Zombie Detector

When I tried to run Training Loop I am getteing following error, Can any one correct me.

ValueError: Shapes must be equal rank, but are 3 and 1 for ‘{{node Loss/Loss/Select}} = Select[T=DT_FLOAT](Loss/Loss/IsNan, concat_1, Loss/stack_2)’ with input shapes: [0], [4,51150,4], [0].

Hello there,

The issue should be with the tf.concat function. Check if you are implementing it right because there is a miss shape when calculating the loss further down.