Py之pycocotools庫的簡介、安裝、使用方法及說明
pycocotools庫的簡介
pycocotools是什么?即python api tools of COCO。
COCO是一個大型的圖像數(shù)據(jù)集,用于目標檢測、分割、人的關鍵點檢測、素材分割和標題生成。
這個包提供了Matlab、Python和luaapi,這些api有助于在COCO中加載、解析和可視化注釋。
請訪問COCO - Common Objects in Context,可以了解關于COCO的更多信息,包括數(shù)據(jù)、論文和教程。
COCO網(wǎng)站上也描述了注釋的確切格式。
Matlab和PythonAPI是完整的,LuaAPI只提供基本功能。
除了這個API,請下載COCO圖片和注釋,以便運行演示和使用API。
兩者都可以在項目網(wǎng)站上找到。
- -請下載、解壓縮并將圖像放入:coco/images/
- -請下載并將注釋放在:coco/annotations中/
COCO API: http://cocodataset.org/
pycocotools庫的安裝
pip install pycocotools==2.0.0 or pip install pycocotools-windows
pycocotools庫的使用方法
1、from pycocotools.coco import COCO
__author__ = 'tylin' __version__ = '2.0' # Interface for accessing the Microsoft COCO dataset. # Microsoft COCO is a large image dataset designed for object detection, # segmentation, and caption generation. pycocotools is a Python API that # assists in loading, parsing and visualizing the annotations in COCO. # Please visit http://mscoco.org/ for more information on COCO, including # for the data, paper, and tutorials. The exact format of the annotations # is also described on the COCO website. For example usage of the pycocotools # please see pycocotools_demo.ipynb. In addition to this API, please download both # the COCO images and annotations in order to run the demo. # An alternative to using the API is to load the annotations directly # into Python dictionary # Using the API provides additional utility functions. Note that this API # supports both *instance* and *caption* annotations. In the case of # captions not all functions are defined (e.g. categories are undefined). # The following API functions are defined: # COCO - COCO api class that loads COCO annotation file and prepare data structures. # decodeMask - Decode binary mask M encoded via run-length encoding. # encodeMask - Encode binary mask M using run-length encoding. # getAnnIds - Get ann ids that satisfy given filter conditions. # getCatIds - Get cat ids that satisfy given filter conditions. # getImgIds - Get img ids that satisfy given filter conditions. # loadAnns - Load anns with the specified ids. # loadCats - Load cats with the specified ids. # loadImgs - Load imgs with the specified ids. # annToMask - Convert segmentation in an annotation to binary mask. # showAnns - Display the specified annotations. # loadRes - Load algorithm results and create API for accessing them. # download - Download COCO images from mscoco.org server. # Throughout the API "ann"=annotation, "cat"=category, and "img"=image. # Help on each functions can be accessed by: "help COCO>function". # See also COCO>decodeMask, # COCO>encodeMask, COCO>getAnnIds, COCO>getCatIds, # COCO>getImgIds, COCO>loadAnns, COCO>loadCats, # COCO>loadImgs, COCO>annToMask, COCO>showAnns # Microsoft COCO Toolbox. version 2.0 # Data, paper, and tutorials available at: http://mscoco.org/ # Code written by Piotr Dollar and Tsung-Yi Lin, 2014. # Licensed under the Simplified BSD License [see bsd.txt]
2、輸出COCO數(shù)據(jù)集信息并進行圖片可視化
from pycocotools.coco import COCO import matplotlib.pyplot as plt import cv2 import os import numpy as np import random #1、定義數(shù)據(jù)集路徑 cocoRoot = "F:/File_Python/Resources/image/COCO" dataType = "val2017" annFile = os.path.join(cocoRoot, f'annotations/instances_{dataType}.json') print(f'Annotation file: {annFile}') #2、為實例注釋初始化COCO的API coco=COCO(annFile) #3、采用不同函數(shù)獲取對應數(shù)據(jù)或類別 ids = coco.getCatIds('person')[0] #采用getCatIds函數(shù)獲取"person"類別對應的ID print(f'"person" 對應的序號: {ids}') id = coco.getCatIds(['dog'])[0] #獲取某一類的所有圖片,比如獲取包含dog的所有圖片 imgIds = coco.catToImgs[id] print(f'包含dog的圖片共有:{len(imgIds)}張, 分別是:',imgIds) cats = coco.loadCats(1) #采用loadCats函數(shù)獲取序號對應的類別名稱 print(f'"1" 對應的類別名稱: {cats}') imgIds = coco.getImgIds(catIds=[1]) #采用getImgIds函數(shù)獲取滿足特定條件的圖片(交集),獲取包含person的所有圖片 print(f'包含person的圖片共有:{len(imgIds)}張') #4、將圖片進行可視化 imgId = imgIds[10] imgInfo = coco.loadImgs(imgId)[0] print(f'圖像{imgId}的信息如下:\n{imgInfo}') imPath = os.path.join(cocoRoot, 'images', dataType, imgInfo['file_name']) im = cv2.imread(imPath) plt.axis('off') plt.imshow(im) plt.show() plt.imshow(im); plt.axis('off') annIds = coco.getAnnIds(imgIds=imgInfo['id']) # 獲取該圖像對應的anns的Id print(f'圖像{imgInfo["id"]}包含{len(anns)}個ann對象,分別是:\n{annIds}') anns = coco.loadAnns(annIds) coco.showAnns(anns) print(f'ann{annIds[3]}對應的mask如下:') mask = coco.annToMask(anns[3]) plt.imshow(mask); plt.axis('off')
總結
以上為個人經(jīng)驗,希望能給大家一個參考,也希望大家多多支持腳本之家。
相關文章
Python中的X[:,0]、X[:,1]、X[:,:,0]、X[:,:,1]、X[:,m:n]和X[:,:,m:n]
這篇文章主要介紹了Python中的X[:,0]、X[:,1]、X[:,:,0]、X[:,:,1]、X[:,m:n]和X[:,:,m:n],文中通過示例代碼介紹的非常詳細,對大家的學習或者工作具有一定的參考學習價值,需要的朋友們下面隨著小編來一起學習學習吧2020-02-02vue.js實現(xiàn)輸入框輸入值內容實時響應變化示例
這篇文章主要介紹了vue.js實現(xiàn)輸入框輸入值內容實時響應變化,結合實例形式分析了vue.js使用v-model屬性進行數(shù)據(jù)綁定的相關操作技巧,需要的朋友可以參考下2018-07-07Python中利用函數(shù)裝飾器實現(xiàn)備忘功能
這篇文章主要介紹了Python中利用函數(shù)裝飾器實現(xiàn)備忘功能,同時還降到了利用裝飾器來檢查函數(shù)的遞歸、確保參數(shù)傳遞的正確,需要的朋友可以參考下2015-03-03