnn (974个子文件)
events.out.tfevents.1592218228.DESKTOP-2SUSMGO.21540.0 2KB
pkg_helpers.bash 2KB
00011.bmp 2.64MB
setup.cfg 819B
.clang-format 2KB
ROIAlignRotated_cpu.cpp 16KB
ROIAlign_cpu.cpp 15KB
caffe2_mask_rcnn.cpp 4KB
vision.cpp 3KB
torchscript_traced_mask_rcnn.cpp 3KB
nms_rotated_cpu.cpp 2KB
box_iou_rotated_cpu.cpp 1KB
vision.cpp 449B
custom.css 257B
deform_conv_cuda_kernel.cu 43KB
deform_conv_cuda.cu 32KB
ROIAlignRotated_cuda.cu 14KB
ROIAlign_cuda.cu 13KB
SwapAlign2Nat_cuda.cu 13KB
nms_rotated_cuda.cu 5KB
box_iou_rotated_cuda.cu 4KB
cuda_version.cu 643B
Dockerfile 2KB
Dockerfile-circleci 650B
_C.cp37-win_amd64.exp 7KB
.flake8 327B
.gitignore 469B
.gitignore 7B
variant.h 105KB
order_preserving_flat_hash_map.h 66KB
flat_hash_map.h 62KB
box_iou_rotated_utils.h 10KB
deform_conv.h 8KB
ROIAlign.h 3KB
ROIAlignRotated.h 3KB
SwapAlign2Nat.h 1KB
nms_rotated.h 1KB
box_iou_rotated.h 993B
16.jpg 340KB
17.jpg 325KB
12.jpg 314KB
15.jpg 313KB
11.jpg 310KB
14.jpg 275KB
13.jpg 263KB
9.jpg 248KB
5.jpg 247KB
6.jpg 237KB
3.jpg 233KB
8.jpg 232KB
2.jpg 221KB
4.jpg 212KB
7.jpg 183KB
0.jpg 181KB
1.jpg 166KB
10.jpg 155KB
res_bbox_dp_u.jpg 155KB
res_bbox_dp_v.jpg 154KB
res_bbox_dp_segm.jpg 153KB
1.jpg 120KB
res_bbox_dp_contour.jpg 89KB
vis_bbox_dp_u.jpg 85KB
vis_bbox_dp_v.jpg 85KB
vis_bbox_dp_i.jpg 84KB
vis_bbox_dp_pts.jpg 81KB
vis_bbox_dp_segm.jpg 78KB
trainval.json 260KB
metrics.json 1KB
settings.json 213B
_C.cp37-win_amd64.lib 13KB
LICENSE 10KB
Makefile 650B
MODEL_ZOO.md 47KB
MODEL_ZOO.md 14KB
datasets.md 12KB
models.md 8KB
benchmarks.md 7KB
README.md 6KB
TOOL_APPLY_NET.md 6KB
deployment.md 5KB
compatibility.md 4KB
TOOL_QUERY_DB.md 4KB
README.md 4KB
README.md 4KB
README.md 4KB
data_loading.md 4KB
GETTING_STARTED.md 3KB
README.md 3KB
extend.md 3KB
README.md 3KB
configs.md 3KB
GETTING_STARTED.md 3KB
training.md 2KB
CONTRIBUTING.md 2KB
README.md 2KB
write-models.md 2KB
evaluation.md 2KB
README.md 2KB
unexpected-problems-bugs.md 2KB
README.md 1KB
共 974 条
- 1
- 2
- 3
- 4
- 5
- 6
- 10
zxl1109007773
- 粉丝: 0
- 资源: 7
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
评论0