Template Function deepmd::session_input_tensors_mixed_type

Function Documentation

template<typename MODELTYPE, typename VALUETYPE>
int deepmd::session_input_tensors_mixed_type(std::vector<std::pair<std::string, tensorflow::Tensor>> &input_tensors, const int &nframes, const std::vector<VALUETYPE> &dcoord_, const int &ntypes, const std::vector<int> &datype_, const std::vector<VALUETYPE> &dbox, const double &cell_size, const std::vector<VALUETYPE> &fparam_, const std::vector<VALUETYPE> &aparam_, const deepmd::AtomMap &atommap, const std::string scope = "", const bool aparam_nall = false)

Get input tensors for mixed type.

Parameters

  • input_tensors – [out] Input tensors.

  • nframes – [in] Number of frames.

  • dcoord_ – [in] Coordinates of atoms.

  • ntypes – [in] Number of atom types.

  • datype_ – [in] Atom types.

  • dlist – [in] Neighbor list.

  • fparam_ – [in] Frame parameters.

  • aparam_ – [in] Atom parameters.

  • atommap – [in] Atom map.

  • nghost – [in] Number of ghost atoms.

  • ago – [in] Update the internal neighbour list if ago is 0.

  • scope – [in] The scope of the tensors.

  • aparam_nall – [in] Whether the atomic dimesion of atomic parameters is nall.