data_download_script

%matplotlib inline
from pycocotools.coco import COCO
import numpy as np
import skimage.io as io
import matplotlib.pyplot as plt
import pylab
import urllib
pylab.rcParams['figure.figsize'] = (10.0, 8.0)
dataDir='/home/ambika'
dataType='val2014'
annFile='%s/annotations/instances_%s.json'%(dataDir,dataType)
# initialize COCO api for instance annotations
coco=COCO(annFile)
# display COCO categories and supercategories
cats = coco.loadCats(coco.getCatIds())
nms=[cat['name'] for cat in cats]
print 'COCO categories: \n\n', ' '.join(nms)

nms = set([cat['supercategory'] for cat in cats])
print 'COCO supercategories: \n', ' '.join(nms)
# get all images containing given categories, select one at random
catIds = coco.getCatIds(catNms=['couch']);
imgIds = coco.getImgIds(catIds=catIds );
print len(imgIds)
for i in range(1,150):
    img = coco.loadImgs(imgIds[np.random.randint(0,len(imgIds))])[0]
    urllib.urlretrieve("%s"%(img['flickr_url']), "/home/ambika/data/couch/%d.jpg"%(img['id']))