An official implementation of "Learning Memory-guided Normality for Anomaly Detection" (CVPR 2020) in PyTorch.
333
stars
82
forks
source link
lack of func "make_one_shot_iterator()",so the train_gt/test_gt can't be got. #59
Open
sjzhang-Gt opened 4 months ago
in train.py ,there is
"with tf.name_scope('dataset'): train_loader = DataLoader(train_folder, resize_height=height, resize_width=width) train_dataset = train_loader(batch_size=batch_size, time_steps=num_his, num_pred=1)
however,there is no "make_one_shot_iterator()"\"get_next()"\"set_shape" in whole project. Could you please add the above code?