CV之detectron2：detectron2的简介、安装、使用方法之详细攻略

CV之detectron2：detectron2的简介、安装、使用方法之详细攻略

 

 

目录

detectron2的简介

1、Detectron2—What's New

detectron2的安装

1、Requirements

2、Build and Install Detectron2

1、官方安装

2、Windows下安装

3、Detectron2 Model Zoo and Baselines

COCO Object Detection Baselines

COCO Instance Segmentation Baselines with Mask R-CNN

COCO Person Keypoint Detection Baselines with Keypoint R-CNN

COCO Panoptic Segmentation Baselines with Panoptic FPN

LVIS Instance Segmentation Baselines with Mask R-CNN

Cityscapes & Pascal VOC Baselines

Other Settings

detectron2的使用方法

---

 

 

detectron2的简介

Detectron is Facebook AI Research's software system that implements state-of-the-art object detection algorithms, including Mask R-CNN. It is written in Python and powered by the Caffe2 deep learning framework.          At FAIR, Detectron has enabled numerous research projects, including: Feature Pyramid Networks for Object Detection, Mask R-CNN, Detecting and Recognizing Human-Object Interactions, Focal Loss for Dense Object Detection, Non-local Neural Networks, Learning to Segment Every Thing, Data Distillation: Towards Omni-Supervised Learning, DensePose: Dense Human Pose Estimation In The Wild, and Group Normalization.

Detectron是Facebook人工智能研究的软件系统，它实现了最先进的目标检测算法，包括Mask R-CNN。它是用Python编写的，由Caffe2深度学习框架提供支持。          在Facebook人工智能研究中，Detectron已经启动了许多研究项目，包括：用于物体检测的特征金字塔网络、掩模R-CNN、检测和识别人类与物体的相互作用、用于密集物体检测的焦距损失、非局部神经网络、学习分割每件事物、数据蒸馏：朝向全监督学习，DensePose：在野外进行密集的人体姿势估计，并进行组规范化。

Detectron2 is Facebook AI Research's next generation software system that implements state-of-the-art object detection algorithms. It is a ground-up rewrite of the previous version, Detectron, and it originates from maskrcnn-benchmark.

Detectron2是Facebook人工智能研究的下一代软件系统，实现了最先进的目标检测算法。它是对先前版本Detectron的一次彻底重写，它源于maskrcnn基准测试。

GitHub：
Detectron，https://github.com/facebookresearch/Detectron/
Detectron2，https://github.com/facebookresearch/detectron2

       Detectron的目的是为目标检测研究提供高质量、高性能的codebase。它的设计是灵活的，以支持快速实施和评估的新研究。Detectron包括以下对象检测算法的实现：

• Mask R-CNN -- Marr Prize at ICCV 2017
• RetinaNet -- Best Student Paper Award at ICCV 2017
• Faster R-CNN
• RPN
• Fast R-CNN
• R-FCN

       采用下列主干网络架构:

• ResNeXt{50,101,152}
• ResNet{50,101,152}
• Feature Pyramid Networks (with ResNet/ResNeXt)
• VGG16

       附加的主干架构可能很容易实现。有关这些模型的详细信息，请参阅下面的参考资料。

 

1、Detectron2—What's New

• It is powered by the PyTorch deep learning framework.
• Includes more features such as panoptic segmentation, densepose, Cascade R-CNN, rotated bounding boxes, etc.
• Can be used as a library to support different projects on top of it. We'll open source more research projects in this way.
• It trains much faster.

 

 

detectron2的安装

1、Requirements

• Linux or macOS
• Python ≥ 3.6
• PyTorch ≥ 1.3
• torchvision that matches the PyTorch installation. You can install them together at pytorch.org to make sure of this.
• OpenCV, needed by demo and visualization
• pycocotools: pip install cython; pip install 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
• GCC ≥ 4.9

2、Build and Install Detectron2

1、官方安装

git clone https://github.com/facebookresearch/detectron2.git
cd detectron2
pip install -e .
# (add --user if you don't have permission)

# or if you are on macOS
# MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ pip install -e .

2、Windows下安装

git clone https://github.com/facebookresearch/detectron2.git
cd detectron2
python setup.py build develop

相关文章：CV之detectron2：detectron2安装过程记录

 

 

3、Detectron2 Model Zoo and Baselines

COCO Object Detection Baselines

Faster R-CNN:

Name	lr sched	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	model id	download
R50-C4	1x	0.551	0.110	4.8	35.7	137257644	model | metrics
R50-DC5	1x	0.380	0.068	5.0	37.3	137847829	model | metrics
R50-FPN	1x	0.210	0.055	3.0	37.9	137257794	model | metrics
R50-C4	3x	0.543	0.110	4.8	38.4	137849393	model | metrics
R50-DC5	3x	0.378	0.073	5.0	39.0	137849425	model | metrics
R50-FPN	3x	0.209	0.047	3.0	40.2	137849458	model | metrics
R101-C4	3x	0.619	0.149	5.9	41.1	138204752	model | metrics
R101-DC5	3x	0.452	0.082	6.1	40.6	138204841	model | metrics
R101-FPN	3x	0.286	0.063	4.1	42.0	137851257	model | metrics
X101-FPN	3x	0.638	0.120	6.7	43.0	139173657	model | metrics

RetinaNet:

Name	lr sched	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	model id	download
R50	1x	0.200	0.062	3.9	36.5	137593951	model | metrics
R50	3x	0.201	0.063	3.9	37.9	137849486	model | metrics
R101	3x	0.280	0.080	5.1	39.9	138363263	model | metrics

RPN & Fast R-CNN:

Name	lr sched	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	prop. AR	model id	download
RPN R50-C4	1x	0.130	0.051	1.5		51.6	137258005	model | metrics
RPN R50-FPN	1x	0.186	0.045	2.7		58.0	137258492	model | metrics
Fast R-CNN R50-FPN	1x	0.140	0.035	2.6	37.8		137635226	model | metrics

COCO Instance Segmentation Baselines with Mask R-CNN

Name	lr sched	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	mask AP	model id	download
R50-C4	1x	0.584	0.117	5.2	36.8	32.2	137259246	model | metrics
R50-DC5	1x	0.471	0.074	6.5	38.3	34.2	137260150	model | metrics
R50-FPN	1x	0.261	0.053	3.4	38.6	35.2	137260431	model | metrics
R50-C4	3x	0.575	0.118	5.2	39.8	34.4	137849525	model | metrics
R50-DC5	3x	0.470	0.075	6.5	40.0	35.9	137849551	model | metrics
R50-FPN	3x	0.261	0.055	3.4	41.0	37.2	137849600	model | metrics
R101-C4	3x	0.652	0.155	6.3	42.6	36.7	138363239	model | metrics
R101-DC5	3x	0.545	0.155	7.6	41.9	37.3	138363294	model | metrics
R101-FPN	3x	0.340	0.070	4.6	42.9	38.6	138205316	model | metrics
X101-FPN	3x	0.690	0.129	7.2	44.3	39.5	139653917	model | metrics

COCO Person Keypoint Detection Baselines with Keypoint R-CNN

Name	lr sched	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	kp. AP	model id	download
R50-FPN	1x	0.315	0.083	5.0	53.6	64.0	137261548	model | metrics
R50-FPN	3x	0.316	0.076	5.0	55.4	65.5	137849621	model | metrics
R101-FPN	3x	0.390	0.090	6.1	56.4	66.1	138363331	model | metrics
X101-FPN	3x	0.738	0.142	8.7	57.3	66.0	139686956	model | metrics

COCO Panoptic Segmentation Baselines with Panoptic FPN

Name	lr sched	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	mask AP	PQ	model id	download
R50-FPN	1x	0.304	0.063	4.8	37.6	34.7	39.4	139514544	model | metrics
R50-FPN	3x	0.302	0.063	4.8	40.0	36.5	41.5	139514569	model | metrics
R101-FPN	3x	0.392	0.078	6.0	42.4	38.5	43.0	139514519	model | metrics

LVIS Instance Segmentation Baselines with Mask R-CNN

Mask R-CNN baselines on the LVIS dataset, v0.5. These baselines are described in Table 3(c) of the LVIS paper.

NOTE: the 1x schedule here has the same amount of iterations as the COCO 1x baselines. They are roughly 24 epochs of LVISv0.5 data. The final results of these configs have large variance across different runs.

Name	lr sched	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	mask AP	model id	download
R50-FPN	1x	0.292	0.127	7.1	23.6	24.4	144219072	model | metrics
R101-FPN	1x	0.371	0.124	7.8	25.6	25.9	144219035	model | metrics
X101-FPN	1x	0.712	0.166	10.2	26.7	27.1	144219108	model | metrics

Cityscapes & Pascal VOC Baselines

Simple baselines for

• Mask R-CNN on Cityscapes instance segmentation (initialized from COCO pre-training, then trained on Cityscapes fine annotations only)
• Faster R-CNN on PASCAL VOC object detection (trained on VOC 2007 train+val + VOC 2012 train+val, tested on VOC 2007 using 11-point interpolated AP)

Name	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	box AP50	mask AP	model id	download
R50-FPN, Cityscapes	0.240	0.092	4.4			36.5	142423278	model | metrics
R50-C4, VOC	0.537	0.086	4.8	51.9	80.3		142202221	model | metrics

Other Settings

Ablations for Deformable Conv and Cascade R-CNN:

Name	lr sched	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	mask AP	model id	download
Baseline R50-FPN	1x	0.261	0.053	3.4	38.6	35.2	137260431	model | metrics
Deformable Conv	1x	0.342	0.061	3.5	41.5	37.5	138602867	model | metrics
Cascade R-CNN	1x	0.317	0.066	4.0	42.1	36.4	138602847	model | metrics
Baseline R50-FPN	3x	0.261	0.055	3.4	41.0	37.2	137849600	model | metrics
Deformable Conv	3x	0.349	0.066	3.5	42.7	38.5	144998336	model | metrics
Cascade R-CNN	3x	0.328	0.075	4.0	44.3	38.5	144998488	model | metrics

Ablations for normalization methods: (Note: The baseline uses 2fc head while the others use 4conv1fc head. According to the GroupNorm paper, the change in head does not improve the baseline by much)

Name	lr sched	train time (s/iter)	inference time (s/im)	train mem (GB)	box AP	mask AP	model id	download
Baseline R50-FPN	3x	0.261	0.055	3.4	41.0	37.2	137849600	model | metrics
SyncBN	3x	0.464	0.063	5.6	42.0	37.8	143915318	model | metrics
GN	3x	0.356	0.077	7.3	42.6	38.6	138602888	model | metrics
GN (scratch)	3x	0.400	0.077	9.8	39.9	36.6	138602908	model | metrics

A few very large models trained for a long time, for demo purposes:

Name	inference time (s/im)	train mem (GB)	box AP	mask AP	PQ	model id	download
Panoptic FPN R101	0.123	11.4	47.4	41.3	46.1	139797668	model | metrics
Mask R-CNN X152	0.281	15.1	50.2	44.0		18131413	model | metrics
above + test-time aug.			51.9	45.9

 

 

detectron2的使用方法

1、demo测试

python demo/demo.py --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml --input input1.jpg input2.jpg [--other-options] --opts MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl