custom loss function bug about anomalydetectioncvpr2018

[WaqasSultani]

No, it is not a bug. Please check out the code again

[VivaaindreanNg]

Hello,
seems like you have a bug in line 267 in TrainingAnomalyDetector_public.py

Hello there,

I've executed the TrainingAnomalyDetector_public.py, and it raised a TypeError as shown below:

File "D:\Anaconda3\envs\tf\lib\site-packages\tensorflow\python\framework\ops.py", line 671, in bool
raise TypeError("Using a tf.Tensor as a Python bool is not allowed. "

TypeError: Using a tf.Tensor as a Python bool is not allowed. Use if t is not None: instead of if t: to test if a tensor is defined, and use TensorFlow ops such as tf.cond to execute subgraphs conditioned on the value of a tensor.

Is it because of the keras/theano version? I'm using keras=1.2.2 & theano=1.0.4 by the way. I couldn't exactly pinpoint on why it raised the error.

[Pr0d19y]

You are right! sorry about that :)

[eticin]

Please, can you explain why it is not a bug? Formulation in the code differs from the formulation given in the paper