[NNAPI QDQ] Add QDQReshape op support

[YUNQIUGUO]

Description: Describe your changes.

Add QDQReshape op support and basic test case

Motivation and Context

More operator support

[guoyu-wang]

The perm initializer needs always to be ignored here

[guoyu-wang]

You need to pass the x_scale and x_zero_point into AddReshapeOperator, otherwise those will be set to 0

[guoyu-wang]

These are not required here, this is only for these operators

onnxruntime/onnxruntime/core/providers/nnapi/nnapi_builtin/builders/helper.cc

Lines 286 to 293 in bfb20b3

	static const std::unordered_set<std::string> internal_quantized_op_types =
	{
	"Transpose",
	"Resize",
	"Concat",
	"MaxPool",
	};

[edgchen1]

see if we want to move this to BaseOpBuilder

doesn't have to be in this PR, but when will the decision be made?

[YUNQIUGUO]

yes, @gwang-msft do you think we should move it to baseopbuilder now or keep it here at individual opbuilder level as we don't have that many qdq ops supported?

[guoyu-wang]

We can move it as a virtual function for BaseOpBuilder and by default return false, each individual builder will override this if necessary
Same for BaseOpSupportChecker

[guoyu-wang]

This is the new shape of the reshape op, it does not need scale and zero_point

[guoyu-wang]

It will be easier to get the scale and zero_point from the input inside this function, instead of passing them in, use something like this

+  // For reshape, the output type should be the same as the input type except the shape is different
+  auto output_operand_type = operand_types.at(input);
+  output_operand_type.SetDimensions(shaper[output]);
+
   // Since Reshape is not running using hardware in NNAPI for some CPU (e.g. Qualcomm SD for now)
   // We will try to see if we the skip the Reshape to prevent context switching between
   // NNAPI CPU impl and NNAPI hardware accelerator impl
   if (CanSkipReshape(model_builder, node_unit, input_rank, output_rank)) {
     // Since reshape can be skipped, only register the dimension and type, with same index and new name
-    const OperandType output_operand_type(operand_types.at(input).type, shaper[output], scale, zero_point);
     model_builder.RegisterOperand(output, operand_indices.at(input), output_operand_type, false);
   } else {
     // We still need to perform a reshape here
     // Add new shape
     Shape shape_dimen = {static_cast<uint32_t>(shape.size())};
     std::string shape_name = model_builder.GetUniqueName(node_unit.Name() + input + "newshape");
-    OperandType shape_operand_type(Type::TENSOR_INT32, shape_dimen, scale, zero_point);
+    OperandType shape_operand_type(Type::TENSOR_INT32, shape_dimen);
     ORT_RETURN_IF_ERROR(model_builder.AddOperandFromPersistMemoryBuffer(shape_name, shape.data(), shape_operand_type));
     input_indices.push_back(operand_indices.at(shape_name));
-
-    const OperandType output_operand_type(operand_types.at(input).type, shaper[output], scale, zero_point);
     ORT_RETURN_IF_ERROR(model_builder.AddOperation(ANEURALNETWORKS_RESHAPE, input_indices, {output}, {output_operand_type}, {false}));
   }