[ graph ] Allow loss layer to be used in inference mode

[skykongkong8]

• Intention of the c5db575 commit was to completely remove the usage of loss and the label in inference.
• However, there are cases where the loss layer is used in inference mode, such as the case of the loss layer being used as a metric which means that the formulation of the loss layer should not be determined by the execution mode, but the presence of the loss layer given by the user.
• Thus, when loss layer is given when the model is formulated, the model will always have the loss layer, and it will expect to have a label vector later on (since the presence of the label vector cannot be detected on compile time.
• On the contrary, when the loss layer is not given, the model will not have the loss layer, and it will not expect to have a label vector later on.

To summarize when inference mode,

loss	label	at inference time...
O	O	Loss layer is formulated, loss will be computed w.r.t. label
O	X	Loss layer is formulated, but no label -> emit error
X	O	Loss layer is not formulated, but label is given -> emit error
X	X	Loss layer is not formulated, label is empty as well -> inference w/o loss

Added TC will emit the output like below with model summary:

================================================================================
          Layer name          Layer type    Output dimension         Input layer
================================================================================
              input0               input           1:1:1:256                    
--------------------------------------------------------------------------------
    fully_connected0     fully_connected          1:1:1:1024              input0
--------------------------------------------------------------------------------
    fully_connected1     fully_connected          1:1:1:1024    fully_connected0
--------------------------------------------------------------------------------
    fully_connected2     fully_connected          1:1:1:1024    fully_connected1
--------------------------------------------------------------------------------
    fully_connected3     fully_connected           1:1:1:100    fully_connected2
--------------------------------------------------------------------------------
                mse0                 mse           1:1:1:100    fully_connected3
================================================================================

Self evaluation:

1. Build test: [X]Passed [ ]Failed [ ]Skipped
2. Run test: [X]Passed [ ]Failed [ ]Skipped

[DonghakPark]

LGTM! especially Consider various case, add unittest and fix tflite export!! 👍

[EunjuYang]

LGTM