2.1.1.1.1.14. emicroml.modelling.cbed.distortion.estimation.MLModel

class MLModel(num_pixels_across_each_cbed_pattern=512, max_num_disks_in_any_cbed_pattern=90, architecture='distoptica_net', mini_batch_norm_eps=1e-05, normalization_weights=None, normalization_biases=None)

Bases: _MLModel

A machine learning model for distortion estimation in CBED.

The current class is a subclass of torch.nn.Module.

A given machine learning (ML) model represented by the current class takes as input a mini-batch of images, where each image is assumed to depict a distorted CBED pattern, and as output, the ML model predicts sets of coordinate transformation parameters that specify the coordinate transformations that describe the distortions of the input images. The coordinate transformation used to describe the distortions of an image is defined in the documentation for the class distoptica.StandardCoordTransformParams. The parameter set parameterizing said coordinate transformation is referred to as the “standard” coordinate transformation parameter set, and is represented by the class distoptica.StandardCoordTransformParams.

ML models are trained using the emicroml.modelling.cbed.distortion.estimation.MLModelTrainer.

After a ML model has been trained, users should use the method emicroml.modelling.cbed.distortion.estimation.MLModel.make_predictions() of the current class to make predictions.

Parameters:

num_pixels_across_each_cbed_patternint, optional

The number of pixels across each imaged CBED pattern stored in the ML dataset used or to be used to train the ML model. This parameter is expected to be equal to the instance attribute emicroml.modelling.cbed.distortion.estimation.MLDataset.num_pixels_across_each_cbed_pattern of the instance of the class emicroml.modelling.cbed.distortion.estimation.MLDataset representing the aforementioned ML dataset. Moreover, the parameter is expected to be a positive integer that is divisible by 2**5.

max_num_disks_in_any_cbed_patternint, optional

The maximum possible number of CBED disks in any imaged CBED pattern stored in the ML dataset used or to be used to train the ML model. This parameter is expected to be equal to the instance attribute emicroml.modelling.cbed.distortion.estimation.MLDataset.max_num_disks_in_any_cbed_pattern of the instance of the class emicroml.modelling.cbed.distortion.estimation.MLDataset representing the aforementioned ML dataset.

architecturestr, optional

This parameter specifies the network architecture of the ML model. At the moment, only one network architecture is available for this ML model, and it is specified by setting architecture to "distoptica_net", referring to the DistopticaNet architecture. Below we refer to this network architecture as the DistopticaNet architecture.

In short, the DistopticaNet architecture is a custom residual network with 37 non-trivial layers, and downsampling operations being performed using strided convolutions rather than pooling. By a non-trivial layer, we mean either a fully connected layer or a 2D convolutional layer with kernel dimensions other than \(1 \times 1\).

Before describing in more detail the DistopticaNet architecture, it is worth introducing several smaller networks used to construct the architecture.

First, we introduce the residual network building block, defined graphically as:

Fig. 2.1.1.1.1.14.1 The residual network building block, where \(C_1\), \(C_2\), \(K\), \(N_{\downarrow}\), and \(f\) are the number of input channels, the number of output channels, the maximum kernel size, the number of downsamplings to perform in the first convolutional layer, and the final activation function respectively.

The above image introduces several mathematical objects: \(\text{conv_2d}\left(C_{1},C_{2},K,S\right)\) is a 2D convolutional layer with \(C_1\) input channels, \(C_2\) output channels, a kernel size of \(K\), a stride of \(S\), a zero-padding width of \((K-1) // 2\) on all sides, all biases fixed to zero, a dilation of unity, and all inputs are convolved to all outputs; \(\text{mini_batch_norm_2d}\left(C\right)\) is a mini-batch normalization layer of 2D inputs with \(C\) input channels; \(\text{relu}\) is the ReLU activation function; \(\text{shortcut}\left(C_{1},C_{2},N_{\downarrow}\right)\) is \(\text{conv_2d}\left(C_{1},C_{2},1,1+N_{\downarrow}\right)\) followed by \(\text{mini_batch_norm_2d}\left(C_{2}\right)\) if either \(C_{1} \neq C_{2}\) or \(N_{\downarrow} > 0\), else it is an identity shortcut connection; \(+\) is the addition operator; \(f\) is an activation function.

Next, we introduce the residual network stage, defined graphically as:

Fig. 2.1.1.1.1.14.2 The residual network stage, where \(C\), \(K\), \(N_B\), and \(f\) are the number of input channels, the maximum kernel size, the number of residual network building blocks in the stage, and the final activation function respectively.

Next, we introduce the “enhance” operation, defined graphically as:

Fig. 2.1.1.1.1.14.3 The enhance operation.

The above image introduces a few mathematical objects: \(\text{min-max normalize}\) is the min-max normalization operation, applied to each image stored in the input tensor of the entry flow; \(\text{pow}\left(\gamma\right)\) is the gamma correction operation with the power-law exponent \(\gamma\); \(\text{equalize}\) is the histogram equalization operation, applied to each feature map.

Next, we introduce the DistopticaNet entry flow, defined graphically as:

Fig. 2.1.1.1.1.14.4 The DistopticaNet entry flow, where \(C_1\), \(C_2\), \(K_1\), and \(K_2\) are the number of input channels, the number of output channels, the kernel size of the first convolutional layer, and the maximum kernel size of the resnet building blocks respectively.

Next, we introduce the DistopticaNet middle flow, defined graphically as:

Fig. 2.1.1.1.1.14.5 The DistopticaNet middle flow, where \(C_1\), \(K\), and \(\mathbf{N}_{\mathbf{B}}\) are the number of input channels, the maximum kernel size, and the building block counts in the residual network stages of the middle flow respectively.

The above image introduces the block of the general form \(X \leftarrow Y\), which denotes the operation of setting the variable \(X\) to the value of \(Y\) while leaving the input tensor of said block unchanged.

Next, we introduce the DistopticaNet exit flow, defined graphically as:

Fig. 2.1.1.1.1.14.6 The no-pool DistopticaNet exit flow, where \(F_1\), \(F_2\), and \(F_3\) are the number of nodes in the third last, the second last, and the last layers respectively.

The above image introduces several mathematical objects: \(\text{flatten}\) is the flatten operation applied to all but the ML data instance dimension; \(\text{fc}\left(F_{1},F_{2},\text{biases}\right)\) is a fully-connected layer with \(F_1\) input channels, \(F_2\) output channels, and the biases fixed to zero if the boolean variable \(\text{biases}\) is set to \(\text{False}\); \(\text{mini_batch_norm_1d}\left(C\right)\) is a mini-batch normalization layer of 1D inputs with \(C\) input channels.

Finally, the DistopticaNet architecture is defined graphically as:

Fig. 2.1.1.1.1.14.7 The "distoptica_net" architecture, where \(W\) is the width of the input tensor in pixels.

See the documentation for the method emicroml.modelling.cbed.distortion.estimation.MLModel.forward() for a discussion on how the output tensor is parsed as a dictionary.

The weights of all the convolutional and fully-connected (FC) layers, except for those of the last FC layer, are He-initialized using the function torch.nn.init.kaiming_normal_(), with the parameters a, mode, nonlinearity, and generator set to 0, 'fan_out', 'relu', and None respectively. The weights of the last FC layer are Glorot-initialized using the function torch.nn.init.xavier_normal_(), with the parameters gain, and generator set to 5/3 and None respectively.

The biases of the last FC layer, and all of the mini-batch normalization layers are initialized to zero; the weights of all the mini-batch normalization layers except for those of the mini-batch normalization layers in \(\text{shortcut}\left(C_{1},C_{2},N_{\downarrow}\right)\) objects are normalized to unity; and the weights of the mini-batch normalization layers in \(\text{shortcut}\left(C_{1},C_{2},N_{\downarrow}\right)\) objects are normalized to zero.

mini_batch_norm_epsfloat, optional

This parameter specifies the value to use for the construction parameter eps for every construction of an instance of the class torch.nn.BatchNorm1d and every construction of an instance of the class torch.nn.BatchNorm2d. Must be a positive number.

normalization_weightsdict, optional

The normalization weights of the ML dataset used or to be used to train the ML model. This parameter is expected to be equal to the instance attribute emicroml.modelling.cbed.distortion.estimation.MLDataset.normalization_weights of the instance of the class emicroml.modelling.cbed.distortion.estimation.MLDataset representing the aforementioned ML dataset. See the documentation for the function emicroml.modelling.cbed.distortion.estimation.normalize_normalizable_elems_in_ml_data_dict() for a discussion on normalizing features of ML data instances.

normalization_biasesdict, optional

The normalization biases of the ML dataset used or to be used to train the ML model. This parameter is expected to be equal to the instance attribute emicroml.modelling.cbed.distortion.estimation.MLDataset.normalization_biases of the instance of the class emicroml.modelling.cbed.distortion.estimation.MLDataset representing the aforementioned ML dataset.

Attributes:

core_attrs

dict: The “core attributes”, i.e. the construction parameters.

Methods

add_module(name, module)	Add a child module to the current module.
apply(fn)	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([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Return the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(ml_inputs)	Perform forward propagation.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_core_attrs([deep_copy])	Return the "core attributes", i.e. the construction parameters, as a dict object.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
make_predictions(ml_inputs[, ...])	Make predictions according to machine learning inputs.
modules()	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
named_buffers([prefix, recurse, ...])	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([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
predict_distortion_models(cbed_pattern_images)	Predict distortion models according to a mini-batch of images.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
set_submodule(target, module[, strict])	Set the submodule given by target if it exists, otherwise throw an error.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Reset gradients of all model parameters.

__call__

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

Attributes:

core_attrs

dict: The “core attributes”, i.e. the construction parameters.

Methods

add_module(name, module)	Add a child module to the current module.
apply(fn)	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([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Return the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(ml_inputs)	Perform forward propagation.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_core_attrs([deep_copy])	Return the "core attributes", i.e. the construction parameters, as a dict object.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
make_predictions(ml_inputs[, ...])	Make predictions according to machine learning inputs.
modules()	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
named_buffers([prefix, recurse, ...])	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([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
predict_distortion_models(cbed_pattern_images)	Predict distortion models according to a mini-batch of images.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
set_submodule(target, module[, strict])	Set the submodule given by target if it exists, otherwise throw an error.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Reset gradients of all model parameters.

__call__

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.
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.
double	Casts all floating point parameters and buffers to double datatype.
eval	Set the module in evaluation mode.
extra_repr	Return the extra representation of the module.
float	Casts all floating point parameters and buffers to float datatype.
forward	Perform forward propagation.
get_buffer	Return the buffer given by target if it exists, otherwise throw an error.
get_core_attrs	Return the "core attributes", i.e. the construction parameters, as a dict object.
get_extra_state	Return any extra state to include in the module's state_dict.
get_parameter	Return the parameter given by target if it exists, otherwise throw an error.
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.
ipu	Move all model parameters and buffers to the IPU.
load_state_dict	Copy parameters and buffers from state_dict into this module and its descendants.
make_predictions	Make predictions according to machine learning inputs.
modules	Return an iterator over all modules in the network.
mtia	Move all model parameters and buffers to the MTIA.
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_distortion_models	Predict distortion models according to a mini-batch of images.
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_load_state_dict_pre_hook	Register a pre-hook to be run before module's load_state_dict() is called.
register_module	Alias for add_module().
register_parameter	Add a parameter to the module.
register_state_dict_post_hook	Register a post-hook for the state_dict() method.
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.
set_extra_state	Set extra state contained in the loaded state_dict.
set_submodule	Set the submodule given by target if it exists, otherwise throw an error.
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
core_attrs	dict: The "core attributes", i.e. the construction parameters.
dump_patches
training

__call__(*args, **kwargs)

Call self as a function.

add_module(name, module)

Add a child module to the current module.

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

Return type:

None

Args:

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.

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 torch.nn.init).

Return type:

TypeVar(T, bound= Module)

Args:

fn (Module -> None): function to be applied to each submodule

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. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Returns:

Module: self

buffers(recurse=True)

Return an iterator over module buffers.

Return type:

Iterator[Tensor]

Args:

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

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()

Return an iterator over immediate children modules.

Return type:

Iterator[Module]

Yields:

Module: a child 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.

property core_attrs

dict: The “core attributes”, i.e. the construction parameters.

Note that core_attrs should be considered read-only.

cpu()

Move all model parameters and buffers to the CPU. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Returns:

Module: self

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 the optimizer if the module will live on GPU while being optimized. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Args:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

double()

Casts all floating point parameters and buffers to double datatype. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Returns:

Module: self

eval()

Set the module in evaluation mode.

This has an effect only on certain modules. See the documentation of particular modules for details of their behaviors in training/evaluation mode, i.e. whether they are affected, e.g. Dropout, BatchNorm, etc.

This is equivalent with self.train(False).

See Locally disabling gradient computation 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()

Return 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. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Returns:

Module: self

forward(ml_inputs)

Perform forward propagation.

The current function forward propagates a dictionary representation ml_inputs of a mini-batch of machine learning (ML) inputs through the ML model.

The ML model takes as input a mini-batch of images, where each image is assumed to depict a distorted CBED pattern, and as output, the ML model predicts sets of coordinate transformation parameters that specify the coordinate transformations that describe the distortions of the input images. The coordinate transformation used to describe the distortions of an image is defined in the documentation for the class distoptica.StandardCoordTransformParams. The parameter set parameterizing said coordinate transformation is referred to as the “standard” coordinate transformation parameter set, and is represented by the class distoptica.StandardCoordTransformParams. See the documentation for said class for a discussion on standard coordinate transformation parameter sets.

The output tensor output_tensor of the neural network of the ML model is an 8-column PyTorch tensor, i.e. PyTorch matrix, of the data type torch.float32. Let mini_batch_size be the number of rows in the output_tensor. For each nonnegative integer n less than mini_batch_size, output_tensor[n] stores the predicted normalized parameters of the standard coordinate transformation that are suppose to describe the distortions of the n th input image of the mini-batch. The parameters are normalized according to the normalization weights and biases of the ML dataset used or to be used to train the ML model. See the documentation for the function emicroml.modelling.cbed.distortion.estimation.normalize_normalizable_elems_in_ml_data_dict() for a discussion on normalizing features of ML data instances, e.g. the standard coordinate transformation parameters. The normalization weights and biases are stored in core_attrs["normalization_weights"] and core_attrs["normalization_biases"] respectively, where core_attrs is the instance attribute emicroml.modelling.cbed.distortion.estimation.MLModel.core_attrs.

output_tensor[:, 0] stores the normalized quadratic radial distortion amplitudes, output_tensor[:, 1] stores the normalized spiral distortion amplitudes, output_tensor[:, 2:4] stores the normalized elliptical distortion vectors, output_tensor[:, 4:6] stores the normalized parabolic distortion vectors, and output_tensor[:, 6:8] stores the normalized distortion centers.

Parameters:

ml_inputsdict

The dictionary representation of the mini-batch of ML inputs.

ml_inputs must have only one dict key, the value of which being "cbed_pattern_images". ml_inputs["cbed_pattern_images"] must be a 3D PyTorch tensor of the data type torch.float32 storing the mini-batch of images assumed to depict distorted CBED patterns. For each nonnegative integer n less than mini_batch_size, ml_inputs["cbed_pattern_images"][n] stores the n th input image of the mini-batch. mini_batch_size must be positive and ml_inputs["cbed_pattern_images"].shape[1:] must be equal to 2*(num_pixels_across_each_cbed_pattern,), where num_pixels_across_each_cbed_pattern is core_attrs["num_pixels_across_each_cbed_pattern"], i.e. the number of pixels across each input image.

Returns:

ml_predictionsdict

The dictionary representation of the mini-batch of ML outputs.

Using the output tensor output_tensor discussed above, ml_predictions is constructed essentially by

ml_predictions = {"quadratic_radial_distortion_amplitudes": \
                  output_tensor[:, 0],
                  "spiral_distortion_amplitudes": \
                  output_tensor[:, 1],
                  "elliptical_distortion_vectors": \
                  output_tensor[:, 2:4],
                  "parabolic_distortion_vectors": \
                  output_tensor[:, 4:6],
                  "distortion_centers": \
                  output_tensor[:, 6:8]}

Users can use the function emicroml.modelling.cbed.distortion.estimation.ml_data_dict_to_distortion_models() to convert ml_predictions to a sequence of distortion models, with each distortion model being represented by the class distoptica.DistortionModel.

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.

Return type:

Tensor

Args:

target: The fully-qualified string name of the buffer

to look for. (See get_submodule for how to specify a fully-qualified string.)

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_core_attrs(deep_copy=True)

Return the “core attributes”, i.e. the construction parameters, as a dict object.

Parameters:

deep_copybool, optional

Let core_attrs denote the core attributes.

If deep_copy is set to True, then a deep copy of core_attrs is returned. Otherwise, a shallow copy of core_attrs is returned.

Returns:

core_attrsdict

The core attributes.

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 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)

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.

Return type:

Parameter

Args:

target: The fully-qualified string name of the Parameter

to look for. (See get_submodule for how to specify a fully-qualified string.)

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)

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 which 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.

Return type:

Module

Args:

target: The fully-qualified string name of the submodule

to look for. (See above example for how to specify a fully-qualified string.)

Returns:

torch.nn.Module: The submodule referenced by target

Raises:

AttributeError: If at any point along the path resulting from

the target string the (sub)path resolves to a non-existent attribute name or an object that is not an instance of nn.Module.

half()

Casts all floating point parameters and buffers to half datatype. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Returns:

Module: self

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 the optimizer if the module will live on IPU while being optimized. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Arguments:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

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.

Args:

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 set to False, the properties of the tensors

in the current module are preserved whereas setting it to True preserves properties of the Tensors in the state dict. The only exception is the requires_grad field of Default: ``False`

Returns:

NamedTuple with missing_keys and unexpected_keys fields:

• 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.

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.

make_predictions(ml_inputs, unnormalize_normalizable_elems_of_ml_predictions=False)

Make predictions according to machine learning inputs.

The machine learning (ML) model takes as input a mini-batch of images, where each image is assumed to depict a distorted CBED pattern, and as output, the ML model predicts sets of coordinate transformation parameters that specify the coordinate transformations that describe the distortions of the input images. The coordinate transformation used to describe the distortions of an image is defined in the documentation for the class distoptica.StandardCoordTransformParams. The parameter set parameterizing said coordinate transformation is referred to as the “standard” coordinate transformation parameter set, and is represented by the class distoptica.StandardCoordTransformParams. See the documentation for said class for a discussion on standard coordinate transformation parameter sets.

Parameters:

ml_inputsdict

The dictionary representation of the mini-batch of ML inputs. ml_inputs must have the dict key "cbed_pattern_images". ml_inputs["cbed_pattern_images"] must be a 3D PyTorch tensor of the data type torch.float32 storing the mini-batch of images assumed to depict distorted CBED patterns. Let mini_batch_size be ml_inputs["cbed_pattern_images"].shape[0], and core_attrs be the instance attribute emicroml.modelling.cbed.distortion.estimation.MLModel.core_attrs. For each nonnegative integer n less than mini_batch_size, ml_inputs["cbed_pattern_images"][n] stores the n th input image of the mini-batch. mini_batch_size must be positive and ml_inputs["cbed_pattern_images"].shape[1:] must be equal to 2*(num_pixels_across_each_cbed_pattern,), where num_pixels_across_each_cbed_pattern is core_attrs["num_pixels_across_each_cbed_pattern"], i.e. the number of pixels across each input image.

unnormalize_normalizable_elems_of_ml_predictionsbool

If unnormalize_normalizable_elems_of_ml_predictions is set to False, then the predicted parameters of the standard coordinate transformations are returned normalized. Otherwise, said parameters are returned unnormalized. See the description below of ml_predictions for more details on how this is implemented effectively.

Returns:

ml_predictionsdict

The dictionary representation of the mini-batch of ML outputs.

Let ml_model be an instance of the current class. Then ml_predictions is calculated effectively by:

import emicroml.modelling.cbed.distortion.estimation

module_alias = \
    emicroml.modelling.cbed.distortion.estimation
func_alias = \
    module_alias.unnormalize_normalizable_elems_in_ml_data_dict

ml_predictions = ml_model.forward(ml_inputs)

if unnormalize_normalizable_elems_of_ml_predictions:
    kwargs = {"ml_data_dict": \
              ml_predictions,
              "normalization_weights": \
              ml_model.core_attrs["normalization_weights"],
              "normalization_biases": \
              ml_model.core_attrs["normalization_biases"]}
    ml_predictions = func_alias(**kwargs)

See the documentation for the method emicroml.modelling.cbed.distortion.estimation.MLModel.forward() for details on the output returned by said method. See the documentation for the function emicroml.modelling.cbed.distortion.estimation.normalize_normalizable_elems_in_ml_data_dict() for a discussion on normalizing features of ML data instances, e.g. the standard coordinate transformation parameters.

Users can use the function emicroml.modelling.cbed.distortion.estimation.ml_data_dict_to_distortion_models() to convert ml_predictions to a sequence of distortion models, with each distortion model being represented by the class distoptica.DistortionModel.

modules()

Return an iterator over all modules in the network.

Return type:

Iterator[Module]

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)

mtia(device=None)

Move all model parameters and buffers to the MTIA.

This also makes associated parameters and buffers different objects. So it should be called before constructing the optimizer if the module will live on MTIA while being optimized. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Arguments:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

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.

Return type:

Iterator[tuple[str, Tensor]]

Args:

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

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.

Return type:

Iterator[tuple[str, Module]]

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)

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.

Args:

memo: a memo to store the set of modules already added to the result prefix: a prefix that will be added to the name of the module remove_duplicate: 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.

Return type:

Iterator[tuple[str, Parameter]]

Args:

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

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.

Return type:

Iterator[Parameter]

Args:

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

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_distortion_models(cbed_pattern_images, sampling_grid_dims_in_pixels=(512, 512), least_squares_alg_params=None)

Predict distortion models according to a mini-batch of images.

The machine learning (ML) model takes as input a mini-batch of images, where each image is assumed to depict a distorted CBED pattern, and as output, the ML model predicts a set of distortion models that describe the distortions of the input images. The distortion model used to describe the distortion of an image is defined in the documentation for the class distoptica.DistortionModel. See the documentation for the class distoptica.DistortionModel for a discussion on distortion models.

For each CBED pattern image, an instance distortion_model of the class distoptica.DistortionModel is constructed according to the distortions predicted by the ML model.

Parameters:

cbed_pattern_imagesarray_like (float, ndim=3)

The mini-batch of images. Let mini_batch_size be cbed_pattern_images.shape[0], and core_attrs be the instance attribute emicroml.modelling.cbed.distortion.estimation.MLModel.core_attrs. For each nonnegative integer n less than mini_batch_size, cbed_pattern_images[n] stores the n th input image of the mini-batch. mini_batch_size must be positive and cbed_pattern_images.shape[1:] must be equal to 2*(num_pixels_across_each_cbed_pattern,), where num_pixels_across_each_cbed_pattern is core_attrs["num_pixels_across_each_cbed_pattern"], i.e. the number of pixels across each input image.

sampling_grid_dims_in_pixelsarray_like (int, shape=(2,)), optional

The dimensions of the sampling grid, in units of pixels, used for all distortion models.

least_squares_alg_paramsdistoptica.LeastSquaresAlgParams | None, optional

least_squares_alg_params specifies the parameters of the least-squares algorithm to be used to calculate the mappings of fractional Cartesian coordinates of distorted images to those of the corresponding undistorted images. least_squares_alg_params is used to calculate the distortion models mentioned above in the summary documentation. If least_squares_alg_params is set to None, then the parameter will be reassigned to the value distoptica.LeastSquaresAlgParams(). See the documentation for the class distoptica.LeastSquaresAlgParams for details on the parameters of the least-squares algorithm.

Returns:

distortion_modelsarray_like (distoptica.DistortionModel, ndim=1)

The distortion models. Note that each distortion model is stored on the same device as that on which the ML model is stored.

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.

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)

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.

Return type:

None

Args:

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.

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

Return type:

RemovableHandle

Args:

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.Module. Otherwise, the provided hook will be fired after all existing forward hooks on this torch.nn.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:

torch.utils.hooks.RemovableHandle:

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

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

Return type:

RemovableHandle

Args:

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.Module. Otherwise, the provided hook will be fired after all existing forward_pre hooks on this torch.nn.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:

torch.utils.hooks.RemovableHandle:

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

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. :rtype: RemovableHandle

Warning

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

Args:

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.Module. Otherwise, the provided hook will be fired after all existing backward hooks on this torch.nn.Module. Note that global backward hooks registered with register_module_full_backward_hook() will fire before all hooks registered by this method.

Returns:

torch.utils.hooks.RemovableHandle:

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

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. :rtype: RemovableHandle

Warning

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

Args:

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.Module. Otherwise, the provided hook will be fired after all existing backward_pre hooks on this torch.nn.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:

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)

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:

torch.utils.hooks.RemovableHandle:

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

register_load_state_dict_pre_hook(hook)

Register a pre-hook to be run before module’s load_state_dict() is called.

It should have the following signature::

hook(module, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_keys, error_msgs) -> None # noqa: B950

Arguments:

hook (Callable): Callable hook that will be invoked before

loading the state dict.

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.

Return type:

None

Args:

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.

register_state_dict_post_hook(hook)

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

It should have the following signature::

hook(module, state_dict, prefix, local_metadata) -> None

The registered hooks can modify the state_dict inplace.

register_state_dict_pre_hook(hook)

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

It should have the following signature::

hook(module, prefix, keep_vars) -> None

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 disabling gradient computation for a comparison between .requires_grad_() and several similar mechanisms that may be confused with it.

Return type:

TypeVar(T, bound= Module)

Args:

requires_grad (bool): whether autograd should record operations on

parameters in this module. Default: True.

Returns:

Module: self

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.

Return type:

None

Args:

state (dict): Extra state from the state_dict

set_submodule(target, module, strict=False)

Set the submodule given by target if it exists, otherwise throw an error. :rtype: None

Note

If strict is set to False (default), the method will replace an existing submodule or create a new submodule if the parent module exists. If strict is set to True, the method will only attempt to replace an existing submodule and throw an error if the submodule does not exist.

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

A(
    (net_b): Module(
        (net_c): Module(
            (conv): Conv2d(3, 3, 3)
        )
        (linear): Linear(3, 3)
    )
)

(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 override the Conv2d with a new submodule Linear, you could call set_submodule("net_b.net_c.conv", nn.Linear(1, 1)) where strict could be True or False

To add a new submodule Conv2d to the existing net_b module, you would call set_submodule("net_b.conv", nn.Conv2d(1, 1, 1)).

In the above if you set strict=True and call set_submodule("net_b.conv", nn.Conv2d(1, 1, 1), strict=True), an AttributeError will be raised because net_b does not have a submodule named conv.

Args:

target: The fully-qualified string name of the submodule

to look for. (See above example for how to specify a fully-qualified string.)

module: The module to set the submodule to. strict: If False, the method will replace an existing submodule

or create a new submodule if the parent module exists. If True, the method will only attempt to replace an existing submodule and throw an error if the submodule doesn’t already exist.

Raises:

ValueError: If the target string is empty or if module is not an instance of nn.Module. AttributeError: If at any point along the path resulting from

the target string the (sub)path resolves to a non-existent attribute name or an object that is not an instance of nn.Module.

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.

Args:

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)

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.

Args:

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, recurse=True)

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

Return type:

TypeVar(T, bound= Module)

Args:

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:

Module: self

train(mode=True)

Set the module in training mode.

This has an effect only on certain modules. See the documentation of particular modules for details of their behaviors in training/evaluation mode, i.e., whether they are affected, e.g. Dropout, BatchNorm, etc.

Return type:

TypeVar(T, bound= Module)

Args:

mode (bool): whether to set training mode (True) or evaluation

mode (False). Default: True.

Returns:

Module: self

type(dst_type)

Casts all parameters and buffers to dst_type. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Args:

dst_type (type or string): the desired type

Returns:

Module: self

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. :rtype: TypeVar(T, bound= Module)

Note

This method modifies the module in-place.

Arguments:

device (int, optional): if specified, all parameters will be

copied to that device

Returns:

Module: self

zero_grad(set_to_none=True)

Reset gradients of all model parameters.

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

Return type:

None

Args:

set_to_none (bool): instead of setting to zero, set the grads to None.

See torch.optim.Optimizer.zero_grad() for details.