clustering.py 文件源码

def get_clusters_from_frames(frame_dir=None):

  # TODO: allow multiple frame directories to be processed at once
  if frame_dir is None:
    filename_to_embedding = pickle.load(open('temp/temp_vid1_290717183249/filename_to_emb.pkl')) # TODO: call get_inception_embeddings on frame dir, but for now just use the pickle
    embs = []
    filenames = []
    for filename, embedding in filename_to_embedding.iteritems():
      embs.append(embedding)
      filenames.append(filename)
    filenames = [filename[filename.rindex('/')+1:] for filename in filenames]
    embs = np.array(embs)
    candidates = [(11, 6)]
    candidates = [(eps, min_pts) for eps in range(7, 15) for min_pts in range(2, 10)]
    labels = cluster(embs, filenames, algorithm='KMeans', n_clusters=6)