Iterates every binary in the dataset

dataset.py

def _preprocess_data(self, root_directory):
    files_data = []
    files_tags = []
    # Iterates over every binary in the dataset
    for binary_path in tqdm.tqdm(glob.glob(os.path.join(root_directory, "*", "binary", "*"))):
        with open(binary_path, "rb") as binary_file:
            binary_elf = ELFFile(binary_file)

            # Extract the code from the binary.
            data = self._generate_data(binary_elf)

            # Extract the tags of each byte in the binary code (1 if it is a start of a function, 0 otherwise).
            tags = self._generate_tags(binary_elf)

            files_data.append(data)
            files_tags.append(tags)
    return files_data, files_tags