Add namespace for functions
* Add FDTensor copy and move assignment and constructor * Upgrade the transpose to receive the output tensor same as input tensor * Add note * Add realloc for FDTensor * Support output equals to input for softmax * Remove FDTensor::Alloc
Remove eigen option
* Add softmax function * Add softmax unittest * Add Softmax docs * Add function directory * Add comment for FD_VISIT_ALL_TYPES macro