1. InferShape should be a method for `OpDescBind` not `Operator`, since
  `OpDescBind` is a compile-time concept.
2. Pre-create operators and store them into a map. Make InferShape
   faster

* Implementing the Adamax optimizer step operator
* Adding unit tests for adamax_op

* Changing learning rate and time step to inputs from attributes

* Changing learning rate and time step to input(tensors)

* Making the Adamax operator conform to naming convention

* Removing Tensor<float> from comments

* Rectifying the Adamax implementation

* Changing Unit Test values and adding comments

* Changing Unit Test to test multiple steps

* Adding Adadelta optimization operator
* Making inputs and outputs conform to naming convention
* Removing type alias from header files
* Fixing Adadelta documentation in comments
* Addressing code review feedback

* Changing learning rate from attribute to input(float)
* Removing obsolete code

* init remove cond_op infershape

* optimize code

* add PrepareDataForSubnet and MergeDataFromSubnet

They were using float64 for FP32 kernel before.