![]() ![]() ![]() Returns the submodules of this Module (the entire submodule hierarchy) and if include_self is true, also inserts a shared_ptr to this module in the first position. Returns an OrderedDict with the buffers of this Module along with their keys, and if recurse is true also recursively of every submodule. Returns the buffers of this Module and if recurse is true, also recursively of every submodule. Returns an OrderedDict with the parameters of this Module along with their keys, and if recurse is true also recursively of every submodule. Named_parameters (bool recurse=true) const Returns the parameters of this Module and if recurse is true, also recursively of every submodule. More.Īpply (const ConstModuleApplyFunction &function) constĪpply (const NamedModuleApplyFunction &function, const std::string &name_prefix=std::string())Īpply (const ConstNamedModuleApplyFunction &function, const std::string &name_prefix=std::string()) constĪpply (const ModulePointerApplyFunction &function) constĪpply (const NamedModulePointerApplyFunction &function, const std::string &name_prefix=std::string()) const More.Īpply (const ModuleApplyFunction &function)Īpplies the function to the Module and recursively to every submodule. Tells the base Module about the name of the submodule.Ĭonstructs the module without immediate knowledge of the submodule's name. Public Member Functions inherited from torch::nn::Module Performs a recursive "deep copy" of the Module, such that all parameters and submodules in the cloned module are different from those in the original module. Public Member Functions inherited from torch::nn::CloneableĬlone (const optional &device=nullopt) const override Modifies the internal storage of weights for optimization purposes. Pretty prints the RNN module into the given stream. Pretty_print (std::ostream &stream) const override Recursively moves all parameters to the given device. To ( torch::Device device, bool non_blocking=false) override Recursively casts all parameters to the given dtype. To (torch::Dtype dtype, bool non_blocking=false) override Overrides nn::Module::to() to call flatten_parameters() after the original operation. To ( torch::Device device, torch::Dtype dtype, bool non_blocking=false) override Initializes the parameters of the RNN module. RNNImplBase (const RNNOptionsBase &options_, optional cudnn_mode=nullopt, int64_t number_of_gates=1) Public Member Functions inherited from torch::nn::detail::RNNImplBase GRUImpl (int64_t input_size, int64_t hidden_size)įorward (const Tensor &input, Tensor state=)Īpplies the GRU module to an input sequence and input state. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |