data_loader.py

#-*- coding: utf-8 -*-
import numpy as np
import os, h5py, sys, argparse
import codecs, json
import skimage
from skimage import io
import cv2

def get_data(input_json, input_img_h5, input_ques_h5, img_norm):
    dataset = {}
    train_data = {}
    # load json file
    print('loading json file...')
    with open(input_json) as data_file:
        data = json.load(data_file)
    for key in data.keys():
        dataset[key] = data[key]

    # load image feature
    print('loading image feature...')
    with h5py.File(input_img_h5,'r') as hf:
        tem = hf.get('images_train')
        img_feature = np.array(tem)

    # load h5 file
    print('loading h5 file...')
    with h5py.File(input_ques_h5,'r') as hf:
        tem = hf.get('ques_train')
        train_data['question'] = np.array(tem)

        tem = hf.get('ques_length_train')
        train_data['length_q'] = np.array(tem)

        tem = hf.get('img_pos_train')
        train_data['img_list'] = np.array(tem)-1

    print('Normalizing image feature')
    if img_norm:
        tem = np.sqrt(np.sum(np.multiply(img_feature, img_feature), axis=1))
        img_feature = np.divide(img_feature, np.transpose(np.tile(tem,(4096,1))))

    return dataset, img_feature, train_data

def crop_image(x, target_height=227, target_width=227, as_float=True):
    image = skimage.io.imread(x)
    if as_float:
        image = skimage.img_as_float(image).astype(np.float32)

    if len(image.shape) == 2:
        image = np.tile(image[:,:,None], 3)
    elif len(image.shape) == 4:
        image = image[:,:,:,0]

    height, width, rgb = image.shape
    if width == height:
        resized_image = cv2.resize(image, (target_height,target_width))

    elif height < width:
        resized_image = cv2.resize(image, (int(width * float(target_height)/height), target_width))
        cropping_length = int((resized_image.shape[1] - target_height) / 2)
        resized_image = resized_image[:,cropping_length:resized_image.shape[1] - cropping_length]

    else:
        resized_image = cv2.resize(image, (target_height, int(height * float(target_width) / width)))
        cropping_length = int((resized_image.shape[0] - target_width) / 2)
        resized_image = resized_image[cropping_length:resized_image.shape[0] - cropping_length,:]

    return cv2.resize(resized_image, (target_height, target_width))

def read_image(path):

     img = crop_image(path, target_height=224, target_width=224)
     if img.shape[2] == 4:
         img = img[:,:,:3]

     img = img[None, ...]
     return img