yolov2 kmeans

import matplotlib.pyplot as plt
import numpy as np
import os, cv2
%matplotlib inline

LABELS = ['aeroplane',  'bicycle', 'bird',  'boat',      'bottle', 
          'bus',        'car',      'cat',  'chair',     'cow',
          'diningtable','dog',    'horse',  'motorbike', 'person',
          'pottedplant','sheep',  'sofa',   'train',   'tvmonitor']

Dowload VOC-dataset

In [2]:

train_image_folder = "../../VOCdevkit/VOC2012/JPEGImages/"
train_annot_folder = "../../VOCdevkit/VOC2012/Annotations/"

In [3]:

import xml.etree.ElementTree as ET

def parse_annotation(ann_dir, img_dir, labels=[]):
    '''
    output:
    - Each element of the train_image is a dictionary containing the annoation infomation of an image.
    - seen_train_labels is the dictionary containing
            (key, value) = (the object class, the number of objects found in the images)
    '''
    all_imgs = []
    seen_labels = {}