build_feature_files.py 文件源码

def build_feature_files(base_directory,
                        new_directory,
                        data_loader,
                        n=None,
                        negative_example_keep_prob=1.0):
    os.makedirs(new_directory, exist_ok=False)
    episode_paths = frame.episode_paths(base_directory)
    label_counts = [0, 0]
    if n is not None:
        np.random.shuffle(episode_paths)
        episode_paths = episode_paths[:n]
    for episode_path in tqdm.tqdm(episode_paths):
        try:
            features, labels = data_loader.load_features_and_labels([episode_path])
        except:
            traceback.print_exc()
        else:
            keep = np.logical_or(labels, (np.less(
                np.random.rand(len(labels)), negative_example_keep_prob)))
            labels = labels[keep]

            for i in range(len(label_counts)):
                label_counts[i] += np.count_nonzero(labels == i)
            features = {k: v[keep] for k, v in features.items()}
            new_path = path_relative_to_new_directory(base_directory, new_directory, episode_path,
                                                      ".features")
            os.makedirs(os.path.dirname(new_path), exist_ok=True)
            with open(new_path, 'wb') as f:
                pickle.dump((features, labels), f)
    return label_counts