|
|
import numpy as np
|
|
|
import cv2
|
|
|
|
|
|
def format_img_size(img):
|
|
|
""" formats the image size based on config """
|
|
|
img_min_side = float(640)
|
|
|
(height,width,_) = img.shape
|
|
|
|
|
|
if width <= height:
|
|
|
ratio = img_min_side/width
|
|
|
new_height = int(ratio * height)
|
|
|
new_width = int(img_min_side)
|
|
|
else:
|
|
|
ratio = img_min_side/height
|
|
|
new_width = int(ratio * width)
|
|
|
new_height = int(img_min_side)
|
|
|
img = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_CUBIC)
|
|
|
return img, ratio
|
|
|
|
|
|
def format_img_channels(img):
|
|
|
""" formats the image channels based on config """
|
|
|
img_channel_mean = [103.939, 116.779, 123.68]
|
|
|
img_scaling_factor = 1.0
|
|
|
|
|
|
img = img[:, :, (2, 1, 0)]
|
|
|
img = img.astype(np.float32)
|
|
|
img[:, :, 0] -= img_channel_mean[0]
|
|
|
img[:, :, 1] -= img_channel_mean[1]
|
|
|
img[:, :, 2] -= img_channel_mean[2]
|
|
|
img /= img_scaling_factor
|
|
|
img = np.transpose(img, (2, 0, 1))
|
|
|
img = np.expand_dims(img, axis=0)
|
|
|
return img
|
|
|
|
|
|
def format_img(img):
|
|
|
""" formats an image for model prediction based on config """
|
|
|
img, ratio = format_img_size(img)
|
|
|
img = format_img_channels(img)
|
|
|
return img, ratio
|
|
|
|
|
|
|
|
|
|
|
|
def get_real_coordinates(ratio, x1, y1, x2, y2):
|
|
|
|
|
|
real_x1 = int(round(x1 // ratio))
|
|
|
real_y1 = int(round(y1 // ratio))
|
|
|
real_x2 = int(round(x2 // ratio))
|
|
|
real_y2 = int(round(y2 // ratio))
|
|
|
|
|
|
return (real_x1, real_y1, real_x2 ,real_y2)
|
|
|
|
