object detection.py

source = 'training_images'
if True:
    for fold in [0]:
        val_index = index[len(index)*fold//5:len(index)*(fold+1)//5]
        for name,mini in tqdm(df.groupby('image_id')):
            if name in val_index:
                path2save = 'val2017/'
            else:
                path2save = 'train2017/'
            if not os.path.exists('/tmp/convertor/fold{}/labels/'.format(fold)+path2save):
                os.makedirs('/tmp/convertor/fold{}/labels/'.format(fold)+path2save)
            with open('/tmp/convertor/fold{}/labels/'.format(fold)+path2save+name+".txt", 'w+') as f:
                row = mini[['classes','x_center','y_center','w','h']].astype(float).values
                row = row.astype(str)
                for j in range(len(row)):
                    text = ' '.join(row[j])
                    f.write(text)
                    f.write("\n")
            if not os.path.exists('/tmp/convertor/fold{}/images/{}'.format(fold,path2save)):
                os.makedirs('/tmp/convertor/fold{}/images/{}'.format(fold,path2save))
            sh.copy("../input/car-object-detection/data/{}/{}.jpg".format(source,name),'/tmp/convertor/fold{}/images/{}/{}.jpg'.format(fold,path2save,name))