8df5470cf8ce9f1a3b7e34fd6bd6b24be42523d8,src/data/dataset_merge.py,,main,#Any#,65

Before Change

    //  param1+=0.05

    X = []
    for id_item in all_id_list:
      X.append(id_item[2])
    X = np.array(X)
    emap = {}
    for id_item in _id_list:
      y = id_item[2]

After Change

  if len(args.exclude)>0:
    if os.path.isdir(args.exclude):
      _path_imgrec = os.path.join(args.exclude, "train.rec")
      _path_imgidx = os.path.join(args.exclude, "train.idx")
      _imgrec = mx.recordio.MXIndexedRecordIO(_path_imgidx, _path_imgrec, "r")  // pylint: disable=redefined-variable-type
      _ds_id = len(rec_list)
      _id_list = []
      s = _imgrec.read_idx(0)
      header, _ = mx.recordio.unpack(s)
      assert header.flag>0
      print("header0 label", header.label)
      header0 = (int(header.label[0]), int(header.label[1]))
      //assert(header.flag==1)
      imgidx = range(1, int(header.label[0]))
      seq_identity = range(int(header.label[0]), int(header.label[1]))
      pp=0
      for identity in seq_identity:
        pp+=1
        if pp%10==0:
          print("processing ex id", pp)
        embedding = get_embedding(args, _imgrec, identity, image_size, model)
        //print(embedding.shape)
        _id_list.append( (_ds_id, identity, embedding) )
        if test_limit>0 and pp>=test_limit:
          break

    //X = []
    //for id_item in all_id_list:
    //  X.append(id_item[2])
    //X = np.array(X)
    //param1 = 0.3
    //while param1<=1.01:
    //  emap = {}
    //  for id_item in _id_list:
    //    y = id_item[2]
    //    sim = np.dot(X, y.T)
    //    //print(sim.shape)
    //    //print(sim)
    //    idx = np.where(sim>=param1)[0]
    //    for j in idx:
    //      emap[j] = 1
    //  exclude_removed = len(emap)
    //  print(param1, exclude_removed)
    //  param1+=0.05

    X = []
    for id_item in all_id_list:
      X.append(id_item[2])
    X = np.array(X)

Instances