tart.representation#

tart.representation.config module#

Configs for model and optimizer

tart.representation.config.build_feature_configs(parser)[source]#

build graph feature config arguments

Parameters:: parser (ArgumentParser) – argparse parser
Return type:: None

tart.representation.config.build_model_configs(parser)[source]#

build model config arguments

Parameters:: parser (ArgumentParser) – argparse parser
Return type:: None

tart.representation.config.build_optimizer_configs(parser)[source]#

build optimizer config arguments

Parameters:: parser (ArgumentParser) – argparse parser
Return type:: None

tart.representation.config.init_user_configs(args, configs_json, tune=False)[source]#

initialize user defined configs

Parameters:

args (Namespace) – argparse namespace
configs_json (Dict) – user defined configs

Raises:

ValueError – node_feats not provided in configs.json
ValueError – edge_feats not provided in configs.json
ValueError – node and edge feats names overlap

Return type:

Namespace

Returns:

Namespace – updated argparse namespace

tart.representation.config.make_tunable(parser, tunable)[source]#

make select arguments tunable

Parameters:

parser (ArgumentParser) – argparse parser
tunable (List[str]) – list of arguments to make tunable

Return type:

None

tart.representation.dataset module#

class tart.representation.dataset.Corpus(args, feat_encoder, train=True)[source]#

Bases: object

Initialize the corpus generator

NOTE: new batch of graphs (positive and negative) are iteratively generated on the fly by sampling from the dataset.

Parameters:

args (Namespace) – tart configs
feat_encoder (Callable) – function to encode graph features
train (bool, optional) – train/test corpus. Defaults to True.

gen_data_loader(batch_size, train=True)[source]#

Initialize a data loader for the corpus

Parameters:

batch_size (int) – batch size
train (bool, optional) – train/test corpus. Defaults to True.

Return type:

DataLoader

Returns:

DataLoader – _description_

class tart.representation.dataset.GraphDataset(root, name, n_samples, feat_encoder, args, transform=None, pre_transform=None, pre_filter=None)[source]#

Bases: Dataset

Dataset of graphs

Parameters:

root (str) – root directory of the dataset
name (str) – name of the dataset
n_samples (int) – number of samples to generate
feat_encoder (Callable) – function to encode graph str features
args (Namespace) – tart configs
transform (Optional[Callable], optional) – _description_. Defaults to None.
pre_transform (Optional[Callable], optional) – _description_. Defaults to None.
pre_filter (Optional[Callable], optional) – _description_. Defaults to None.

download()[source]#: Downloads the dataset to the self.raw_dir folder.

get(idx)[source]#

load a processed graph from disk.

Parameters:: idx (int) – index of graph to load
Raises:: FileNotFoundError – if graph is not found
Return type:: BaseData
Returns:: BaseData – graph data object

get_summary()#: Collects summary statistics for the dataset.

property has_download: bool#: Checks whether the dataset defines a download() method.

property has_process: bool#: Checks whether the dataset defines a process() method.

index_select(idx)#

Creates a subset of the dataset from specified indices idx. Indices idx can be a slicing object, e.g., [2:5], a list, a tuple, or a torch.Tensor or np.ndarray of type long or bool.

Return type:: Dataset

indices()#

Return type:: Sequence

len()[source]#

Number of graphs in the dataset

Return type:: int
Returns:: int – number of graphs in the dataset

property num_classes: int#: Returns the number of classes in the dataset.

property num_edge_attributes: int#

Number of edge attributes

Returns:: int – number of edge attributes

property num_edge_features: int#: Returns the number of features per edge in the dataset.

property num_edge_labels: int#

Number of edge labels

Returns:: int – number of edge labels

property num_features: int#: Returns the number of features per node in the dataset. Alias for num_node_features.

property num_node_attributes: int#

Number of node attributes

Returns:: int – number of node attributes

property num_node_features: int#: Returns the number of features per node in the dataset.

property num_node_labels: int#

Number of node labels

Returns:: int – number of node labels

pre_transform(data)[source]#

print_summary()#: Prints summary statistics of the dataset to the console.

process()[source]#

process and store graphs as a Data object onto the disk

Return type:: None

property processed_dir: str#

property processed_file_names: List[str]#

List of processed file names

note: currently returns [], so that the dataset is reprocessed on every run.

Returns:: List[str] – list of processed file names

property processed_paths: List[str]#: The absolute filepaths that must be present in order to skip processing.

random_samples_generator(graph_sizes, count)[source]#

Generate random samples of graphs

Steps:

choose a random size for graph
choose a random target graph
perform random bfs traversal in neighborhood = size
choose a random but anchored query = positive e.g.
repeat for negative e.g. but with different random graph for the query

Parameters:

graph_sizes (List[int]) – distribution of graph sizes
count (int) – number of graphs

Return type:

None

property raw_dir: str#

property raw_file_names: List[str]#

List of raw file names

Returns:: List[str] – list of raw file names

property raw_paths: List[str]#: The absolute filepaths that must be present in order to skip downloading.

sample_neigh(ps, count, size)[source]#

random bfs walk to find neighborhood graphs of a set size

Parameters:

ps (List[int]) – distribution of graph sizes
count (int) – number of graphs
size (int) – size of subgraph to sample

Return type:

Tuple[Graph, List[int]]

Returns:

Tuple[nx.Graph, List[int]] – graph and list of nodes in subgraph

shuffle(return_perm=False)#

Randomly shuffles the examples in the dataset.

Parameters:: return_perm (bool, optional) – If set to True, will also return the random permutation used to shuffle the dataset. (default: False)
Return type:: Union[Dataset, Tuple[Dataset, Tensor]]

to_datapipe()#

Converts the dataset into a torch.utils.data.DataPipe.

The returned instance can then be used with :pyg:`PyG's` built-in DataPipes for baching graphs as follows:

from torch_geometric.datasets import QM9

dp = QM9(root='./data/QM9/').to_datapipe()
dp = dp.batch_graphs(batch_size=2, drop_last=True)

for batch in dp:
    pass

See the PyTorch tutorial for further background on DataPipes.

tart.representation.dataset.my_collate(batch)[source]#: dummy collate fn to just return data as is

tart.representation.train module#

tart.representation.train.tart_train(user_config_file, tune=False, trials=0)[source]#

tart’s train API

Parameters:

user_config_file (str) – config file path
tune (bool, optional) – flag to perform hyperparam tuning. Defaults to False.
trials (int, optional) – #trials for hyperparam tuning . Defaults to None.

Return type:

None

tart.representation.train.train(args, model, corpus, in_queue, out_queue)[source]#

Train a single iteration for the model on a corpus of graphs. NOTE: This function is called by each worker process.

Parameters:

args (Namespace) – tart configs
model (nn.Module) – tart model to train
corpus (Corpus) – corpus generator for graphs
in_queue (mp.Queue) – multiprocessing queue for input
out_queue (mp.Queue) – multiprocessing queue for output

tart.representation.train.train_loop(args, feat_encoder)[source]#

train the model for a number of iterations by spinning up a number of workers.

Parameters:

args (Namespace) – tart configs
feat_encoder (Callable) – encoder function that converts string to torch.tensor

tart.representation.test module#

tart.representation.test.precision(pred, labels)[source]#

Calculate precision for predictions.

Parameters:

pred (torch.Tensor) – tensor of predicted labels
labels (torch.Tensor) – tensor of true labels

Return type:

float

Returns:

float – average precision

tart.representation.test.recall(pred, labels)[source]#

Calculate recall for predictions.

Parameters:

pred (torch.Tensor) – tensor of predicted labels
labels (torch.Tensor) – tensor of true labels

Return type:

float

Returns:

float – average recall

tart.representation.test.tart_test(user_config_file)[source]#

tart’s test API

Parameters:: user_config_file (str) – config file path

tart.representation.test.test(model, dataloader)[source]#

Test the model on a corpus of graphs loaded by a dataloader.

Parameters:

model (nn.Module) – tart model to test
dataloader (DataLoader) – dataloader for test data

tart.representation.test.validation(args, model, test_pts, logger, batch_n, epoch)[source]#

validate the model on the validation set

Parameters:

args (Namespace) – tart configs
model (nn.Module) – tart model
test_pts (List) – validation set
logger (SummaryWriter) – tensorboard logger
batch_n (int) – batch number
epoch (int) – epoch number

tart.representation.encoders module#

tart.representation.encoders.codebert_bpe_encoder(x)[source]#

feature encoder using CodeBert BPE tokenizer

Parameters:: x (str) – string to be encoded
Return type:: tensor
Returns:: torch.tensor – encoding of the string

tart.representation.encoders.codebert_encoder(x)[source]#

feature encoder using CodeBert model

Parameters:: x (str) – string to be encoded
Return type:: tensor
Returns:: torch.tensor – encoding of the string

tart.representation.encoders.get_feature_encoder(encoder_name, **kwargs)[source]#

Factory function to get a feature encoder

Parameters:: encoder_name (str) – name of the encoder to retrieve
Return type:: Callable[[str], tensor]
Returns:: Callable[[str], torch.tensor] – callable feature encoder

tart.representation.models module#

models to learn tensor representations of graphs with specific relational properties using graph neural networks

class tart.representation.models.BasicGNN(input_dim, hidden_dim, output_dim, args)[source]#

Bases: Module

Basic GNN model with the following configurable options: - number of layers - aggregation type - skip connections

Initializes internal Module state, shared by both nn.Module and ScriptModule.

add_module(name, module)#

Adds 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)#

Applies 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

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.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

buffers(recurse=True)#

Returns 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)

children()#

Returns an iterator over immediate children modules.

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

cpu()#

Moves all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

cuda(device=None)#

Moves 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

double()#

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

eval()#

Sets 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.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

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

float()#

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

forward(data)[source]#

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

get_buffer(target)#

Returns the buffer given by target if it exists, otherwise throws 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.)
Return type:: Tensor
Returns:: torch.Tensor – The buffer referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not a buffer

get_extra_state()#

Returns 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 pickleable 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.

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

get_parameter(target)#

Returns the parameter given by target if it exists, otherwise throws 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.)
Return type:: Parameter
Returns:: torch.nn.Parameter – The Parameter referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Parameter

get_submodule(target)#

Returns the submodule given by target if it exists, otherwise throws 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.)
Return type:: Module
Returns:: torch.nn.Module – The submodule referenced by target
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.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

ipu(device=None)#

Moves 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

load_state_dict(state_dict, strict=True)#

Copies 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.

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

Returns:

NamedTuple with missing_keys and unexpected_keys fields – * missing_keys is a list of str containing the missing keys * unexpected_keys is a list of str containing the unexpected keys

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()#

Returns an iterator over all modules in the network.

Yields:: Module – a module in the network
Return type:: Iterator[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.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)

named_buffers(prefix='', recurse=True)#

Returns 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) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.

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()#

Returns 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)#

Returns 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)#

Returns 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.

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)#

Returns 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)

register_backward_hook(hook)#

Registers 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.

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

register_buffer(name, tensor, persistent=True)#

Adds 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)#

Registers a forward hook on the module.

The hook will be called every time after forward() has computed an output. It should have the following signature:

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

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.

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

register_forward_pre_hook(hook)#

Registers a forward pre-hook on the module.

The hook will be called every time before forward() is invoked. It should have the following signature:

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

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).

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

register_full_backward_hook(hook)#

Registers a backward hook on the module.

The hook will be called every time the gradients with respect to module inputs 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.

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

register_load_state_dict_post_hook(hook)#

Registers 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 clearning out both missing and unexpected keys will avoid an error.

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

register_module(name, module)#

Alias for add_module().

Return type:: None

register_parameter(name, param)#

Adds 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

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.
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

set_extra_state(state)#

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

share_memory()#

See torch.Tensor.share_memory_()

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

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

Returns 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:

dict – a dictionary containing a whole state of the module

Example:

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

to(*args, **kwargs)#

Moves and/or casts 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:

Module – self

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)#

Moves 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.
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

train(mode=True)#

Sets the module in training mode.

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

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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

xpu(device=None)#

Moves 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

zero_grad(set_to_none=False)#

Sets gradients of all model parameters to zero. 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

class tart.representation.models.SubgraphEmbedder(input_dim, hidden_dim, args)[source]#

Bases: Module

Model for order embeddings. Uses a GNN (encoder) to embed graphs into a vector space, and then uses a MLP (classifier) to predict if queries are subgraphs of targets.

Initializes internal Module state, shared by both nn.Module and ScriptModule.

add_module(name, module)#

Adds 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)#

Applies 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

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.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

buffers(recurse=True)#

Returns 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)

children()#

Returns an iterator over immediate children modules.

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

cpu()#

Moves all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

criterion(pred, labels)[source]#: Loss function for subgraph ordering in embedding space. error = amount of violation (if b is a subgraph of a). For + examples, train to minimize error -> 0; For - examples, train to minimize error to be atleast self.margin

cuda(device=None)#

Moves 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

double()#

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

eval()#

Sets the module in evaluation mode.

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.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

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

float()#

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

forward(emb_targets, emb_queries)[source]#

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

get_buffer(target)#

Returns the buffer given by target if it exists, otherwise throws 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.)
Return type:: Tensor
Returns:: torch.Tensor – The buffer referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not a buffer

get_extra_state()#

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

get_parameter(target)#

Returns the parameter given by target if it exists, otherwise throws 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.)
Return type:: Parameter
Returns:: torch.nn.Parameter – The Parameter referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Parameter

get_submodule(target)#

Returns the submodule given by target if it exists, otherwise throws 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.)

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.)
Return type:: Module
Returns:: torch.nn.Module – The submodule referenced by target
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.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

ipu(device=None)#

Moves 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

load_state_dict(state_dict, strict=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

Returns:

NamedTuple with missing_keys and unexpected_keys fields – * missing_keys is a list of str containing the missing keys * unexpected_keys is a list of str containing the unexpected keys

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()#

Returns an iterator over all modules in the network.

Yields:: Module – a module in the network
Return type:: Iterator[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.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)

named_buffers(prefix='', recurse=True)#

Returns 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) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.

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()#

Returns 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)#

Returns 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)#

Returns 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.

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)#

Returns 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(pred)[source]#: Inference API: predict if queries are subgraphs of targets :type pred: :param pred: embeddings of pairs of graphs :type pred: List<emb_t, emb_q>

predictv2(pred)[source]#: Inference API v2: predict if queries are subgraphs of targets :type pred: :param pred: embeddings of pairs of graphs :type pred: List<emb_t, emb_q>

register_backward_hook(hook)#

Registers 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.

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

register_buffer(name, tensor, persistent=True)#

Adds a buffer to the module.

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)#

Registers a forward hook on the module.

The hook will be called every time after forward() has computed an output. It should have the following signature:

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

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

register_forward_pre_hook(hook)#

Registers a forward pre-hook on the module.

The hook will be called every time before forward() is invoked. It should have the following signature:

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

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

register_full_backward_hook(hook)#

Registers a backward hook on the module.

The hook will be called every time the gradients with respect to module inputs are computed. The hook should have the following signature:

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

Warning

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

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

register_load_state_dict_post_hook(hook)#

Registers 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 given incompatible_keys can be modified inplace if needed.

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

register_module(name, module)#

Alias for add_module().

Return type:: None

register_parameter(name, param)#

Adds 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

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.
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

set_extra_state(state)#

Parameters:: state (dict) – Extra state from the state_dict

share_memory()#

See torch.Tensor.share_memory_()

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

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

Returns 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

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:

dict – a dictionary containing a whole state of the module

Example:

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

to(*args, **kwargs)#

Moves and/or casts 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)

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:

Module – self

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)#

Moves 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.
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

train(mode=True)#

Sets the module in training mode.

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

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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

xpu(device=None)#

Moves 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

zero_grad(set_to_none=False)#

Sets gradients of all model parameters to zero. 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

class tart.representation.models.WeightedGINConv(nn, eps=0, train_eps=False, **kwargs)[source]#

Bases: MessagePassing

WeightedGINConv implementation for PyG.

Initializes internal Module state, shared by both nn.Module and ScriptModule.

add_module(name, module)#

Adds 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

aggregate(inputs, index, ptr=None, dim_size=None)#

Aggregates messages from neighbors as \(\bigoplus_{j \in \mathcal{N}(i)}\).

Takes in the output of message computation as first argument and any argument which was initially passed to propagate().

By default, this function will delegate its call to the underlying Aggregation module to reduce messages as specified in __init__() by the aggr argument.

Return type:: Tensor

apply(fn)#

Applies 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

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.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

buffers(recurse=True)#

Returns 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)

children()#

Returns an iterator over immediate children modules.

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

cpu()#

Moves all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

cuda(device=None)#

Moves 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

double()#

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

edge_update()#

Computes or updates features for each edge in the graph. This function can take any argument as input which was initially passed to edge_updater(). Furthermore, tensors passed to edge_updater() can be mapped to the respective nodes \(i\) and \(j\) by appending _i or _j to the variable name, .e.g. x_i and x_j.

Return type:: Tensor

edge_updater(edge_index, **kwargs)#

The initial call to compute or update features for each edge in the graph.

Parameters:

edge_index (torch.Tensor or SparseTensor) – A torch.Tensor, a torch_sparse.SparseTensor or a torch.sparse.Tensor that defines the underlying graph connectivity/message passing flow. See propagate() for more information.
**kwargs – Any additional data which is needed to compute or update features for each edge in the graph.

eval()#

Sets the module in evaluation mode.

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.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

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

float()#

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

get_buffer(target)#

Returns the buffer given by target if it exists, otherwise throws 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.)
Return type:: Tensor
Returns:: torch.Tensor – The buffer referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not a buffer

get_extra_state()#

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

get_parameter(target)#

Returns the parameter given by target if it exists, otherwise throws 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.)
Return type:: Parameter
Returns:: torch.nn.Parameter – The Parameter referenced by target
Raises:: AttributeError – If the target string references an invalid path or resolves to something that is not an nn.Parameter

get_submodule(target)#

Returns the submodule given by target if it exists, otherwise throws 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.)

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.)
Return type:: Module
Returns:: torch.nn.Module – The submodule referenced by target
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.

Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

ipu(device=None)#

Moves 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

jittable(typing=None)#

Analyzes the MessagePassing instance and produces a new jittable module.

Parameters:: typing (str, optional) – If given, will generate a concrete instance with forward() types based on typing, e.g., "(Tensor, Optional[Tensor]) -> Tensor".
Return type:: MessagePassing

load_state_dict(state_dict, strict=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

Returns:

NamedTuple with missing_keys and unexpected_keys fields – * missing_keys is a list of str containing the missing keys * unexpected_keys is a list of str containing the unexpected keys

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.

message(x_j, edge_weight)[source]#: Constructs messages from node \(j\) to node \(i\) in analogy to \(\phi_{\mathbf{\Theta}}\) for each edge in edge_index. This function can take any argument as input which was initially passed to propagate(). Furthermore, tensors passed to propagate() can be mapped to the respective nodes \(i\) and \(j\) by appending _i or _j to the variable name, .e.g. x_i and x_j.

message_and_aggregate(adj_t)#

Fuses computations of message() and aggregate() into a single function. If applicable, this saves both time and memory since messages do not explicitly need to be materialized. This function will only gets called in case it is implemented and propagation takes place based on a torch_sparse.SparseTensor or a torch.sparse.Tensor.

Return type:: Tensor

modules()#

Returns an iterator over all modules in the network.

Yields:: Module – a module in the network
Return type:: Iterator[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.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)

named_buffers(prefix='', recurse=True)#

Returns 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) – if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module.

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()#

Returns 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)#

Returns 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)#

Returns 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.

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)#

Returns 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)

propagate(edge_index, size=None, **kwargs)#

The initial call to start propagating messages.

Parameters:

edge_index (torch.Tensor or SparseTensor) – A torch.Tensor, a torch_sparse.SparseTensor or a torch.sparse.Tensor that defines the underlying graph connectivity/message passing flow. edge_index holds the indices of a general (sparse) assignment matrix of shape [N, M]. If edge_index is a torch.Tensor, its dtype should be torch.long and its shape needs to be defined as [2, num_messages] where messages from nodes in edge_index[0] are sent to nodes in edge_index[1] (in case flow="source_to_target"). If edge_index is a torch_sparse.SparseTensor or a torch.sparse.Tensor, its sparse indices (row, col) should relate to row = edge_index[1] and col = edge_index[0]. The major difference between both formats is that we need to input the transposed sparse adjacency matrix into propagate().
size ((int, int), optional) – The size (N, M) of the assignment matrix in case edge_index is a torch.Tensor. If set to None, the size will be automatically inferred and assumed to be quadratic. This argument is ignored in case edge_index is a torch_sparse.SparseTensor or a torch.sparse.Tensor. (default: None)
**kwargs – Any additional data which is needed to construct and aggregate messages, and to update node embeddings.

register_aggregate_forward_hook(hook)#

Registers a forward hook on the module. The hook will be called every time after aggregate() has computed an output. See register_propagate_forward_hook() for more information.

Return type:: RemovableHandle

register_aggregate_forward_pre_hook(hook)#

Registers a forward pre-hook on the module. The hook will be called every time before aggregate() is invoked. See register_propagate_forward_pre_hook() for more information.

Return type:: RemovableHandle

register_backward_hook(hook)#

Registers 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.

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

register_buffer(name, tensor, persistent=True)#

Adds a buffer to the module.

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_edge_update_forward_hook(hook)#

Registers a forward hook on the module. The hook will be called every time after edge_update() has computed an output. See register_propagate_forward_hook() for more information.

Return type:: RemovableHandle

register_edge_update_forward_pre_hook(hook)#

Registers a forward pre-hook on the module. The hook will be called every time before edge_update() is invoked. See register_propagate_forward_pre_hook() for more information.

Return type:: RemovableHandle

register_forward_hook(hook)#

Registers a forward hook on the module.

The hook will be called every time after forward() has computed an output. It should have the following signature:

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

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

register_forward_pre_hook(hook)#

Registers a forward pre-hook on the module.

The hook will be called every time before forward() is invoked. It should have the following signature:

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

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

register_full_backward_hook(hook)#

Registers a backward hook on the module.

The hook will be called every time the gradients with respect to module inputs are computed. The hook should have the following signature:

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

Warning

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

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

register_load_state_dict_post_hook(hook)#

Registers 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 given incompatible_keys can be modified inplace if needed.

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

register_message_and_aggregate_forward_hook(hook)#

Registers a forward hook on the module. The hook will be called every time after message_and_aggregate() has computed an output. See register_propagate_forward_hook() for more information.

Return type:: RemovableHandle

register_message_and_aggregate_forward_pre_hook(hook)#

Registers a forward pre-hook on the module. The hook will be called every time before message_and_aggregate() is invoked. See register_propagate_forward_pre_hook() for more information.

Return type:: RemovableHandle

register_message_forward_hook(hook)#

Registers a forward hook on the module. The hook will be called every time after message() has computed an output. See register_propagate_forward_hook() for more information.

Return type:: RemovableHandle

register_message_forward_pre_hook(hook)#

Registers a forward pre-hook on the module. The hook will be called every time before message() is invoked. See register_propagate_forward_pre_hook() for more information.

Return type:: RemovableHandle

register_module(name, module)#

Alias for add_module().

Return type:: None

register_parameter(name, param)#

Adds 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_propagate_forward_hook(hook)#

Registers a forward hook on the module. The hook will be called every time after propagate() has computed an output. It should have the following signature:

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

The hook can modify the output. Input keyword arguments are passed to the hook as a dictionary in inputs[-1].

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

Return type:: RemovableHandle

register_propagate_forward_pre_hook(hook)#

Registers a forward pre-hook on the module. The hook will be called every time before propagate() is invoked. It should have the following signature:

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

The hook can modify the input. Input keyword arguments are passed to the hook as a dictionary in inputs[-1].

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

Return type:: RemovableHandle

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.
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

reset_parameters()[source]#: Resets all learnable parameters of the module.

set_extra_state(state)#

Parameters:: state (dict) – Extra state from the state_dict

share_memory()#

See torch.Tensor.share_memory_()

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

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

Returns 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

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:

dict – a dictionary containing a whole state of the module

Example:

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

to(*args, **kwargs)#

Moves and/or casts 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)

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:

Module – self

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)#

Moves 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.
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

train(mode=True)#

Sets the module in training mode.

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

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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

update(inputs)#

Updates node embeddings in analogy to \(\gamma_{\mathbf{\Theta}}\) for each node \(i \in \mathcal{V}\). Takes in the output of aggregation as first argument and any argument which was initially passed to propagate().

Return type:: Tensor

xpu(device=None)#

Moves 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
Return type:: TypeVar(T, bound= Module)
Returns:: Module – self

zero_grad(set_to_none=False)#

Sets gradients of all model parameters to zero. 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

tart.representation#

tart.representation.config module#

tart.representation.dataset module#

tart.representation.train module#

tart.representation.test module#

tart.representation.encoders module#

tart.representation.models module#

Module contents#