Python keras.utils.data_utils.get_file() Examples

def decode_predictions(preds, top=5):
    global CLASS_INDEX
    if len(preds.shape) != 2 or preds.shape[1] != 1000:
        raise ValueError('`decode_predictions` expects '
                         'a batch of predictions '
                         '(i.e. a 2D array of shape (samples, 1000)). '
                         'Found array with shape: ' + str(preds.shape))
    if CLASS_INDEX is None:
        fpath = get_file('imagenet_class_index.json',
                         CLASS_INDEX_PATH,
                         cache_subdir='models')
        CLASS_INDEX = json.load(open(fpath))
    results = []
    for pred in preds:
        top_indices = pred.argsort()[-top:][::-1]
        result = [tuple(CLASS_INDEX[str(i)]) + (pred[i],) for i in top_indices]
        results.append(result)
    return results 

def check_pennaction_dataset():
    version = 'v0.3'
    try:
        penn_path = os.path.join(os.getcwd(), 'datasets/PennAction/')
        annot_path = get_file(penn_path + 'annotations.mat',
                ORIGIN + version + '/penn_annotations.mat',
                md5_hash='b37a2e72c0ba308bd7ad476bc2aa4d33')
        bbox_path = get_file(penn_path + 'penn_pred_bboxes_16f.json',
                ORIGIN + version + '/penn_pred_bboxes_16f.json',
                md5_hash='30b124a919185cb031b928bc6154fa9b')

        if os.path.isdir(penn_path + 'frames') is False:
            raise Exception('PennAction dataset (frames) not found! '
                    'You must download it by yourself from '
                    'http://dreamdragon.github.io/PennAction')

    except:
        sys.stderr.write('Error checking PennAction dataset!\n')
        raise 

def check_h36m_dataset():
    version = 'v0.2'
    try:
        h36m_path = os.path.join(os.getcwd(), 'datasets/Human3.6M/')
        annot_path = get_file(h36m_path + 'annotations.mat',
                ORIGIN + version + '/h36m_annotations.mat',
                md5_hash='4067d52db61737fbebdec850238d87dd')

        if os.path.isdir(h36m_path + 'images') is False:
            raise Exception('Human3.6M dataset (images) not found! '
                    'You must download it by yourself from '
                    'http://vision.imar.ro/human3.6m '
                    'and extract the video files!')

    except:
        sys.stderr.write('Error checking Human3.6M dataset!\n')
        raise 

def decode_imagenet_predictions(preds, top=5):
    global CLASS_INDEX
    if len(preds.shape) != 2 or preds.shape[1] != 1000:
        raise ValueError('`decode_predictions` expects '
                         'a batch of predictions '
                         '(i.e. a 2D array of shape (samples, 1000)). '
                         'Found array with shape: ' + str(preds.shape))
    if CLASS_INDEX is None:
        fpath = get_file('imagenet_class_index.json',
                         CLASS_INDEX_PATH,
                         cache_subdir='models')
        CLASS_INDEX = json.load(open(fpath))
    results = []

    for pred in preds:
        top_indices = pred.argsort()[-top:][::-1]
        result = [tuple(CLASS_INDEX[str(i)]) + (pred[i],) for i in top_indices]
        results.append(result)
    return results 

def check_mpii_dataset():
    version = 'v0.1'
    try:
        mpii_path = os.path.join(os.getcwd(), 'datasets/MPII/')
        annot_path = get_file(mpii_path + 'annotations.mat',
                ORIGIN + version + '/mpii_annotations.mat',
                md5_hash='cc62b1bb855bf4866d19bc0637526930')

        if os.path.isdir(mpii_path + 'images') is False:
            raise Exception('MPII dataset (images) not found! '
                    'You must download it by yourself from '
                    'http://human-pose.mpi-inf.mpg.de')

    except:
        sys.stderr.write('Error checking MPII dataset!\n')
        raise 

def get_weights_path_resnet():
    TF_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5'
    weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',TF_WEIGHTS_PATH,cache_subdir='models')
    return weights_path 

def get_embeddings_index(embedding_type='glove.42B.300d'):
    """Retrieves embeddings index from embedding name. Will automatically download and cache as needed.

    Args:
        embedding_type: The embedding type to load.

    Returns:
        The embeddings indexed by word.
    """

    embeddings_index = _EMBEDDINGS_CACHE.get(embedding_type)
    if embeddings_index is not None:
        return embeddings_index

    data_obj = _EMBEDDING_TYPES.get(embedding_type)
    if data_obj is None:
        raise ValueError("Embedding name should be one of '{}'".format(_EMBEDDING_TYPES.keys()))

    cache_dir = os.path.expanduser(os.path.join('~', '.keras-text'))
    if not os.path.exists(cache_dir):
        os.makedirs(cache_dir)

    file_path = get_file(embedding_type, origin=data_obj['url'], extract=True,
                         cache_dir=cache_dir, cache_subdir='embeddings')
    file_path = os.path.join(os.path.dirname(file_path), data_obj['file'])

    embeddings_index = _build_embeddings_index(file_path)
    _EMBEDDINGS_CACHE[embedding_type] = embeddings_index
    return embeddings_index 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def decode_predictions(preds, top=5):
    LABELS = None
    if len(preds.shape) == 2:
        if preds.shape[1] == 2622:
            fpath = get_file('rcmalli_vggface_labels_v1.npy',
                             V1_LABELS_PATH,
                             cache_subdir=VGGFACE_DIR)
            LABELS = np.load(fpath)
        elif preds.shape[1] == 8631:
            fpath = get_file('rcmalli_vggface_labels_v2.npy',
                             V2_LABELS_PATH,
                             cache_subdir=VGGFACE_DIR)
            LABELS = np.load(fpath)
        else:
            raise ValueError('`decode_predictions` expects '
                             'a batch of predictions '
                             '(i.e. a 2D array of shape (samples, 2622)) for V1 or '
                             '(samples, 8631) for V2.'
                             'Found array with shape: ' + str(preds.shape))
    else:
        raise ValueError('`decode_predictions` expects '
                         'a batch of predictions '
                         '(i.e. a 2D array of shape (samples, 2622)) for V1 or '
                         '(samples, 8631) for V2.'
                         'Found array with shape: ' + str(preds.shape))
    results = []
    for pred in preds:
        top_indices = pred.argsort()[-top:][::-1]
        result = [[str(LABELS[i].encode('utf8')), pred[i]] for i in top_indices]
        result.sort(key=lambda x: x[1], reverse=True)
        results.append(result)
    return results 

def decode_predictions(preds, top=5):
    LABELS = None
    if len(preds.shape) == 2:
        if preds.shape[1] == 2622:
            fpath = get_file('rcmalli_vggface_labels_v1.npy',
                             V1_LABELS_PATH,
                             cache_subdir=VGGFACE_DIR,
                             cache_dir='./')
            LABELS = np.load(fpath)
        elif preds.shape[1] == 8631:
            fpath = get_file('rcmalli_vggface_labels_v2.npy',
                             V2_LABELS_PATH,
                             cache_subdir=VGGFACE_DIR,
                             cache_dir='./')
            LABELS = np.load(fpath)
        else:
            raise ValueError('`decode_predictions` expects '
                             'a batch of predictions '
                             '(i.e. a 2D array of shape (samples, 2622)) for V1 or '
                             '(samples, 8631) for V2.'
                             'Found array with shape: ' + str(preds.shape))
    else:
        raise ValueError('`decode_predictions` expects '
                         'a batch of predictions '
                         '(i.e. a 2D array of shape (samples, 2622)) for V1 or '
                         '(samples, 8631) for V2.'
                         'Found array with shape: ' + str(preds.shape))
    results = []
    for pred in preds:
        top_indices = pred.argsort()[-top:][::-1]
        result = [[str(LABELS[i].encode('utf8')), pred[i]] for i in top_indices]
        result.sort(key=lambda x: x[1], reverse=True)
        results.append(result)
    return results 

def get_weights_path_vgg16():
    TF_WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5'
    weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels.h5',TF_WEIGHTS_PATH,cache_subdir='models')
    return weights_path 

def load_data():
    """Loads PCam dataset.

    # Returns
        Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
    """
    dirname = os.path.join('datasets', 'pcam')
    base = 'https://drive.google.com/uc?export=download&id='
    try:
        y_train = HDF5Matrix(get_file('camelyonpatch_level_2_split_train_y.h5', origin= base+ '1269yhu3pZDP8UYFQs-NYs3FPwuK-nGSG', cache_subdir=dirname, archive_format='gzip'), 'y')
        x_valid = HDF5Matrix(get_file('camelyonpatch_level_2_split_valid_x.h5', origin= base+ '1hgshYGWK8V-eGRy8LToWJJgDU_rXWVJ3', cache_subdir=dirname, archive_format='gzip'), 'x')
        y_valid = HDF5Matrix(get_file('camelyonpatch_level_2_split_valid_y.h5', origin= base+ '1bH8ZRbhSVAhScTS0p9-ZzGnX91cHT3uO', cache_subdir=dirname, archive_format='gzip'), 'y')
        x_test = HDF5Matrix(get_file('camelyonpatch_level_2_split_test_x.h5', origin= base+ '1qV65ZqZvWzuIVthK8eVDhIwrbnsJdbg_', cache_subdir=dirname, archive_format='gzip'), 'x')
        y_test = HDF5Matrix(get_file('camelyonpatch_level_2_split_test_y.h5', origin= base+ '17BHrSrwWKjYsOgTMmoqrIjDy6Fa2o_gP', cache_subdir=dirname, archive_format='gzip'), 'y')

        meta_train = pd.read_csv(get_file('camelyonpatch_level_2_split_train_meta.csv', origin= base+ '1XoaGG3ek26YLFvGzmkKeOz54INW0fruR', cache_subdir=dirname))
        meta_valid = pd.read_csv(get_file('camelyonpatch_level_2_split_valid_meta.csv', origin= base+ '16hJfGFCZEcvR3lr38v3XCaD5iH1Bnclg', cache_subdir=dirname))
        meta_test = pd.read_csv(get_file('camelyonpatch_level_2_split_test_meta.csv', origin= base+ '19tj7fBlQQrd4DapCjhZrom_fA4QlHqN4', cache_subdir=dirname))
        x_train = HDF5Matrix(get_file('camelyonpatch_level_2_split_train_x.h5', origin= base+ '1Ka0XfEMiwgCYPdTI-vv6eUElOBnKFKQ2', cache_subdir=dirname, archive_format='gzip'), 'x')
    except OSError:
        raise NotImplementedError('Direct download currently not working. Please go to https://drive.google.com/drive/folders/1gHou49cA1s5vua2V5L98Lt8TiWA3FrKB and press download all. Then place files (ungzipped) in ~/.keras/datasets/pcam.')
        
    if K.image_data_format() == 'channels_first':
        raise NotImplementedError()

    return (x_train, y_train, meta_train), (x_valid, y_valid, meta_valid), (x_test, y_test, meta_test) 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def get_unzip_file(fname,
             origin,
             untar=False,
             md5_hash=None,
             file_hash=None,
             cache_subdir='datasets',
             hash_algorithm='auto',
             extract=False,
             archive_format='auto',
             cache_dir=None):
    import gzip
    import shutil
    get_file()
    with open('file.txt', 'rb') as f_in, gzip.open('file.txt.gz', 'wb') as f_out:
        shutil.copyfileobj(f_in, f_out) 

def from_toml(filename):
        from keras.utils.data_utils import get_file

        volumes = {}
        with open(filename, 'rb') as fin:
            datasets = toml.load(fin).get('dataset', [])
            for dataset in datasets:
                hdf5_file = dataset['hdf5_file']
                if dataset.get('use_keras_cache', False):
                    hdf5_file = get_file(hdf5_file, dataset['download_url'], md5_hash=dataset.get('download_md5', None))
                image_dataset = dataset.get('image_dataset', None)
                label_dataset = dataset.get('label_dataset', None)
                mask_dataset = dataset.get('mask_dataset', None)
                mask_bounds = dataset.get('mask_bounds', None)
                resolution = dataset.get('resolution', None)
                hdf5_pathed_file = os.path.join(os.path.dirname(filename), hdf5_file)
                volume = HDF5Volume(hdf5_pathed_file,
                                    image_dataset,
                                    label_dataset,
                                    mask_dataset,
                                    mask_bounds=mask_bounds)
                # If the volume configuration specifies an explicit resolution,
                # override any provided in the HDF5 itself.
                if resolution:
                    logging.info('Overriding resolution for volume "%s"', dataset['name'])
                    volume.resolution = np.array(resolution)
                volumes[dataset['name']] = volume

        return volumes 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def decode_predictions(preds, top=5):
    """Decodes the prediction of an ImageNet model.

    # Arguments
        preds: Numpy tensor encoding a batch of predictions.
        top: integer, how many top-guesses to return.

    # Returns
        A list of lists of top class prediction tuples
        `(class_name, class_description, score)`.
        One list of tuples per sample in batch input.

    # Raises
        ValueError: in case of invalid shape of the `pred` array
            (must be 2D).
    """
    global CLASS_INDEX
    if len(preds.shape) != 2 or preds.shape[1] != 1000:
        raise ValueError('`decode_predictions` expects '
                         'a batch of predictions '
                         '(i.e. a 2D array of shape (samples, 1000)). '
                         'Found array with shape: ' + str(preds.shape))
    if CLASS_INDEX is None:
        fpath = get_file('imagenet_class_index.json',
                         CLASS_INDEX_PATH,
                         cache_subdir='models')
        CLASS_INDEX = json.load(open(fpath))
    results = []
    for pred in preds:
        top_indices = pred.argsort()[-top:][::-1]
        result = [tuple(CLASS_INDEX[str(i)]) + (pred[i],) for i in top_indices]
        result.sort(key=lambda x: x[2], reverse=True)
        results.append(result)
    return results 

def decode_predictions(preds, top=5):
    """Decodes the prediction of an ImageNet model.

    # Arguments
        preds: Numpy tensor encoding a batch of predictions.
        top: integer, how many top-guesses to return.

    # Returns
        A list of lists of top class prediction tuples
        `(class_name, class_description, score)`.
        One list of tuples per sample in batch input.

    # Raises
        ValueError: in case of invalid shape of the `pred` array
            (must be 2D).
    """
    global CLASS_INDEX
    if len(preds.shape) != 2 or preds.shape[1] != 1000:
        raise ValueError('`decode_predictions` expects '
                         'a batch of predictions '
                         '(i.e. a 2D array of shape (samples, 1000)). '
                         'Found array with shape: ' + str(preds.shape))
    if CLASS_INDEX is None:
        fpath = get_file('imagenet_class_index.json',
                         CLASS_INDEX_PATH,
                         cache_subdir='models')
        CLASS_INDEX = json.load(open(fpath))
    results = []
    for pred in preds:
        top_indices = pred.argsort()[-top:][::-1]
        result = [tuple(CLASS_INDEX[str(i)]) + (pred[i],) for i in top_indices]
        result.sort(key=lambda x: x[2], reverse=True)
        results.append(result)
    return results 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def download_facades_bw(tmp_path, data_folder_path):
    # download to .tmp file
    downloaded_path = get_file(tmp_path + '/facades_bw.tar', origin=AWS_FACADES_PATH)

    # un-tar
    untar_file(downloaded_path, data_folder_path + '/facades_bw', remove_tar=False, flags='-xvf')

    # move data file
    subprocess.call(['rm', '-rf', tmp_path]) 

def main_thread():

    # Build the model and load the pre-trained weights on MPII
    model = posereg.build(input_shape, pa16j.num_joints, export_heatmaps=True)
    weights_path = get_file(weights_file, TF_WEIGHTS_PATH, md5_hash=md5_hash,
            cache_subdir=cache_subdir)
    model.load_weights(weights_path)

    queue_frames = queue.Queue(2)
    queue_poses = queue.Queue(2)
    proc = threading.Thread(target=thread_grab_frames,
            args=(queue_frames, queue_poses))
    proc.daemon = True
    proc.start()

    clock = pygame.time.Clock()

    show_fps_cnt = 0
    while True:
        x = queue_frames.get()
        pred = model.predict(x)
        pred.append(x) # Append the input frame
        queue_poses.put(pred)

        clock.tick()
        show_fps_cnt += 1
        if show_fps_cnt == 10:
            show_fps_cnt = 0
            print ('fps: ' + str(clock.get_fps())) 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path 

def get_imagenet_weights(self):
        """Downloads ImageNet trained weights from Keras.
        Returns path to weights file.
        """
        from keras.utils.data_utils import get_file
        TF_WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/'\
                                 'releases/download/v0.2/'\
                                 'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
        weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
                                TF_WEIGHTS_PATH_NO_TOP,
                                cache_subdir='models',
                                md5_hash='a268eb855778b3df3c7506639542a6af')
        return weights_path