VerificationCode/dev/click_captcha/utils.py

import colorsys
from enum import Enum
from functools import reduce
from PIL import ImageDraw, ImageFont, Image
from keras import backend as K
import numpy as np
import cv2


def compose(*funcs):
    """Compose arbitrarily many functions, evaluated left to right.
    Reference: https://mathieularose.com/function-composition-in-python/
    """
    if funcs:
        return reduce(lambda f, g: lambda *a, **kw: g(f(*a, **kw)), funcs)
    else:
        raise ValueError('Composition of empty sequence not supported.')


def box_iou(b1, b2):
    """Return iou tensor
    Parameters
    ----------
    b1: tensor, shape=(i1,...,iN, 4), xywh
    b2: tensor, shape=(j, 4), xywh
    Returns
    -------
    iou: tensor, shape=(i1,...,iN, j)
    """

    # Expand dim to apply broadcasting.
    b1 = K.expand_dims(b1, -2)
    b1_xy = b1[..., :2]
    b1_wh = b1[..., 2:4]
    b1_wh_half = b1_wh/2.
    b1_mins = b1_xy - b1_wh_half
    b1_maxes = b1_xy + b1_wh_half

    # Expand dim to apply broadcasting.
    b2 = K.expand_dims(b2, 0)
    b2_xy = b2[..., :2]
    b2_wh = b2[..., 2:4]
    b2_wh_half = b2_wh/2.
    b2_mins = b2_xy - b2_wh_half
    b2_maxes = b2_xy + b2_wh_half

    intersect_mins = K.maximum(b1_mins, b2_mins)
    intersect_maxes = K.minimum(b1_maxes, b2_maxes)
    intersect_wh = K.maximum(intersect_maxes - intersect_mins, 0.)
    intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
    b1_area = b1_wh[..., 0] * b1_wh[..., 1]
    b2_area = b2_wh[..., 0] * b2_wh[..., 1]
    iou = intersect_area / (b1_area + b2_area - intersect_area)

    return iou


def get_classes(classes_path):
    """loads the classes"""
    with open(classes_path) as f:
        class_names = f.readlines()
    class_names = [c.strip() for c in class_names]
    return class_names


def get_anchors(anchors_path):
    """loads the anchors from a file"""
    with open(anchors_path) as f:
        anchors = f.readline()
    anchors = [float(x) for x in anchors.split(',')]
    return np.array(anchors).reshape(-1, 2)


def get_colors(number, bright=True):
    """
    Generate random colors for drawing bounding boxes.
    To get visually distinct colors, generate them in HSV space then
    convert to RGB.
    """
    if number <= 0:
        return []

    brightness = 1.0 if bright else 0.7
    hsv_tuples = [(x / number, 1., brightness)
                  for x in range(number)]
    colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
    colors = list(
        map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
            colors))
    np.random.seed(10101)  # Fixed seed for consistent colors across runs.
    np.random.shuffle(colors)  # Shuffle colors to decorrelate adjacent classes.
    np.random.seed(None)  # Reset seed to default.
    return colors


labelType = Enum('labelType', ('LABEL_TOP_OUTSIDE',
                               'LABEL_BOTTOM_OUTSIDE',
                               'LABEL_TOP_INSIDE',
                               'LABEL_BOTTOM_INSIDE',))


def draw_boxes(image, out_boxes, out_classes, out_scores, class_names, colors):
    print()
    font = ImageFont.truetype(font='yolo_data/FiraMono-Medium.otf',
                              size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
    thickness = (image.size[0] + image.size[1]) // 300

    box_list = []
    for i, c in reversed(list(enumerate(out_classes))):
        predicted_class = class_names[c]
        box = out_boxes[i]
        score = out_scores[i]

        label = '{} {:.2f}'.format(predicted_class, score)
        draw = ImageDraw.Draw(image)
        label_size = draw.textsize(label, font)

        top, left, bottom, right = box
        top = max(0, np.floor(top + 0.5).astype('int32'))
        left = max(0, np.floor(left + 0.5).astype('int32'))
        bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
        right = min(image.size[0], np.floor(right + 0.5).astype('int32'))
        print(label, (left, top), (right, bottom))
        box_list.append([(left, top), (right, bottom)])

        if top - label_size[1] >= 0:
            text_origin = np.array([left, top - label_size[1]])
        else:
            text_origin = np.array([left, top + 1])

        # My kingdom for a good redistributable image drawing library.
        for i in range(thickness):
            draw.rectangle(
                [left + i, top + i, right - i, bottom - i],
                outline=colors[c])
        draw.rectangle(
            [tuple(text_origin), tuple(text_origin + label_size)],
            fill=colors[c])
        draw.text(text_origin, label, fill=(0, 0, 0), font=font)
        del draw

    return image, box_list


def draw_label(image, text, color, coords, label_type=labelType.LABEL_TOP_OUTSIDE):
    font = cv2.FONT_HERSHEY_PLAIN
    font_scale = 1.
    (text_width, text_height) = cv2.getTextSize(text, font, fontScale=font_scale, thickness=1)[0]

    padding = 5
    rect_height = text_height + padding * 2
    rect_width = text_width + padding * 2

    (x, y) = coords

    if label_type == labelType.LABEL_TOP_OUTSIDE or label_type == labelType.LABEL_BOTTOM_INSIDE:
        cv2.rectangle(image, (x, y), (x + rect_width, y - rect_height), color, cv2.FILLED)
        cv2.putText(image, text, (x + padding, y - text_height + padding), font,
                    fontScale=font_scale,
                    color=(255, 255, 255),
                    lineType=cv2.LINE_AA)
    else:
        # LABEL_BOTTOM_OUTSIDE or LABEL_TOP_INSIDE
        cv2.rectangle(image, (x, y), (x + rect_width, y + rect_height), color, cv2.FILLED)
        cv2.putText(image, text, (x + padding, y + text_height + padding), font,
                    fontScale=font_scale,
                    color=(255, 255, 255),
                    lineType=cv2.LINE_AA)

    return image


def pil_resize(image_np, height, width):
    image_pil = Image.fromarray(cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB))
    image_pil = image_pil.resize((int(width), int(height)), Image.BICUBIC)
    image_np = cv2.cvtColor(np.asarray(image_pil), cv2.COLOR_RGB2BGR)
    return image_np


def pil_resize_a(image_np, height, width):
    image_pil = Image.fromarray(cv2.cvtColor(image_np, cv2.COLOR_BGRA2RGBA))
    image_pil = image_pil.resize((int(width), int(height)), Image.BICUBIC)
    image_np = cv2.cvtColor(np.asarray(image_pil), cv2.COLOR_RGBA2BGRA)
    return image_np


def np2pil(image_np):
    image_pil = Image.fromarray(cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB))
    return image_pil


def pil2np(image_pil):
    image_np = cv2.cvtColor(np.array(image_pil), cv2.COLOR_RGB2BGR)
    return image_np


def np2pil_a(image_np):
    image_pil = Image.fromarray(cv2.cvtColor(image_np, cv2.COLOR_BGRA2RGBA))
    return image_pil


def pil2np_a(image_pil):
    image_np = cv2.cvtColor(np.array(image_pil), cv2.COLOR_RGBA2BGRA)
    return image_np


def pil_rotate(image_np, angle, fill_color=(255, 255, 255)):
    image_pil = np2pil(image_np)
    image_rotate = image_pil.rotate(angle, expand=False, fillcolor=fill_color)
    image_np = pil2np(image_rotate)
    return image_np


def pil_rotate_a(image_np, angle):
    image_pil = np2pil_a(image_np)
    image_rotate = image_pil.rotate(angle, expand=False, fillcolor=(255, 255, 255))
    image_np = pil2np_a(image_rotate)
    return image_np