CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutSign UpSign In
amanchadha

Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place. Commercial Alternative to JupyterHub.

GitHub Repository: amanchadha/coursera-deep-learning-specialization
 Path: blob/master/C4 - Convolutional Neural Networks/Week 3/Car detection for Autonomous Driving/yolo_utils.py
Views: 4818
1
import colorsys

2
import imghdr

3
import os

4
import random

5
from keras import backend as K

6


7
import numpy as np

8
from PIL import Image, ImageDraw, ImageFont

9


10
def read_classes(classes_path):

11
    with open(classes_path) as f:

12
        class_names = f.readlines()

13
    class_names = [c.strip() for c in class_names]

14
    return class_names

15


16
def read_anchors(anchors_path):

17
    with open(anchors_path) as f:

18
        anchors = f.readline()

19
        anchors = [float(x) for x in anchors.split(',')]

20
        anchors = np.array(anchors).reshape(-1, 2)

21
    return anchors

22


23
def generate_colors(class_names):

24
    hsv_tuples = [(x / len(class_names), 1., 1.) for x in range(len(class_names))]

25
    colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))

26
    colors = list(map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)), colors))

27
    random.seed(10101)  # Fixed seed for consistent colors across runs.

28
    random.shuffle(colors)  # Shuffle colors to decorrelate adjacent classes.

29
    random.seed(None)  # Reset seed to default.

30
    return colors

31


32
def scale_boxes(boxes, image_shape):

33
    """ Scales the predicted boxes in order to be drawable on the image"""

34
    height = image_shape[0]

35
    width = image_shape[1]

36
    image_dims = K.stack([height, width, height, width])

37
    image_dims = K.reshape(image_dims, [1, 4])

38
    boxes = boxes * image_dims

39
    return boxes

40


41
def preprocess_image(img_path, model_image_size):

42
    image_type = imghdr.what(img_path)

43
    image = Image.open(img_path)

44
    resized_image = image.resize(tuple(reversed(model_image_size)), Image.BICUBIC)

45
    image_data = np.array(resized_image, dtype='float32')

46
    image_data /= 255.

47
    image_data = np.expand_dims(image_data, 0)  # Add batch dimension.

48
    return image, image_data

49


50
def draw_boxes(image, out_scores, out_boxes, out_classes, class_names, colors):

51
    

52
    font = ImageFont.truetype(font='font/FiraMono-Medium.otf',size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))

53
    thickness = (image.size[0] + image.size[1]) // 300

54


55
    for i, c in reversed(list(enumerate(out_classes))):

56
        predicted_class = class_names[c]

57
        box = out_boxes[i]

58
        score = out_scores[i]

59


60
        label = '{} {:.2f}'.format(predicted_class, score)

61


62
        draw = ImageDraw.Draw(image)

63
        label_size = draw.textsize(label, font)

64


65
        top, left, bottom, right = box

66
        top = max(0, np.floor(top + 0.5).astype('int32'))

67
        left = max(0, np.floor(left + 0.5).astype('int32'))

68
        bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))

69
        right = min(image.size[0], np.floor(right + 0.5).astype('int32'))

70
        print(label, (left, top), (right, bottom))

71


72
        if top - label_size[1] >= 0:

73
            text_origin = np.array([left, top - label_size[1]])

74
        else:

75
            text_origin = np.array([left, top + 1])

76


77
        # My kingdom for a good redistributable image drawing library.

78
        for i in range(thickness):

79
            draw.rectangle([left + i, top + i, right - i, bottom - i], outline=colors[c])

80
        draw.rectangle([tuple(text_origin), tuple(text_origin + label_size)], fill=colors[c])

81
        draw.text(text_origin, label, fill=(0, 0, 0), font=font)

82
        del draw

83