* Add test for the qnn_add operator
The tests use fake quant approach so until the tf session tensors remain in float32.
The test data has to be passed in uint8 because of how the tflite/tvm comparison works.
Abs tolerance up to 1 is allowed for the qnn results. For now input_stats are hardcoded
assuming the tests for the other qnn ops will pass the input data in the same range.
* Separate qnn uint8 test function from the fp32 elemwise tests
Isolate qnn uint8 elemwise tests
Remove blank lines
