preprocess.py

train_images = []
train_labels = []
test_images = []
test_labels = []

dataset_path = 'tomato'
for train_test_folder in os.listdir(dataset_path):
    # if we are in train folder, we go through disease/healthy folders there
    if train_test_folder == 'train':
        train_path = os.path.join(dataset_path, train_test_folder)
        # for each disease/healthy folder we take folder name as label and go through it to read images
        for disease_folder in os.listdir(train_path):
            disease_path = os.path.join(train_path, disease_folder)
            label = disease_folder.split('___')[1]
            # in each disease/healthy folder we read files with jpg format, i.e images and normalize them
            for file in os.listdir(disease_path):
                if file.endswith('jpg'):
                    img_path = os.path.join(disease_path, file)
                    img = cv2.imread(img_path)
                    r, g, b = img[:, :, 0]/255, img[:, :, 1]/255, img[:, :, 2]/255
                    img = np.dstack((r, g, b))
                    train_images.append(img)
                    train_labels.append(label)
                    
    # if we are in val folder, we go through disease/healthy folders there         
    if train_test_folder == 'val':
        test_path = os.path.join(dataset_path, train_test_folder)
        # for each disease/healthy folder we take folder name as label and go through it to read images
        for disease_folder in os.listdir(test_path):
            disease_path = os.path.join(test_path, disease_folder)
            label = disease_folder.split('___')[1]
            # in each disease/healthy folder we read files with jpg format, i.e images and normalize them
            for file in os.listdir(disease_path):
                if file.endswith('jpg'):
                    img_path = os.path.join(disease_path, file)
                    img = cv2.imread(img_path)
                    r, g, b = img[:, :, 0]/255, img[:, :, 1]/255, img[:, :, 2]/255
                    img = np.dstack((r, g, b))
                    test_images.append(img)
                    test_labels.append(label)
                    
train_images = np.array(train_images)
train_labels = np.array(train_labels)
test_images = np.array(test_images)
test_labels = np.array(test_labels)
print('Shape of the stacked train images:', train_images.shape)
print('Shape of the train labels:', train_labels.shape)
print('Shape of the stacked test images:', test_images.shape)
print('Shape of the test_labels:', test_labels.shape)