* [TFLite] Dynamically calculate input_stats of any fake_quant range

* pass the input range to the convertor and caclulate (mean, scale) there
* change the range of the second tensor in elemwise operations
  so that we test inputs with different quant params
* change the possible output range for elemwise ops wrt the updated ranges
* update the comments for (m, s) calculations
* add input range dict to reduce_mean op

* Apply requested changes

* add exception handling for zero division in input_stats
* fix range of the input tensor in elemwsie