graphorge.gnn_base_model.model.gnn_model.GNNEPDBaseModel¶

class GNNEPDBaseModel(n_node_in, n_node_out, n_edge_in, n_edge_out, n_global_in, n_global_out, n_message_steps, enc_n_hidden_layers, pro_n_hidden_layers, dec_n_hidden_layers, hidden_layer_size, model_directory, model_name='gnn_epd_model', n_time_node=0, n_time_edge=0, n_time_global=0, is_model_in_normalized=False, is_model_out_normalized=False, pro_edge_to_node_aggr='add', pro_node_to_global_aggr='add', enc_node_hidden_activ_type='identity', enc_node_output_activ_type='identity', enc_edge_hidden_activ_type='identity', enc_edge_output_activ_type='identity', enc_global_hidden_activ_type='identity', enc_global_output_activ_type='identity', pro_node_hidden_activ_type='identity', pro_node_output_activ_type='identity', pro_edge_hidden_activ_type='identity', pro_edge_output_activ_type='identity', pro_global_hidden_activ_type='identity', pro_global_output_activ_type='identity', dec_node_hidden_activ_type='identity', dec_node_output_activ_type='identity', dec_edge_hidden_activ_type='identity', dec_edge_output_activ_type='identity', dec_global_hidden_activ_type='identity', dec_global_output_activ_type='identity', is_save_model_init_file=True, device_type='cpu')[source]¶

Bases: Module

GNN Encoder-Processor-Decoder base model.

model_directory¶

Directory where model is stored.

Type:: str

model_name¶

Name of model.

Type:: str, default=’gnn_epd_model’

_n_node_in¶

Number of node input features.

Type:: int

_n_node_out¶

Number of node output features.

Type:: int

_n_edge_in¶

Number of edge input features.

Type:: int

_n_edge_out¶

Number of edge output features.

Type:: int

_n_global_in¶

Number of global input features.

Type:: int

_n_global_out¶

Number of global output features.

Type:: int

_n_time_node¶

Number of discrete time steps of nodal features. If greater than 0, then nodal input features include a time dimension and message passing layers are RNNs.

Type:: int

_n_time_edge¶

Number of discrete time steps of edge features. If greater than 0, then edge input features include a time dimension and message passing layers are RNNs.

Type:: int

_n_time_global¶

Number of discrete time steps of global features. If greater than 0, then global input features include a time dimension and message passing layers are RNNs.

Type:: int

_n_message_steps¶

Number of message-passing steps.

Type:: int

_enc_n_hidden_layers¶

Encoder: Number of hidden layers of multilayer feed-forward neural network update functions.

Type:: int

_pro_n_hidden_layers¶

Processor: Number of hidden layers of multilayer feed-forward neural network update functions.

Type:: int

_dec_n_hidden_layers¶

Decoder: Number of hidden layers of multilayer feed-forward neural network update functions.

Type:: int

_hidden_layer_size¶

Number of neurons of hidden layers of multilayer feed-forward neural network update functions.

Type:: int

_pro_edge_to_node_aggr¶

Processor: Edge-to-node aggregation scheme.

Type:: {‘add’,}, default=’add’

_pro_node_to_global_aggr¶

Processor: Node-to-global aggregation scheme.

Type:: {‘add’,}, default=’add’

_enc_node_hidden_activ_type¶

Encoder: Hidden unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_enc_node_output_activ_type¶

Encoder: Output unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_enc_edge_hidden_activ_type¶

Encoder: Hidden unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_enc_edge_output_activ_type¶

Encoder: Output unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_enc_global_hidden_activ_type¶

Encoder: Hidden unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_enc_global_output_activ_type¶

Encoder: Output unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_pro_node_hidden_activ_type¶

Processor: Hidden unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_pro_node_output_activ_type¶

Processor: Output unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_pro_edge_hidden_activ_type¶

Processor: Hidden unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_pro_edge_output_activ_type¶

Processor: Output unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_pro_global_hidden_activ_type¶

Processor: Hidden unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_pro_global_output_activ_type¶

Processor: Output unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_dec_node_hidden_activ_type¶

Decoder: Hidden unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_dec_node_output_activ_type¶

Decoder: Output unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_dec_edge_hidden_activ_type¶

Decoder: Hidden unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_dec_edge_output_activ_type¶

Decoder: Output unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_dec_global_hidden_activ_type¶

Decoder: Hidden unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_dec_global_output_activ_type¶

Decoder: Output unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.

Type:: str, default=’identity’

_gnn_epd_model¶

GNN-based Encoder-Process-Decoder model.

Type:: EncodeProcessDecode

_device_type¶

Type of device on which torch.Tensor is allocated.

Type:: {‘cpu’, ‘cuda’}, default=’cpu’

_device¶

Device on which torch.Tensor is allocated.

Type:: torch.device

is_model_in_normalized¶

If True, then model input features are assumed to be normalized (normalized input data has been seen during model training).

Type:: bool, default=False

is_model_out_normalized¶

If True, then model output features are assumed to be normalized (normalized output data has been seen during model training).

Type:: bool, default=False

_data_scalers¶

Data scaler (item, sklearn.preprocessing.StandardScaler) for each feature data (key, str).

Type:: dict

_available_activ_fn¶

For each available activation function type (key, str), store the corresponding PyTorch unit activation function (item, torch.nn.Module).

Type:: dict

init_model_from_file(model_directory)[source]¶: Initialize GNN-based model from initialization file.

set_device(self, device_type)[source]¶: Set device on which torch.Tensor is allocated.

get_device(self)[source]¶: Get device on which torch.Tensor is allocated.

forward(self, node_features_in=None, edge_features_in=None, global_features_in=None, edges_indexes=None, batch_vector=None)[source]¶: Forward propagation.

save_model_init_file(self)[source]¶: Save model class initialization attributes.

get_input_features_from_graph(self, graph, is_normalized=False)[source]¶: Get input features from graph.

get_output_features_from_graph(self, graph, is_normalized=False)[source]¶: Get output features from graph.

get_metadata_from_graph(self, graph)[source]¶: Get metadata from graph.

predict_output_features(self, input_graph, is_normalized=False)[source]¶: Predict output features.

save_model_init_state(self)[source]¶: Save model initial state to file.

save_model_state(self)[source]¶: Save model state to file.

load_model_state(self)[source]¶: Load model state from file.

_check_state_file(self, filename)[source]¶: Check if file is model training epoch state file.

_check_best_state_file(self, filename)[source]¶: Check if file is model training epoch best state file.

_remove_posterior_state_files(self, epoch)[source]¶: Delete model training epoch state files posterior to given epoch.

_remove_best_state_files(self)[source]¶: Delete existent model best state files.

_init_data_scalers(self)[source]¶: Initialize model data scalers.

set_data_scalers(self, scaler_node_in, scaler_edge_in, scaler_global_in,: scaler_node_out, scaler_edge_out, scaler_global_out)

Set fitted model data scalers.

fit_data_scalers(self, dataset, is_verbose=False)[source]¶: Fit model data scalers.

get_fitted_data_scaler(self, features_type)[source]¶: Get fitted model data scalers.

get_fitted_data_scaler(self, features_type)[source]¶: Get fitted model data scalers.

load_model_data_scalers_from_file(self)[source]¶: Load data scalers from model initialization file.

check_normalized_return(self)[source]¶: Check if model data normalization is available.

Constructor.

Parameters:

n_node_in (int) – Number of node input features.
n_node_out (int) – Number of node output features.
n_edge_in (int) – Number of edge input features.
n_edge_out (int) – Number of edge output features.
n_global_in (int) – Number of global input features.
n_global_out (int) – Number of global output features.
n_message_steps (int) – Number of message-passing steps.
enc_n_hidden_layers (int) – Encoder: Number of hidden layers of multilayer feed-forward neural network update functions.
pro_n_hidden_layers (int) – Processor: Number of hidden layers of multilayer feed-forward neural network update functions.
dec_n_hidden_layers (int) – Decoder: Number of hidden layers of multilayer feed-forward neural network update functions.
hidden_layer_size (int) – Number of neurons of hidden layers of multilayer feed-forward neural network update functions.
model_directory (str) – Directory where model is stored.
model_name (str, default='gnn_epd_model') – Name of model.
n_time_node (int, default=0) – Number of discrete time steps of nodal features. If greater than 0, then nodal input features include a time dimension and message passing layers are RNNs.
n_time_edge (int, default=0) – Number of discrete time steps of edge features. If greater than 0, then edge input features include a time dimension and message passing layers are RNNs.
n_time_global (int, default=0) – Number of discrete time steps of global features. If greater than 0, then global input features include a time dimension and message passing layers are RNNs.
is_model_in_normalized (bool, default=False) – If True, then model input features are assumed to be normalized (normalized input data has been seen during model training).
is_model_out_normalized (bool, default=False) – If True, then model output features are assumed to be normalized (normalized output data has been seen during model training).
pro_edge_to_node_aggr ({'add',}, default='add') – Processor: Edge-to-node aggregation scheme.
pro_node_to_global_aggr ({'add',}, default='add') – Processor: Node-to-global aggregation scheme.
enc_node_hidden_activ_type (str, default='identity') – Encoder: Hidden unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_node_output_activ_type (str, default='identity') – Encoder: Output unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_edge_hidden_activ_type (str, default='identity') – Encoder: Hidden unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_edge_output_activ_type (str, default='identity') – Encoder: Output unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_global_hidden_activ_type (str, default='identity') – Encoder: Hidden unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_global_output_activ_type (str, default='identity') – Encoder: Output unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_node_hidden_activ_type (str, default='identity') – Processor: Hidden unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_node_output_activ_type (str, default='identity') – Processor: Output unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_edge_hidden_activ_type (str, default='identity') – Processor: Hidden unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_edge_output_activ_type (str, default='identity') – Processor: Output unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_global_hidden_activ_type (str, default='identity') – Processor: Hidden unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_global_output_activ_type (str, default='identity') – Processor: Output unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_node_hidden_activ_type (str, default='identity') – Decoder: Hidden unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_node_output_activ_type (str, default='identity') – Decoder: Output unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_edge_hidden_activ_type (str, default='identity') – Decoder: Hidden unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_edge_output_activ_type (str, default='identity') – Decoder: Output unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_global_hidden_activ_type (str, default='identity') – Decoder: Hidden unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_global_output_activ_type (str, default='identity') – Decoder: Output unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
is_save_model_init_file (bool, default=True) – If True, saves model initialization file when model is initialized (overwritting existent initialization file), False otherwise. When initializing model from initialization file this option should be set to False to avoid updating the initialization file and preserve fitted data scalers.
device_type ({'cpu', 'cuda'}, default='cpu') – Type of device on which torch.Tensor is allocated.

List of Public Methods

`add_module`	Add a child module to the current module.
`apply`	Apply `fn` recursively to every submodule (as returned by `.children()`) as well as self.
`bfloat16`	Casts all floating point parameters and buffers to `bfloat16` datatype.
`buffers`	Return an iterator over module buffers.
`check_normalized_return`	Check if model data normalization is available.
`children`	Return an iterator over immediate children modules.
`compile`	Compile this Module's forward using `torch.compile()`.
`cpu`	Move all model parameters and buffers to the CPU.
`cuda`	Move all model parameters and buffers to the GPU.
`data_scaler_transform`	Perform data scaling operation on features PyTorch tensor.
`double`	Casts all floating point parameters and buffers to `double` datatype.
`eval`	Set the module in evaluation mode.
`extra_repr`	Set the extra representation of the module.
`fit_data_scalers`	Fit model data scalers.
`float`	Casts all floating point parameters and buffers to `float` datatype.
`forward`	Forward propagation.
`get_buffer`	Return the buffer given by `target` if it exists, otherwise throw an error.
`get_device`	Get device on which torch.Tensor is allocated.
`get_extra_state`	Return any extra state to include in the module's state_dict.
`get_fitted_data_scaler`	Get fitted model data scalers.
`get_input_features_from_graph`	Get input features from graph.
`get_metadata_from_graph`	Get metadata from graph.
`get_output_features_from_graph`	Get output features from graph.
`get_parameter`	Return the parameter given by `target` if it exists, otherwise throw an error.
`get_pytorch_activation`	Get PyTorch unit activation function.
`get_submodule`	Return the submodule given by `target` if it exists, otherwise throw an error.
`half`	Casts all floating point parameters and buffers to `half` datatype.
`init_model_from_file`	Initialize model from initialization file.
`ipu`	Move all model parameters and buffers to the IPU.
`load_model_data_scalers_from_file`	Load data scalers from model initialization file.
`load_model_state`	Load model state from file.
`load_state_dict`	Copy parameters and buffers from `state_dict` into this module and its descendants.
`modules`	Return an iterator over all modules in the network.
`named_buffers`	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
`named_children`	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
`named_modules`	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
`named_parameters`	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
`parameters`	Return an iterator over module parameters.
`predict_output_features`	Predict output features.
`register_backward_hook`	Register a backward hook on the module.
`register_buffer`	Add a buffer to the module.
`register_forward_hook`	Register a forward hook on the module.
`register_forward_pre_hook`	Register a forward pre-hook on the module.
`register_full_backward_hook`	Register a backward hook on the module.
`register_full_backward_pre_hook`	Register a backward pre-hook on the module.
`register_load_state_dict_post_hook`	Register a post hook to be run after module's `load_state_dict` is called.
`register_module`	Alias for `add_module()`.
`register_parameter`	Add a parameter to the module.
`register_state_dict_pre_hook`	Register a pre-hook for the `state_dict()` method.
`requires_grad_`	Change if autograd should record operations on parameters in this module.
`save_model_init_file`	Save model initialization file.
`save_model_init_state`	Save model initial state to file.
`save_model_state`	Save model state to file.
`set_data_scalers`	Set fitted model data scalers.
`set_device`	Set device on which torch.Tensor is allocated.
`set_extra_state`	Set extra state contained in the loaded state_dict.
`share_memory`	See `torch.Tensor.share_memory_()`.
`state_dict`	Return a dictionary containing references to the whole state of the module.
`to`	Move and/or cast the parameters and buffers.
`to_empty`	Move the parameters and buffers to the specified device without copying storage.
`train`	Set the module in training mode.
`type`	Casts all parameters and buffers to `dst_type`.
`xpu`	Move all model parameters and buffers to the XPU.
`zero_grad`	Reset gradients of all model parameters.

Attributes

`T_destination`
`call_super_init`
`dump_patches`
`training`

Methods

__call__(*args, **kwargs)¶: Call self as a function.

__init__(n_node_in, n_node_out, n_edge_in, n_edge_out, n_global_in, n_global_out, n_message_steps, enc_n_hidden_layers, pro_n_hidden_layers, dec_n_hidden_layers, hidden_layer_size, model_directory, model_name='gnn_epd_model', n_time_node=0, n_time_edge=0, n_time_global=0, is_model_in_normalized=False, is_model_out_normalized=False, pro_edge_to_node_aggr='add', pro_node_to_global_aggr='add', enc_node_hidden_activ_type='identity', enc_node_output_activ_type='identity', enc_edge_hidden_activ_type='identity', enc_edge_output_activ_type='identity', enc_global_hidden_activ_type='identity', enc_global_output_activ_type='identity', pro_node_hidden_activ_type='identity', pro_node_output_activ_type='identity', pro_edge_hidden_activ_type='identity', pro_edge_output_activ_type='identity', pro_global_hidden_activ_type='identity', pro_global_output_activ_type='identity', dec_node_hidden_activ_type='identity', dec_node_output_activ_type='identity', dec_edge_hidden_activ_type='identity', dec_edge_output_activ_type='identity', dec_global_hidden_activ_type='identity', dec_global_output_activ_type='identity', is_save_model_init_file=True, device_type='cpu')[source]¶

Constructor.

Parameters:

n_node_in (int) – Number of node input features.
n_node_out (int) – Number of node output features.
n_edge_in (int) – Number of edge input features.
n_edge_out (int) – Number of edge output features.
n_global_in (int) – Number of global input features.
n_global_out (int) – Number of global output features.
n_message_steps (int) – Number of message-passing steps.
enc_n_hidden_layers (int) – Encoder: Number of hidden layers of multilayer feed-forward neural network update functions.
pro_n_hidden_layers (int) – Processor: Number of hidden layers of multilayer feed-forward neural network update functions.
dec_n_hidden_layers (int) – Decoder: Number of hidden layers of multilayer feed-forward neural network update functions.
hidden_layer_size (int) – Number of neurons of hidden layers of multilayer feed-forward neural network update functions.
model_directory (str) – Directory where model is stored.
model_name (str, default='gnn_epd_model') – Name of model.
n_time_node (int, default=0) – Number of discrete time steps of nodal features. If greater than 0, then nodal input features include a time dimension and message passing layers are RNNs.
n_time_edge (int, default=0) – Number of discrete time steps of edge features. If greater than 0, then edge input features include a time dimension and message passing layers are RNNs.
n_time_global (int, default=0) – Number of discrete time steps of global features. If greater than 0, then global input features include a time dimension and message passing layers are RNNs.
is_model_in_normalized (bool, default=False) – If True, then model input features are assumed to be normalized (normalized input data has been seen during model training).
is_model_out_normalized (bool, default=False) – If True, then model output features are assumed to be normalized (normalized output data has been seen during model training).
pro_edge_to_node_aggr ({'add',}, default='add') – Processor: Edge-to-node aggregation scheme.
pro_node_to_global_aggr ({'add',}, default='add') – Processor: Node-to-global aggregation scheme.
enc_node_hidden_activ_type (str, default='identity') – Encoder: Hidden unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_node_output_activ_type (str, default='identity') – Encoder: Output unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_edge_hidden_activ_type (str, default='identity') – Encoder: Hidden unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_edge_output_activ_type (str, default='identity') – Encoder: Output unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_global_hidden_activ_type (str, default='identity') – Encoder: Hidden unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
enc_global_output_activ_type (str, default='identity') – Encoder: Output unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_node_hidden_activ_type (str, default='identity') – Processor: Hidden unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_node_output_activ_type (str, default='identity') – Processor: Output unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_edge_hidden_activ_type (str, default='identity') – Processor: Hidden unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_edge_output_activ_type (str, default='identity') – Processor: Output unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_global_hidden_activ_type (str, default='identity') – Processor: Hidden unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
pro_global_output_activ_type (str, default='identity') – Processor: Output unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_node_hidden_activ_type (str, default='identity') – Decoder: Hidden unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_node_output_activ_type (str, default='identity') – Decoder: Output unit activation function type of node update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_edge_hidden_activ_type (str, default='identity') – Decoder: Hidden unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_edge_output_activ_type (str, default='identity') – Decoder: Output unit activation function type of edge update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_global_hidden_activ_type (str, default='identity') – Decoder: Hidden unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
dec_global_output_activ_type (str, default='identity') – Decoder: Output unit activation function type of global update function (multilayer feed-forward neural network). Defaults to identity (linear) unit activation function.
is_save_model_init_file (bool, default=True) – If True, saves model initialization file when model is initialized (overwritting existent initialization file), False otherwise. When initializing model from initialization file this option should be set to False to avoid updating the initialization file and preserve fitted data scalers.
device_type ({'cpu', 'cuda'}, default='cpu') – Type of device on which torch.Tensor is allocated.

_check_best_state_file(filename)[source]¶

Check if file is model best state file.

Model state file corresponding to the best performance is stored in model_directory under the name < model_name >-best.pt. or < model_name >-< epoch >-best.pt if the training epoch is known.

Parameters:

filename (str) – File name.

Returns:

is_best_state_file (bool) – True if model training epoch state file, False otherwise.
epoch ({None, int}) – Training epoch corresponding to model state file if is_best_state_file=True and training epoch is known, None otherwise.

_check_state_file(filename)[source]¶

Check if file is model training epoch state file.

Model training epoch state file is stored in model_directory under the name < model_name >-< epoch >.pt.

Parameters:

filename (str) – File name.

Returns:

is_state_file (bool) – True if model training epoch state file, False otherwise.
epoch ({None, int}) – Training epoch corresponding to model state file if is_state_file=True, None otherwise.

_get_backward_hooks()¶

Return the backward hooks for use in the call function.

It returns two lists, one with the full backward hooks and one with the non-full backward hooks.

_init_data_scalers()[source]¶: Initialize model data scalers.

_load_from_state_dict(state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs)¶

Copy parameters and buffers from state_dict into only this module, but not its descendants.

This is called on every submodule in load_state_dict(). Metadata saved for this module in input state_dict is provided as local_metadata. For state dicts without metadata, local_metadata is empty. Subclasses can achieve class-specific backward compatible loading using the version number at local_metadata.get(“version”, None). Additionally, local_metadata can also contain the key assign_to_params_buffers that indicates whether keys should be assigned their corresponding tensor in the state_dict.

Note

state_dict is not the same object as the input state_dict to load_state_dict(). So it can be modified.

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
prefix (str) – the prefix for parameters and buffers used in this module
local_metadata (dict) – a dict containing the metadata for this module. See
strict (bool) – whether to strictly enforce that the keys in state_dict with prefix match the names of parameters and buffers in this module
missing_keys (list of str) – if strict=True, add missing keys to this list
unexpected_keys (list of str) – if strict=True, add unexpected keys to this list
error_msgs (list of str) – error messages should be added to this list, and will be reported together in load_state_dict()

_named_members(get_members_fn, prefix='', recurse=True, remove_duplicate=True)¶: Help yield various names + members of modules.

_register_load_state_dict_pre_hook(hook, with_module=False)¶

Register a pre-hook for the load_state_dict() method.

These hooks will be called with arguments: state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs, before loading state_dict into self. These arguments are exactly the same as those of _load_from_state_dict.

If with_module is True, then the first argument to the hook is an instance of the module.

Parameters:

hook (Callable) – Callable hook that will be invoked before loading the state dict.
with_module (bool, optional) – Whether or not to pass the module instance to the hook as the first parameter.

_register_state_dict_hook(hook)¶

Register a state-dict hook.

These hooks will be called with arguments: self, state_dict, prefix, local_metadata, after the state_dict of self is set. Note that only parameters and buffers of self or its children are guaranteed to exist in state_dict. The hooks may modify state_dict inplace or return a new one.

_remove_best_state_files()[source]¶: Delete existent model best state files.

_remove_posterior_state_files(epoch)[source]¶

Delete model training epoch state files posterior to given epoch.

Parameters:: epoch (int) – Training epoch.

_save_to_state_dict(destination, prefix, keep_vars)¶

Save module state to the destination dictionary.

The destination dictionary will contain the state of the module, but not its descendants. This is called on every submodule in state_dict().

In rare cases, subclasses can achieve class-specific behavior by overriding this method with custom logic.

Parameters:

destination (dict) – a dict where state will be stored
prefix (str) – the prefix for parameters and buffers used in this module

_version: int = 1¶

This allows better BC support for load_state_dict(). In state_dict(), the version number will be saved as in the attribute _metadata of the returned state dict, and thus pickled. _metadata is a dictionary with keys that follow the naming convention of state dict. See _load_from_state_dict on how to use this information in loading.

If new parameters/buffers are added/removed from a module, this number shall be bumped, and the module’s _load_from_state_dict method can compare the version number and do appropriate changes if the state dict is from before the change.

add_module(name, module)¶

Add a child module to the current module.

The module can be accessed as an attribute using the given name.

Parameters:

name (str) – name of the child module. The child module can be accessed from this module using the given name
module (Module) – child module to be added to the module.

Return type:

None

apply(fn)¶

Apply fn recursively to every submodule (as returned by .children()) as well as self.

Typical use includes initializing the parameters of a model (see also nn-init-doc).

Parameters:: fn (Module -> None) – function to be applied to each submodule
Returns:: self
Return type:: Module

Example:

>>> @torch.no_grad()
>>> def init_weights(m):
>>>     print(m)
>>>     if type(m) == nn.Linear:
>>>         m.weight.fill_(1.0)
>>>         print(m.weight)
>>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2))
>>> net.apply(init_weights)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)

bfloat16()¶

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

buffers(recurse=True)¶

Return an iterator over module buffers.

Parameters:: recurse (bool) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.
Yields:: torch.Tensor – module buffer
Return type:: Iterator[Tensor]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for buf in model.buffers():
>>>     print(type(buf), buf.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

check_normalized_return()[source]¶: Check if model data normalization is available.

children()¶

Return an iterator over immediate children modules.

Yields:: Module – a child module
Return type:: Iterator[Module]

compile(*args, **kwargs)¶

Compile this Module’s forward using torch.compile().

This Module’s __call__ method is compiled and all arguments are passed as-is to torch.compile().

See torch.compile() for details on the arguments for this function.

cpu()¶

Move all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

cuda(device=None)¶

Move all model parameters and buffers to the GPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on GPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: self
Return type:: Module

data_scaler_transform(tensor, features_type, mode='normalize')[source]¶

Perform data scaling operation on features PyTorch tensor.

Parameters:

tensor (torch.Tensor) – Features PyTorch tensor.
features_type (str) –
Features for which data scaler is required:

’node_features_in’ : Node features input matrix

’edge_features_in’ : Edge features input matrix

’global_features_in’ : Global features input matrix

’node_features_out’ : Node features output matrix

’edge_features_out’ : Edge features output matrix

’global_features_out’ : Global features output matrix
mode ({'normalize', 'denormalize'}, default=normalize) – Data scaling transformation type.

Returns:

transformed_tensor – Transformed features PyTorch tensor.

Return type:

torch.Tensor

double()¶

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

eval()¶

Set the module in evaluation mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

This is equivalent with self.train(False).

See locally-disable-grad-doc for a comparison between .eval() and several similar mechanisms that may be confused with it.

Returns:: self
Return type:: Module

extra_repr()¶

Set the extra representation of the module.

To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.

Return type:: str

fit_data_scalers(dataset, is_verbose=False, tqdm_flavor='default')[source]¶

Fit model data scalers.

Data scalars are set a standard scalers where features are normalized by removing the mean and scaling to unit variance.

Calling this method turns on model data normalization.

Parameters:

dataset (torch.utils.data.Dataset) – GNN-based data set. Each sample corresponds to a torch_geometric.data.Data object describing a homogeneous graph.
is_verbose (bool, default=False) – If True, enable verbose output.
tqdm_flavor ({'default', 'notebook'}, default='default') – Type of tqdm progress bar to use when is_verbose=True.

float()¶

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

forward(node_features_in=None, edge_features_in=None, global_features_in=None, edges_indexes=None, batch_vector=None)[source]¶

Forward propagation.

Parameters:

node_features_in ({torch.Tensor, None}, default=None) – Nodes features input matrix stored as a torch.Tensor(2d) of shape (n_nodes, n_features).
edge_features_in ({torch.Tensor, None}, default=None) – Edges features input matrix stored as a torch.Tensor(2d) of shape (n_edges, n_features).
global_features_in ({torch.Tensor, None}, default=None) – Global features input matrix stored as a torch.Tensor(2d) of shape (1, n_features).
edges_indexes ({torch.Tensor, None}, default=None) – Edges indexes matrix stored as torch.Tensor(2d) with shape (2, n_edges), where the i-th global is stored in edges_indexes[:, i] as (start_node_index, end_node_index).
batch_vector (torch.Tensor, default=None) – Batch vector stored as torch.Tensor(1d) of shape (n_nodes,), assigning each node to a specific batch subgraph. Required to process a graph holding multiple isolated subgraphs when batch size is greater than 1.

Returns:

node_features_out ({torch.Tensor, None}) – Nodes features output matrix stored as a torch.Tensor(2d) of shape (n_nodes, n_features).
edge_features_out ({torch.Tensor, None}) – Edges features output matrix stored as a torch.Tensor(2d) of shape (n_edges, n_features).
global_features_out ({torch.Tensor, None}) – Global features output matrix stored as a torch.Tensor(2d) of shape (1, n_features).

get_buffer(target)¶

Return the buffer given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the buffer to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: The buffer referenced by target
Return type:: torch.Tensor
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not a buffer

get_device()[source]¶

Get device on which torch.Tensor is allocated.

Parameters:

device_type ({'cpu', 'cuda'}) – Type of device on which torch.Tensor is allocated.
device (torch.device) – Device on which torch.Tensor is allocated.

get_extra_state()¶

Return any extra state to include in the module’s state_dict.

Implement this and a corresponding set_extra_state() for your module if you need to store extra state. This function is called when building the module’s state_dict().

Note that extra state should be picklable to ensure working serialization of the state_dict. We only provide provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.

Returns:: Any extra state to store in the module’s state_dict
Return type:: object

get_fitted_data_scaler(features_type)[source]¶

Get fitted model data scalers.

Parameters:

features_type (str) –

Features for which data scaler is required:

’node_features_in’ : Node features input matrix

’edge_features_in’ : Edge features input matrix

’global_features_in’ : Global features input matrix

’node_features_out’ : Node features output matrix

’edge_features_out’ : Edge features output matrix

’global_features_out’ : Global features output matrix

Returns:

data_scaler – Fitted data scaler.

Return type:

sklearn.preprocessing.StandardScaler

get_input_features_from_graph(graph, is_normalized=False)[source]¶

Get input features from graph.

Parameters:

graph (torch_geometric.data.Data) – Homogeneous graph.
is_normalized (bool, default=False) – If True, get normalized input features from graph, False otherwise.

Returns:

node_features_in ({torch.Tensor, None}) – Nodes features input matrix stored as a torch.Tensor(2d) of shape (n_nodes, n_features).
edge_features_in ({torch.Tensor, None}) – Edges features input matrix stored as a torch.Tensor(2d) of shape (n_edges, n_features).
global_features_in ({torch.Tensor, None}) – Global features input matrix stored as a torch.Tensor(2d) of shape (1, n_features).
edges_indexes ({torch.Tensor, None}) – Edges indexes matrix stored as torch.Tensor(2d) with shape (2, n_edges), where the i-th global is stored in edges_indexes[:, i] as (start_node_index, end_node_index).

get_metadata_from_graph(graph)[source]¶

Get metadata from graph.

Parameters:: graph (torch_geometric.data.Data) – Homogeneous graph.
Returns:: metadata – Metadata dictionary.
Return type:: dict

get_output_features_from_graph(graph, is_normalized=False)[source]¶

Get output features from graph.

Parameters:

graph (torch_geometric.data.Data) – Homogeneous graph.
is_normalized (bool, default=False) – If True, get normalized output features from graph, False otherwise.

Returns:

node_features_out ({torch.Tensor, None}) – Nodes features output matrix stored as a torch.Tensor(2d) of shape (n_nodes, n_features).
edge_features_out ({torch.Tensor, None}) – Edges features output matrix stored as a torch.Tensor(2d) of shape (n_edges, n_features).
global_features_out ({torch.Tensor, None}) – Global features output matrix stored as a torch.Tensor(2d) of shape (1, n_features).

get_parameter(target)¶

Return the parameter given by target if it exists, otherwise throw an error.

See the docstring for get_submodule for a more detailed explanation of this method’s functionality as well as how to correctly specify target.

Parameters:: target (str) – The fully-qualified string name of the Parameter to look for. (See get_submodule for how to specify a fully-qualified string.)
Returns:: The Parameter referenced by target
Return type:: torch.nn.Parameter
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Parameter

classmethod get_pytorch_activation(activation_type, **kwargs)[source]¶

Get PyTorch unit activation function.

Parameters:

activation_type ({'identity', 'relu', 'tanh'}) –
Unit activation function type:

’identity’ : Linear (torch.nn.Identity)

’relu’ : Rectified linear unit (torch.nn.Identity)

’tanh’ : Hyperbolic Tangent (torch.nn.Tanh)
**kwargs – Arguments of torch.nn._Module initializer.

Returns:

activation_function – PyTorch unit activation function.

Return type:

torch.nn._Module

get_submodule(target)¶

Return the submodule given by target if it exists, otherwise throw an error.

For example, let’s say you have an nn.Module A that looks like this:

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
        )
        (linear): Linear(in_features=100, out_features=200, bias=True)
    )
)

(The diagram shows an nn.Module A. A has a nested submodule net_b, which itself has two submodules net_c and linear. net_c then has a submodule conv.)

To check whether or not we have the linear submodule, we would call get_submodule("net_b.linear"). To check whether we have the conv submodule, we would call get_submodule("net_b.net_c.conv").

The runtime of get_submodule is bounded by the degree of module nesting in target. A query against named_modules achieves the same result, but it is O(N) in the number of transitive modules. So, for a simple check to see if some submodule exists, get_submodule should always be used.

Parameters:: target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
Returns:: The submodule referenced by target
Return type:: torch.nn.Module
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Module

half()¶

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

static init_model_from_file(model_directory)[source]¶

Initialize model from initialization file.

Initialization file is assumed to be stored in the model directory under the name model_init_file.pkl.

Parameters:: model_directory (str) – Directory where model is stored.

ipu(device=None)¶

Move all model parameters and buffers to the IPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on IPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: self
Return type:: Module

load_model_data_scalers_from_file()[source]¶: Load data scalers from model initialization file.

load_model_state(load_model_state=None, is_remove_posterior=True)[source]¶

Load model state from file.

Model state file is stored in model_directory under the name < model_name >.pt or < model_name >-< epoch >.pt if epoch is known.

Model state file corresponding to the best performance is stored in model_directory under the name < model_name >-best.pt or < model_name >-< epoch >-best.pt if epoch if known.

Model initial state file is stored in model directory under the name < model_name >-init.pt

Parameters:

load_model_state ({'best', 'last', int, None}, default=None) –
Load available GNN-based model state from the model directory. Options:

’best’ : Model state corresponding to best performance

’last’ : Model state corresponding to highest training epoch

int : Model state corresponding to given training epoch

’init’ : Model initial state

None : Model default state file
is_remove_posterior (bool, default=True) – Remove model state files corresponding to training epochs posterior to the loaded state file. Effective only if loaded training epoch is known.

Returns:

epoch – Loaded model state training epoch. Defaults to None if training epoch is unknown.

Return type:

int

load_state_dict(state_dict, strict=True, assign=False)¶

Copy parameters and buffers from state_dict into this module and its descendants.

If strict is True, then the keys of state_dict must exactly match the keys returned by this module’s state_dict() function.

Warning

If assign is True the optimizer must be created after the call to load_state_dict unless get_swap_module_params_on_conversion() is True.

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
strict (bool, optional) – whether to strictly enforce that the keys in state_dict match the keys returned by this module’s state_dict() function. Default: True
assign (bool, optional) – When False, the properties of the tensors in the current module are preserved while when True, the properties of the Tensors in the state dict are preserved. The only exception is the requires_grad field of Default: ``False`

Returns:

missing_keys is a list of str containing any keys that are expected
by this module but missing from the provided state_dict.
unexpected_keys is a list of str containing the keys that are not
expected by this module but present in the provided state_dict.

Return type:

NamedTuple with missing_keys and unexpected_keys fields

Note

If a parameter or buffer is registered as None and its corresponding key exists in state_dict, load_state_dict() will raise a RuntimeError.

modules()¶

Return an iterator over all modules in the network.

Yields:: Module – a module in the network

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.modules()):
...     print(idx, '->', m)

0 -> Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
)
1 -> Linear(in_features=2, out_features=2, bias=True)

Return type:: Iterator[Module]

named_buffers(prefix='', recurse=True, remove_duplicate=True)¶

Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

Parameters:

prefix (str) – prefix to prepend to all buffer names.
recurse (bool, optional) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module. Defaults to True.
remove_duplicate (bool, optional) – whether to remove the duplicated buffers in the result. Defaults to True.

Yields:

(str, torch.Tensor) – Tuple containing the name and buffer

Return type:

Iterator[Tuple[str, Tensor]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, buf in self.named_buffers():
>>>     if name in ['running_var']:
>>>         print(buf.size())

named_children()¶

Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

Yields:: (str, Module) – Tuple containing a name and child module

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, module in model.named_children():
>>>     if name in ['conv4', 'conv5']:
>>>         print(module)

Return type:: Iterator[Tuple[str, Module]]

named_modules(memo=None, prefix='', remove_duplicate=True)¶

Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

Parameters:

memo (Optional[Set[Module]]) – a memo to store the set of modules already added to the result
prefix (str) – a prefix that will be added to the name of the module
remove_duplicate (bool) – whether to remove the duplicated module instances in the result or not

Yields:

(str, Module) – Tuple of name and module

Note

Duplicate modules are returned only once. In the following example, l will be returned only once.

Example:

>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.named_modules()):
...     print(idx, '->', m)

0 -> ('', Sequential(
  (0): Linear(in_features=2, out_features=2, bias=True)
  (1): Linear(in_features=2, out_features=2, bias=True)
))
1 -> ('0', Linear(in_features=2, out_features=2, bias=True))

named_parameters(prefix='', recurse=True, remove_duplicate=True)¶

Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

Parameters:

prefix (str) – prefix to prepend to all parameter names.
recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
remove_duplicate (bool, optional) – whether to remove the duplicated parameters in the result. Defaults to True.

Yields:

(str, Parameter) – Tuple containing the name and parameter

Return type:

Iterator[Tuple[str, Parameter]]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for name, param in self.named_parameters():
>>>     if name in ['bias']:
>>>         print(param.size())

parameters(recurse=True)¶

Return an iterator over module parameters.

This is typically passed to an optimizer.

Parameters:: recurse (bool) – if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module.
Yields:: Parameter – module parameter
Return type:: Iterator[Parameter]

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> for param in model.parameters():
>>>     print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)

predict_output_features(node_features_in=None, edge_features_in=None, global_features_in=None, edges_indexes=None, batch_vector=None)[source]¶

Predict output features.

Parameters:

node_features_in ({torch.Tensor, None}, default=None) – Nodes features input matrix stored as a torch.Tensor(2d) of shape (n_nodes, n_features).
edge_features_in ({torch.Tensor, None}, default=None) – Edges features input matrix stored as a torch.Tensor(2d) of shape (n_edges, n_features).
global_features_in ({torch.Tensor, None}, default=None) – Global features input matrix stored as a torch.Tensor(2d) of shape (1, n_features).
edges_indexes ({torch.Tensor, None}, default=None) – Edges indexes matrix stored as torch.Tensor(2d) with shape (2, n_edges), where the i-th global is stored in edges_indexes[:, i] as (start_node_index, end_node_index).
batch_vector (torch.Tensor, default=None) – Batch vector stored as torch.Tensor(1d) of shape (n_nodes,), assigning each node to a specific batch subgraph. Required to process a graph holding multiple isolated subgraphs when batch size is greater than 1.

Returns:

node_features_out ({torch.Tensor, None}) – Nodes features output matrix stored as a torch.Tensor(2d) of shape (n_nodes, n_features).
edge_features_out ({torch.Tensor, None}) – Edges features output matrix stored as a torch.Tensor(2d) of shape (n_edges, n_features).
global_features_out ({torch.Tensor, None}) – Global features output matrix stored as a torch.Tensor(2d) of shape (1, n_features).

register_backward_hook(hook)¶

Register a backward hook on the module.

This function is deprecated in favor of register_full_backward_hook() and the behavior of this function will change in future versions.

Returns:: a handle that can be used to remove the added hook by calling handle.remove()
Return type:: torch.utils.hooks.RemovableHandle

register_buffer(name, tensor, persistent=True)¶

Add a buffer to the module.

This is typically used to register a buffer that should not to be considered a model parameter. For example, BatchNorm’s running_mean is not a parameter, but is part of the module’s state. Buffers, by default, are persistent and will be saved alongside parameters. This behavior can be changed by setting persistent to False. The only difference between a persistent buffer and a non-persistent buffer is that the latter will not be a part of this module’s state_dict.

Buffers can be accessed as attributes using given names.

Parameters:

name (str) – name of the buffer. The buffer can be accessed from this module using the given name
tensor (Tensor or None) – buffer to be registered. If None, then operations that run on buffers, such as cuda, are ignored. If None, the buffer is not included in the module’s state_dict.
persistent (bool) – whether the buffer is part of this module’s state_dict.

Return type:

None

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> self.register_buffer('running_mean', torch.zeros(num_features))

register_forward_hook(hook, *, prepend=False, with_kwargs=False, always_call=False)¶

Register a forward hook on the module.

The hook will be called every time after forward() has computed an output.

If with_kwargs is False or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the output. It can modify the input inplace but it will not have effect on forward since this is called after forward() is called. The hook should have the following signature:

hook(module, args, output) -> None or modified output

If with_kwargs is True, the forward hook will be passed the kwargs given to the forward function and be expected to return the output possibly modified. The hook should have the following signature:

hook(module, args, kwargs, output) -> None or modified output

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided hook will be fired before all existing forward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward hooks on this torch.nn.modules.Module. Note that global forward hooks registered with register_module_forward_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If True, the hook will be passed the kwargs given to the forward function. Default: False
always_call (bool) – If True the hook will be run regardless of whether an exception is raised while calling the Module. Default: False

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_forward_pre_hook(hook, *, prepend=False, with_kwargs=False)¶

Register a forward pre-hook on the module.

The hook will be called every time before forward() is invoked.

If with_kwargs is false or not specified, the input contains only the positional arguments given to the module. Keyword arguments won’t be passed to the hooks and only to the forward. The hook can modify the input. User can either return a tuple or a single modified value in the hook. We will wrap the value into a tuple if a single value is returned (unless that value is already a tuple). The hook should have the following signature:

hook(module, args) -> None or modified input

If with_kwargs is true, the forward pre-hook will be passed the kwargs given to the forward function. And if the hook modifies the input, both the args and kwargs should be returned. The hook should have the following signature:

hook(module, args, kwargs) -> None or a tuple of modified input and kwargs

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing forward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing forward_pre hooks on this torch.nn.modules.Module. Note that global forward_pre hooks registered with register_module_forward_pre_hook() will fire before all hooks registered by this method. Default: False
with_kwargs (bool) – If true, the hook will be passed the kwargs given to the forward function. Default: False

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_full_backward_hook(hook, prepend=False)¶

Register a backward hook on the module.

The hook will be called every time the gradients with respect to a module are computed, i.e. the hook will execute if and only if the gradients with respect to module outputs are computed. The hook should have the following signature:

hook(module, grad_input, grad_output) -> tuple(Tensor) or None

The grad_input and grad_output are tuples that contain the gradients with respect to the inputs and outputs respectively. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the input that will be used in place of grad_input in subsequent computations. grad_input will only correspond to the inputs given as positional arguments and all kwarg arguments are ignored. Entries in grad_input and grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs or outputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward hooks on this torch.nn.modules.Module. Note that global backward hooks registered with register_module_full_backward_hook() will fire before all hooks registered by this method.

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_full_backward_pre_hook(hook, prepend=False)¶

Register a backward pre-hook on the module.

The hook will be called every time the gradients for the module are computed. The hook should have the following signature:

hook(module, grad_output) -> tuple[Tensor] or None

The grad_output is a tuple. The hook should not modify its arguments, but it can optionally return a new gradient with respect to the output that will be used in place of grad_output in subsequent computations. Entries in grad_output will be None for all non-Tensor arguments.

For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module’s forward function.

Warning

Modifying inputs inplace is not allowed when using backward hooks and will raise an error.

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward_pre hooks on this torch.nn.modules.Module. Otherwise, the provided hook will be fired after all existing backward_pre hooks on this torch.nn.modules.Module. Note that global backward_pre hooks registered with register_module_full_backward_pre_hook() will fire before all hooks registered by this method.

Returns:

a handle that can be used to remove the added hook by calling handle.remove()

Return type:

torch.utils.hooks.RemovableHandle

register_load_state_dict_post_hook(hook)¶

Register a post hook to be run after module’s load_state_dict is called.

It should have the following signature::: hook(module, incompatible_keys) -> None

The module argument is the current module that this hook is registered on, and the incompatible_keys argument is a NamedTuple consisting of attributes missing_keys and unexpected_keys. missing_keys is a list of str containing the missing keys and unexpected_keys is a list of str containing the unexpected keys.

The given incompatible_keys can be modified inplace if needed.

Note that the checks performed when calling load_state_dict() with strict=True are affected by modifications the hook makes to missing_keys or unexpected_keys, as expected. Additions to either set of keys will result in an error being thrown when strict=True, and clearing out both missing and unexpected keys will avoid an error.

Returns:: a handle that can be used to remove the added hook by calling handle.remove()
Return type:: torch.utils.hooks.RemovableHandle

register_module(name, module)¶

Alias for add_module().

Return type:: None

register_parameter(name, param)¶

Add a parameter to the module.

The parameter can be accessed as an attribute using given name.

Parameters:

name (str) – name of the parameter. The parameter can be accessed from this module using the given name
param (Parameter or None) – parameter to be added to the module. If None, then operations that run on parameters, such as cuda, are ignored. If None, the parameter is not included in the module’s state_dict.

Return type:

None

register_state_dict_pre_hook(hook)¶

Register a pre-hook for the state_dict() method.

These hooks will be called with arguments: self, prefix, and keep_vars before calling state_dict on self. The registered hooks can be used to perform pre-processing before the state_dict call is made.

requires_grad_(requires_grad=True)¶

Change if autograd should record operations on parameters in this module.

This method sets the parameters’ requires_grad attributes in-place.

This method is helpful for freezing part of the module for finetuning or training parts of a model individually (e.g., GAN training).

See locally-disable-grad-doc for a comparison between .requires_grad_() and several similar mechanisms that may be confused with it.

Parameters:: requires_grad (bool) – whether autograd should record operations on parameters in this module. Default: True.
Returns:: self
Return type:: Module

save_model_init_file()[source]¶

Save model initialization file.

Initialization file is stored in the model directory under the name model_init_file.pkl.

Initialization file contains a dictionary model_init_attributes that includes:

‘model_init_args’ - Model initialization parameters

‘model_data_scalers’ - Model fitted data scalers

save_model_init_state()[source]¶

Save model initial state to file.

Model state file is stored in model_directory under the name < model_name >-init.pt.

save_model_state(epoch=None, is_best_state=False, is_remove_posterior=True)[source]¶

Save model state to file.

Model state file is stored in model_directory under the name < model_name >.pt or < model_name >-< epoch >.pt if epoch is known.

Model state file corresponding to the best performance is stored in model_directory under the name < model_name >-best.pt or < model_name >-< epoch >-best.pt if epoch is known.

Parameters:

epoch (int, default=None) – Training epoch corresponding to current model state.
is_best_state (bool, default=False) – If True, save model state file corresponding to the best performance instead of regular state file.
is_remove_posterior (bool, default=True) – Remove model and optimizer state files corresponding to training epochs posterior to the saved state file. Effective only if saved training epoch is known.

set_data_scalers(scaler_node_in, scaler_edge_in, scaler_global_in, scaler_node_out, scaler_edge_out, scaler_global_out)[source]¶

Set fitted model data scalers.

Parameters:

scaler_node_in ({TorchMinMaxScaler, TorchMinMaxScaler}) – Data scaler for input node features.
scaler_edge_in ({TorchMinMaxScaler, TorchMinMaxScaler}) – Data scaler for input edge features.
scaler_global_in ({TorchMinMaxScaler, TorchMinMaxScaler}) – Data scaler for input global features.
scaler_node_out ({TorchMinMaxScaler, TorchMinMaxScaler}) – Data scaler for output node features.
scaler_edge_out ({TorchMinMaxScaler, TorchMinMaxScaler}) – Data scaler for output edge features.
scaler_global_out ({TorchMinMaxScaler, TorchMinMaxScaler}) – Data scaler for output global features.

set_device(device_type)[source]¶

Set device on which torch.Tensor is allocated.

Parameters:

device_type ({'cpu', 'cuda'}) – Type of device on which torch.Tensor is allocated.
device (torch.device) – Device on which torch.Tensor is allocated.

set_extra_state(state)¶

Set extra state contained in the loaded state_dict.

This function is called from load_state_dict() to handle any extra state found within the state_dict. Implement this function and a corresponding get_extra_state() for your module if you need to store extra state within its state_dict.

Parameters:: state (dict) – Extra state from the state_dict
Return type:: None

share_memory()¶

See torch.Tensor.share_memory_().

Return type:: TypeVar(T, bound= Module)

state_dict(*args, destination=None, prefix='', keep_vars=False)¶

Return a dictionary containing references to the whole state of the module.

Both parameters and persistent buffers (e.g. running averages) are included. Keys are corresponding parameter and buffer names. Parameters and buffers set to None are not included.

Note

The returned object is a shallow copy. It contains references to the module’s parameters and buffers.

Warning

Currently state_dict() also accepts positional arguments for destination, prefix and keep_vars in order. However, this is being deprecated and keyword arguments will be enforced in future releases.

Warning

Please avoid the use of argument destination as it is not designed for end-users.

Parameters:

destination (dict, optional) – If provided, the state of module will be updated into the dict and the same object is returned. Otherwise, an OrderedDict will be created and returned. Default: None.
prefix (str, optional) – a prefix added to parameter and buffer names to compose the keys in state_dict. Default: ''.
keep_vars (bool, optional) – by default the Tensor s returned in the state dict are detached from autograd. If it’s set to True, detaching will not be performed. Default: False.

Returns:

a dictionary containing a whole state of the module

Return type:

dict

Example:

>>> # xdoctest: +SKIP("undefined vars")
>>> module.state_dict().keys()
['bias', 'weight']

to(*args, **kwargs)¶

Move and/or cast the parameters and buffers.

This can be called as

to(device=None, dtype=None, non_blocking=False)

to(dtype, non_blocking=False)

to(tensor, non_blocking=False)

to(memory_format=torch.channels_last)

Its signature is similar to torch.Tensor.to(), but only accepts floating point or complex dtypes. In addition, this method will only cast the floating point or complex parameters and buffers to dtype (if given). The integral parameters and buffers will be moved device, if that is given, but with dtypes unchanged. When non_blocking is set, it tries to convert/move asynchronously with respect to the host if possible, e.g., moving CPU Tensors with pinned memory to CUDA devices.

See below for examples.

Note

This method modifies the module in-place.

Parameters:

device (torch.device) – the desired device of the parameters and buffers in this module
dtype (torch.dtype) – the desired floating point or complex dtype of the parameters and buffers in this module
tensor (torch.Tensor) – Tensor whose dtype and device are the desired dtype and device for all parameters and buffers in this module
memory_format (torch.memory_format) – the desired memory format for 4D parameters and buffers in this module (keyword only argument)

Returns:

self

Return type:

Module

Examples:

>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> linear = nn.Linear(2, 2)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]])
>>> linear.to(torch.double)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]], dtype=torch.float64)
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA1)
>>> gpu1 = torch.device("cuda:1")
>>> linear.to(gpu1, dtype=torch.half, non_blocking=True)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1')
>>> cpu = torch.device("cpu")
>>> linear.to(cpu)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16)

>>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble)
>>> linear.weight
Parameter containing:
tensor([[ 0.3741+0.j,  0.2382+0.j],
        [ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128)
>>> linear(torch.ones(3, 2, dtype=torch.cdouble))
tensor([[0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)

to_empty(*, device, recurse=True)¶

Move the parameters and buffers to the specified device without copying storage.

Parameters:

device (torch.device) – The desired device of the parameters and buffers in this module.
recurse (bool) – Whether parameters and buffers of submodules should be recursively moved to the specified device.

Returns:

self

Return type:

Module

train(mode=True)¶

Set the module in training mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

Parameters:: mode (bool) – whether to set training mode (True) or evaluation mode (False). Default: True.
Returns:: self
Return type:: Module

type(dst_type)¶

Casts all parameters and buffers to dst_type.

Note

This method modifies the module in-place.

Parameters:: dst_type (type or string) – the desired type
Returns:: self
Return type:: Module

xpu(device=None)¶

Move all model parameters and buffers to the XPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on XPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: self
Return type:: Module

zero_grad(set_to_none=True)¶

Reset gradients of all model parameters.

See similar function under torch.optim.Optimizer for more context.

Parameters:: set_to_none (bool) – instead of setting to zero, set the grads to None. See torch.optim.Optimizer.zero_grad() for details.
Return type:: None