コード例 #1
0
ファイル: per_video.py プロジェクト: danoneata/test
def get_per_video_mbh_data(split, suffix=''):
    """ Returns the 'train' or 'test' video descriptors. The `suffix` argument
    can be '_morenull' to load the data with 5296 null samples. 
    
    """
    base_path = ('/home/clear/oneata/data/trecvid12/features/'
                 'dense5.track15mbh.small.skip_1/')
    sstats_fn = os.path.join(
        base_path, 'statistics_k_256', '%s%s.dat' % (split, suffix))
    labels_fn = os.path.join(
        base_path, 'statistics_k_256', 'labels_%s%s.info' % (split, suffix))
    info_fn = os.path.join(
        base_path, 'statistics_k_256', 'info_%s%s.info' % (split, suffix))
    gmm_fn = os.path.join(base_path, 'gmm', 'gmm_256')

    sstats = np.fromfile(sstats_fn, dtype=np.float32)
    labels = np.array([tuple_label[0]
              for tuple_label in cPickle.load(open(labels_fn, 'r'))])
    video_names = cPickle.load(open(info_fn, 'r'))['video_names']

    # Convert sufficient statistics to Fisher vectors.
    gmm = gmm_read(open(gmm_fn, 'r'))
    data = FVModel.sstats_to_features(sstats, gmm)

    return data, labels, video_names
コード例 #2
0
def double_normalization(filenames, sstats_in , sstats_out, N, len_sstats,
                         gmm):
    """ The slices in each sample are converted to Fisher vectors, square-
    rooted, L2 normalized, and then aggregated together.

    Inputs
    ------
    filenames: list of str
        The names of the files to be aggregated. Usually, this should be the
        entire dataset, i.e. dataset.get_data('train')[0] +
        dataset.get_data('test')[0].

    sstats_in: SstatsMap instance
        The sufficient statistics that we operate on.

    sstats_out: SstatsMap instance
        The resulting sufficient statistics.

    N: int
        The number of slices that are aggregated together. If N is -1 all the
        slices in the clip are aggregated together.

    len_sstats: int
        The length of a typical sufficient statistics vector.

    gmm: yael.gmm object
        The Gaussian mixture model for the current sufficient statistics.

    """
    assert len_sstats == gmm.k + 2 * gmm.k * gmm.d, (
        "GMM and len_sstats don't match")
    for filename in filenames:
        if sstats_out.exists(filename):
            continue

        if not sstats_in.exists(filename):
            print 'Not found ' + filename
            continue

        if sstats_in.getsize(filename) == 0:
            print 'Not computed ' + filename
            continue

        sstats = sstats_in.read(filename).reshape((-1, len_sstats))
        info = sstats_in.read_info(filename)

        fv = FVModel.sstats_to_features(sstats, gmm)
        fv = power_normalize(fv, 0.5)
        fv = L2_normalize(fv)

        agg_sstats, agg_info = _aggregate(fv, info, N) 
        sstats_out.write(filename, agg_sstats, info=agg_info)
コード例 #3
0
def double_normalization(filenames, sstats_in, sstats_out, N, len_sstats, gmm):
    """ The slices in each sample are converted to Fisher vectors, square-
    rooted, L2 normalized, and then aggregated together.

    Inputs
    ------
    filenames: list of str
        The names of the files to be aggregated. Usually, this should be the
        entire dataset, i.e. dataset.get_data('train')[0] +
        dataset.get_data('test')[0].

    sstats_in: SstatsMap instance
        The sufficient statistics that we operate on.

    sstats_out: SstatsMap instance
        The resulting sufficient statistics.

    N: int
        The number of slices that are aggregated together. If N is -1 all the
        slices in the clip are aggregated together.

    len_sstats: int
        The length of a typical sufficient statistics vector.

    gmm: yael.gmm object
        The Gaussian mixture model for the current sufficient statistics.

    """
    assert len_sstats == gmm.k + 2 * gmm.k * gmm.d, (
        "GMM and len_sstats don't match")
    for filename in filenames:
        if sstats_out.exists(filename):
            continue

        if not sstats_in.exists(filename):
            print 'Not found ' + filename
            continue

        if sstats_in.getsize(filename) == 0:
            print 'Not computed ' + filename
            continue

        sstats = sstats_in.read(filename).reshape((-1, len_sstats))
        info = sstats_in.read_info(filename)

        fv = FVModel.sstats_to_features(sstats, gmm)
        fv = power_normalize(fv, 0.5)
        fv = L2_normalize(fv)

        agg_sstats, agg_info = _aggregate(fv, info, N)
        sstats_out.write(filename, agg_sstats, info=agg_info)
コード例 #4
0
ファイル: per_video.py プロジェクト: danoneata/test
def get_per_video_mbh_data_given_list(list_name, **kwargs):
    """ Loads the Fisher vectors corresponding to the samples found in the
    list specified by `list_name`.

    """
    K = kwargs.get('K', 256)
    sstats_path = ('/home/clear/oneata/data/trecvid12/features'
                   '/dense5.track15mbh.small.skip_1/statistics_k_%d' % K)

    # Default base directories.
    list_base_path = kwargs.get(
        'list_base_path', '/home/lear/douze/src/experiments/trecvid12/data')
    cache_base_path = kwargs.get(
        'cache_base_path', sstats_path)
    double_norm = kwargs.get('double_norm', False)

    suffix = '.double_norm' if double_norm else ''

    # If this file exists load them directly.
    cache_filename = os.path.join(cache_base_path, 'mbh_' + list_name + suffix + '.raw')
    if os.path.exists(cache_filename):
        print "Loading Fisher vectors from MBH descriptors for list %s..." % (
            list_name)
        with open(cache_filename, 'r') as ff:
            data = np.load(ff)
            labels = np.load(ff)
            names = cPickle.load(ff)
        return data, labels, names

    D = 64
    data, labels, names = [], [], []
    sstats_generic_name = os.path.join(sstats_path, 'stats.tmp' + suffix, '%s.dat')
    list_path = os.path.join(list_base_path, list_name + '.list')
    gmm_path = os.path.join(sstats_path, 'gmm_%d' % K)
    gmm = gmm_read(open(gmm_path, 'r'))

    # Get descriptors for the files in list.
    print "Creating cache file from list %s..." % list_name
    for line in open(list_path, 'r'):
        fields = line.split()

        sstats_filename = fields[0]
        video_name = sstats_filename.split('-')[0]
        sys.stdout.write("%s\t\r" % video_name)

        try:
            class_name = fields[1]
        except IndexError:
            class_name = 'unknown'

        try:
            sstats = np.fromfile(sstats_generic_name % sstats_filename,
                                 dtype=np.float32)
            if double_norm:
                fv = sstats
            else:
                fv = FVModel.sstats_to_features(sstats, gmm)
        except IOError:
            print ('Sufficient statistics for video %s are missing;'
                   'replacing with zeros.') % video_name
            fv = np.zeros(K + 2 * K * D)

        data.append(fv)
        names.append(video_name)
        labels.append(rev_label_map[class_name])

    data = np.vstack(data)
    labels = np.array(labels)

    assert data.shape[0] == len(labels), "Data size doesn't match nr of labels"

    # Cache results to file.
    with open(cache_filename, 'w') as ff:
        np.save(ff, data)
        np.save(ff, labels)
        cPickle.dump(names, ff)

    return data, labels, names