data extract for hyperas

data.py

def data():
    """
    Data providing function:
    This function is separated from create_model() so that hyperopt
    won't reload data for each evaluation run.
    """
    #Encodings
    encode = {0:'Attire',
              1:'Decorationandsignage',
              2:'Food',
              3: 'misc'}

    reverse = {v: k for k, v in encode.items()}
    #Loading
    PATH = 'train_images/'
    image_names = os.listdir(PATH)
    train = pd.read_csv('train.csv')

    images = [cv2.imread(PATH+image_name) for image_name in tqdm(image_names)]
    labels = [train.loc[train['Image'] == image_name]['Class'].iloc[0] for image_name in tqdm(image_names)]
    
    def standard_image(img):
        img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        return cv2.resize(img,(48,48),interpolation=cv2.INTER_AREA).reshape((48,48,1))

    #Encoding and preparation for training
    X = np.array(images)
    y_raw = np.array([reverse[label] for label in labels])
    y = []
    for cls in y_raw:
        init = np.zeros(4)
        init[cls] = 1
        y.append(init)

    y = np.array(y)
    X.shape,y.shape
    np.random.seed(40)

    ratio = 0.8
    indexes = range(len(images))
    train_idx = random.sample(indexes,int(0.8*len(images)))
    test_idx = np.delete(indexes, train_idx)

    #Cross Validation
    X_train_raw, y_train = X[train_idx], y[train_idx]
    X_test_raw, y_test = X[test_idx], y[test_idx]

    #Standardize_all elements
    X_train = np.array([standard_image(X_train_raw[i]) for i in range(len(X_train_raw))])
    X_test = np.array([standard_image(X_test_raw[i]) for i in range(len(X_test_raw))])
    return X_train, y_train, X_test, y_test