Yes, if you model needs prepross or postprocess, you should add the function to process it. Maybe you can refer the topic below:
https://forums.developer.nvidia.com/t/getting-0-0-0-0-output-from-tao-multitask-classifier/210302
Also, you can add your model training process step by step.
At last, There may be some problems about the order of the output layer. You can check it.
In your log:
INFO: [Implicit Engine Info]: layers num: 4
0 INPUT kFLOAT input_1 3x80x60
1 OUTPUT kFLOAT pose/Softmax 5x1x1
2 OUTPUT kFLOAT object/Softmax 2x1x1
3 OUTPUT kFLOAT action/Softmax 6x1x1
But in your config file:
output-blob-names=action/Softmax;object/Softmax;pose/Softmax