Preprocess for kaggle

datasupplier.py

import os
import cv2
import numpy as np
from glob import glob
from tqdm import tqdm
from keras.preprocessing import image
from keras.applications.inception_v3 import preprocess_input


def preprocess_input(x):
    x = np.divide(x, 255.0)
    x = np.subtract(x, 0.5)
    x = np.multiply(x, 2.0)
    return x


def central_crop(image, central_fraction):
	"""Crop the central region of the image.
	Remove the outer parts of an image but retain the central region of the image
	along each dimension. If we specify central_fraction = 0.5, this function
	returns the region marked with "X" in the below diagram.
	   --------
	  |        |
	  |  XXXX  |
	  |  XXXX  |
	  |        |   where "X" is the central 50% of the image.
	   --------
	Args:
	image: 3-D array of shape [height, width, depth]
	central_fraction: float (0, 1], fraction of size to crop
	Raises:
	ValueError: if central_crop_fraction is not within (0, 1].
	Returns:
	3-D array
	"""
	if central_fraction <= 0.0 or central_fraction > 1.0:
		raise ValueError('central_fraction must be within (0, 1]')
	if central_fraction == 1.0:
		return image

	img_shape = image.shape
	depth = img_shape[2]
	fraction_offset = int(1 / ((1 - central_fraction) / 2.0))
	bbox_h_start = np.divide(img_shape[0], fraction_offset)
	bbox_w_start = np.divide(img_shape[1], fraction_offset)

	bbox_h_size = img_shape[0] - bbox_h_start * 2
	bbox_w_size = img_shape[1] - bbox_w_start * 2

	image = image[bbox_h_start:bbox_h_start+bbox_h_size, bbox_w_start:bbox_w_start+bbox_w_size]
	return image


def path_to_label(path):
	current = np.zeros((3))
	if "Type_1" in path:
		current[0] = 1
		return current
	if "Type_2" in path:
		current[1] = 1
		return current
	if "Type_3" in path:
		current[2] = 1
		return current

def get_processed_image(img_path):
	# Load image and convert from BGR to RGB
	im = cv2.imread(img_path)
	im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
	im = central_crop(im, 0.875)
	im = cv2.resize(im, (299, 299))
	im = np.asarray(im)
	im = preprocess_input(im)
	return im


def get_training_data(PATH=os.getcwd() + '/train'):
	images = []
	labels = []
	for x in tqdm(os.walk(PATH)):
		for cpath in tqdm(glob(os.path.join(x[0], '*.jpg'))):
			current_label = path_to_label(cpath)
			current_image = get_processed_image(cpath)
			
			images.append(current_image)
			labels.append(current_label)
			# print(current_image.shape)
	return np.asarray(images), np.asarray(labels)


if __name__ == '__main__':
	[images, labels] = get_training_data()
	print(images.shape)
	print(labels.shape)