當(dāng)前位置：首頁 > 编程资源 > 编程问答 >内容正文

编程问答

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

發(fā)布時(shí)間：2025/3/21 编程问答 37 豆豆

生活随笔收集整理的這篇文章主要介紹了 CV之detectron2：detectron2的简介、安装、使用方法之详细攻略小編覺得挺不錯(cuò)的,現(xiàn)在分享給大家,幫大家做個(gè)參考.

CV之detectron2：detectron2的簡(jiǎn)介、安裝、使用方法之詳細(xì)攻略

detectron2的簡(jiǎn)介

1、Detectron2—What's New

detectron2的安裝

1、Requirements

2、Build and Install Detectron2

1、官方安裝

2、Windows下安裝

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的簡(jiǎn)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人工智能研究的軟件系統(tǒng)，它實(shí)現(xiàn)了最先進(jìn)的目標(biāo)檢測(cè)算法，包括Mask R-CNN。它是用Python編寫的，由Caffe2深度學(xué)習(xí)框架提供支持。
? ? ? ? ?在Facebook人工智能研究中，Detectron已經(jīng)啟動(dòng)了許多研究項(xiàng)目，包括：用于物體檢測(cè)的特征金字塔網(wǎng)絡(luò)、掩模R-CNN、檢測(cè)和識(shí)別人類與物體的相互作用、用于密集物體檢測(cè)的焦距損失、非局部神經(jīng)網(wǎng)絡(luò)、學(xué)習(xí)分割每件事物、數(shù)據(jù)蒸餾：朝向全監(jiān)督學(xué)習(xí)，DensePose：在野外進(jìn)行密集的人體姿勢(shì)估計(jì)，并進(jìn)行組規(guī)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軟件系統(tǒng)，實(shí)現(xiàn)了最先進(jìn)的目標(biāo)檢測(cè)算法。它是對(duì)先前版本Detectron的一次徹底重寫，它源于maskrcnn基準(zhǔn)測(cè)試。

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

? ? ? ?Detectron的目的是為目標(biāo)檢測(cè)研究提供高質(zhì)量、高性能的codebase。它的設(shè)計(jì)是靈活的，以支持快速實(shí)施和評(píng)估的新研究。Detectron包括以下對(duì)象檢測(cè)算法的實(shí)現(xiàn)：

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

? ? ? ?采用下列主干網(wǎng)絡(luò)架構(gòu):

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

? ? ? ?附加的主干架構(gòu)可能很容易實(shí)現(xiàn)。有關(guān)這些模型的詳細(xì)信息，請(qǐng)參閱下面的參考資料。

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的安裝

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、官方安裝

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下安裝

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

相關(guān)文章：CV之detectron2：detectron2安裝過程記錄

3、Detectron2 Model Zoo and Baselines

COCO Object Detection Baselines

Faster R-CNN:

Namelr
schedtrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APmodel iddownload

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:

Namelr
schedtrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APmodel iddownload

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:

Namelr
schedtrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APprop.
ARmodel iddownload

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

Namelr
schedtrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APmask
APmodel iddownload

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

Namelr
schedtrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APkp.
APmodel iddownload

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

Namelr
schedtrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APmask
APPQmodel iddownload

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.

Namelr
schedtrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APmask
APmodel iddownload

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)

Nametrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APbox
AP50mask
APmodel iddownload

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:

Namelr
schedtrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APmask
APmodel iddownload

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)

Namelr
schedtrain
time
(s/iter)inference
time
(s/im)train
mem
(GB)box
APmask
APmodel iddownload

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:

Nameinference
time
(s/im)train
mem
(GB)box
APmask
APPQmodel iddownload

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測(cè)試

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

總結(jié)

以上是生活随笔為你收集整理的CV之detectron2：detectron2的简介、安装、使用方法之详细攻略的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。

上一篇： Interview：算法岗位面试—11.
下一篇：成功解决ModuleNotFoundEr