Before starting the training process, we need to pre-process the dataset into a simpler format, which we will use in the further automatic fine-tuning.

First, we make a Python package with named scripts in the project folder. Then, we create a Python file named convert_oxford_data.py and add the following code:

    import os 
    import tensorflow as tf 
    from tqdm import tqdm 
    from scipy.misc import imread, imsave 
 
    FLAGS = tf.app.flags.FLAGS 
 
    tf.app.flags.DEFINE_string( 
    'dataset_dir', 'data/datasets', 
    'The location of Oxford IIIT Pet Dataset which contains    
     annotations and images folders' 
    ) 
 
    tf.app.flags.DEFINE_string( 
    'target_dir', 'data/train_data', 
    'The location where all the images will be stored' 
    ) 
 
    def ensure_folder_exists(folder_path): 
    if not os.path.exists(folder_path): 
        os.mkdir(folder_path) 
    return folder_path 
 
    def read_image(image_path): 
    try: 
        image = imread(image_path) 
        return image 
    except IOError: 
        print(image_path, "not readable") 
    return None 

In this code, we use tf.app.flags.FLAGS to parse arguments so that we can customize the script easily. We also create two helper methods to make a directory and read images.

Next, we add the following code to convert the Oxford dataset into our preferred format:

 def convert_data(split_name, save_label=False): 
    if split_name not in ["trainval", "test"]: 
    raise ValueError("split_name is not recognized!") 
    target_split_path =  
    ensure_folder_exists(os.path.join(FLAGS.target_dir, split_name)) 
    output_file = open(os.path.join(FLAGS.target_dir, split_name +  
    ".txt"), "w") 
 
    image_folder = os.path.join(FLAGS.dataset_dir, "images") 
    anno_folder = os.path.join(FLAGS.dataset_dir, "annotations") 
 
    list_data = [line.strip() for line in open(anno_folder + "/" +  
    split_name + ".txt")] 
 
    class_name_idx_map = dict() 
    for data in tqdm(list_data, desc=split_name): 
      file_name,class_index,species,breed_id = data.split(" ") 
      file_label = int(class_index) - 1 
 
      class_name = "_".join(file_name.split("_")[0:-1]) 
      class_name_idx_map[class_name] = file_label 
 
      image_path = os.path.join(image_folder, file_name + ".jpg") 
      image = read_image(image_path) 
      if image is not None: 
      target_class_dir =  
       ensure_folder_exists(os.path.join(target_split_path,    
       class_name)) 
      target_image_path = os.path.join(target_class_dir,  
       file_name + ".jpg") 
            imsave(target_image_path, image) 
            output_file.write("%s %s
" % (file_label,  
            target_image_path)) 
 
    if save_label: 
        label_file = open(os.path.join(FLAGS.target_dir,  
        "labels.txt"), "w") 
        for class_name in sorted(class_name_idx_map,  
        key=class_name_idx_map.get): 
        label_file.write("%s
" % class_name) 
 
 
 def main(_): 
    if not FLAGS.dataset_dir: 
    raise ValueError("You must supply the dataset directory with  
    --dataset_dir") 
 
    ensure_folder_exists(FLAGS.target_dir) 
    convert_data("trainval", save_label=True) 
    convert_data("test") 
 
 
 if __name__ == "__main__": 
    tf.app.run() 

Now, we can run the scripts with the following code:

python scripts/convert_oxford_data.py --dataset_dir data/datasets/ --target_dir data/train_data.

The script reads the Oxford-IIIT dataset ground truth data and creates a new dataset in data/train_data with the following structure:

- train_data
-- trainval.txt
-- test.txt
-- labels.txt
-- trainval
---- Abyssinian
---- ...
-- test
---- Abyssinian
---- ...

Let's discuss these a bit:

• labels.txt contains a list of 37 species in our dataset.
• trainval.txt contains a list of the images that we will use in the training process, with the format <class_id> <image_path>.
• test.txt contains a list of the images that we will use to check the accuracy of the model. The format of test.txt is the same as trainval.txt.
• trainval and test folders contain 37 sub-folders, which are the names of each class and contains all the images of each class.