mini-open-images.py

df = pd.read_csv('../validation-annotations-bbox.csv')
df['LabelName'] = df['LabelName'].map(lambda x: code2label[x])
unique_classes = df['LabelName'].value_counts()
unique_classes = unique_classes[unique_classes < 501]
df = df[df['LabelName'].map(lambda x: x in unique_classes)]
print(df.ImageID.nunique())

!mkdir -p open-images-mini
from tqdm import tqdm
for f in tqdm(df.ImageID.unique()):
# for f in df.ImageID.unique()[:10]:
  f = find(f, files)
  im = cv2.imread(f, 1)[::2,::2]
  h, w = im.shape[:2]
  factor = max(h/512, w/512)
  if factor != 1:
    im = cv2.resize(im, None, fx=1/factor, fy=1/factor)
  cv2.imwrite(f'open-images-mini/{stem(f)}.jpg', im)