MaskGIT

MaskGIT (Masked Generative Image Transformer) is a bidirectional masked transformer for discrete latent generation.

Key Features:

Bidirectional attention (parallel decoding)
Confidence-based masked prediction
Halton scheduler for spatially-dispersed unmasking
KLASS early stopping based on KL divergence
Token critic for quality-guided generation

Architecture

        graph LR
    A[Input: Masked Tokens] --> B[Token Embedding]
    B --> C[Positional Encoding]
    C --> D[Transformer Layers]
    D --> D1[Self-Attention Bidirectional]
    D --> D2[Feed-Forward Network]
    D --> D3[LayerNorm]
    D --> E[Output Layer]
    E --> F[Predictions for Unmasked]

    D1 --> style D1 fill:#ff9999
    D2 --> style D2 fill:#99ff99
    D3 --> style D3 fill:#9999ff

Basic Usage

Training

from medlatents import MaskGIT
from medlatents.configs import MODEL_CONFIGS
import torch

config = MODEL_CONFIGS["nano"]
model = MaskGIT(
    seq_length=256,
    vocab_size=512,
    hidden_size=config["hidden_size"],
    depth=config["depth"],
    num_heads=config["num_heads"],
    gradient_checkpointing=True,
)

# Training uses masked language modeling
# (See tutorials/01_training.ipynb)

Generation

from medlatents.sampling import MaskGITScheduler

# Initialize scheduler
scheduler = MaskGITScheduler(num_steps=12, mask_schedule='cosine')

# Start from fully masked input
tokens = torch.full((1, 256), model.mask_token, dtype=torch.long)
mask = torch.ones_like(tokens, dtype=torch.bool)

# Iterative unmasking
for step in range(scheduler.num_steps):
    logits = model(tokens)

    tokens, mask = scheduler.step(logits, tokens, mask, step)

print(f"Generated tokens: {tokens.shape}")

Advanced Features

Halton Scheduler (Spatially-Dispersed Unmasking)

Low-discrepancy sequence for better spatial locality:

from medlatents.sampling.maskgit import halton_schedule_1d

# Use Halton sequence for spatially-dispersed unmasking
scheduler = MaskGITScheduler(
    num_steps=16,
    mask_schedule="halton",  # Low-discrepancy spatial dispersion
)

KLASS Early Stopping

Adaptive stopping based on KL divergence:

from medlatents.sampling.maskgit import KLASSGenerator

klass = KLASSGenerator(
    scheduler=scheduler,
    kl_threshold=0.01,  # Stop when KL falls below threshold
    min_steps=8,          # Minimum steps before early stopping
)

generated, metrics = klass.generate(model, initial_tokens=tokens, mask_token=model.mask_token)
print(f"Steps taken: {metrics['steps_taken']}")

Token Critic

Quality-guided generation with binary critic:

from medlatents.sampling.maskgit import TokenCritic, CriticGuidedGenerator

critic = TokenCritic(vocab_size=512, hidden_dim=256)
guided_gen = CriticGuidedGenerator(
    model=model,
    critic=critic,
    num_refinement=2,
)

generated = guided_gen.generate(
    batch_size=4,
    num_steps=12,
    use_best_of_n=True,  # Best-of-N sampling
)

Masking Strategies

Confidence-Based Masking

Unmask lowest-confidence tokens first:

from medlatents.sampling.maskgit import adaptive_masking

# Compute token confidences
confidences = torch.softmax(logits, dim=-1)

# Mask lowest-confidence tokens
tokens_to_mask = adaptive_masking(
    confidences=confidences,
    num_to_mask=64,
)

Random Masking

Random uniform masking:

scheduler = MaskGITScheduler(
    num_steps=12,
    mask_schedule='cosine',
)

Curriculum Masking

Gradually reduce mask ratio during training:

from medlatents.training import MaskingSchedule

# Curriculum: 90% -> 50% -> 10% mask over training
masking_schedule = MaskingSchedule(
    start_ratio=0.9,
    end_ratio=0.1,
    total_epochs=100,
)

API Reference

Classes

class medlatents.MaskGIT(seq_length=1024, vocab_size=1024, hidden_size=384, depth=12, num_heads=6, mlp_ratio=4.0, mask_ratio=0.15, rope_theta=10000.0, allow_dynamic_seq_length=True, chunk_size=None, gradient_checkpointing=True, special_tokens=None, add_special_tokens=True)[source][source]

Bases: medlatents.networks.transformer.DiscreteTransformer

Bidirectional transformer with RoPE and masked training (MaskGIT).

Parameters:

seq_length (int, default: 1024)
vocab_size (int, default: 1024)
hidden_size (int, default: 384)
depth (int, default: 12)
num_heads (int, default: 6)
mlp_ratio (float, default: 4.0)
mask_ratio (float, default: 0.15)
rope_theta (float, default: 10000.0)
allow_dynamic_seq_length (bool, default: True)
chunk_size (int | None, default: None)
gradient_checkpointing (bool, default: True)
special_tokens (SpecialTokenIds | None, default: None)
add_special_tokens (bool, default: True)

__init__(seq_length=1024, vocab_size=1024, hidden_size=384, depth=12, num_heads=6, mlp_ratio=4.0, mask_ratio=0.15, rope_theta=10000.0, allow_dynamic_seq_length=True, chunk_size=None, gradient_checkpointing=True, special_tokens=None, add_special_tokens=True)[source][source]

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

Parameters:

seq_length (int, default: 1024)
vocab_size (int, default: 1024)
hidden_size (int, default: 384)
depth (int, default: 12)
num_heads (int, default: 6)
mlp_ratio (float, default: 4.0)
mask_ratio (float, default: 0.15)
rope_theta (float, default: 10000.0)
allow_dynamic_seq_length (bool, default: True)
chunk_size (int | None, default: None)
gradient_checkpointing (bool, default: True)
special_tokens (SpecialTokenIds | None, default: None)
add_special_tokens (bool, default: True)

initialize_weights()[source][source]

random_masking(x, mask_ratio=None)[source][source]

Apply random masking to input tokens.

Parameters:

x (Int[Tensor, 'batch seq']) – Input token indices [batch_size, seq_len]
mask_ratio (float | None, default: None) – Fraction of tokens to mask (uses self.mask_ratio if None)

Returns:

Input with masked positions replaced with mask token mask: Boolean mask indicating which positions were masked

Return type:

x_masked

forward(x, mask=None, mask_ratio=None)[source][source]

Forward pass through the bidirectional transformer.

Parameters:

x (Int[Tensor, 'batch seq']) – Input token indices [batch_size, seq_len]
mask (Bool[Tensor, 'batch seq'] | None, default: None) – Optional pre-computed mask of positions to predict
mask_ratio (float | None, default: None) – Optional mask ratio for training (auto-masks if None during training)

Returns:

Output logits [batch_size, seq_len, vocab_size]

Return type:

logits

generate(x, num_steps=8, temperature=1.0, top_k=None, eos_token=None, critic=None, use_critic=False, critic_threshold=0.5, num_candidates=4, refinement_steps=0, generator=None)[source][source]

Iterative parallel generation following MaskGIT schedule.

Parameters:

x (Int[Tensor, 'batch seq']) – Initial sequence with mask tokens [batch_size, seq_len]
num_steps (int, default: 8) – Number of demasking iterations
temperature (float, default: 1.0) – Sampling temperature. Must be > 0.
top_k (int | None, default: None) – If set, only sample from top-k logits
eos_token (int | None, default: None) – End-of-sequence token
critic (Module | None, default: None) – Optional token critic model for quality-guided generation
use_critic (bool, default: False) – If True, use critic for rejection/refinement (requires critic)
critic_threshold (float, default: 0.5) – Score threshold for rejection sampling (0-1)
num_candidates (int, default: 4) – Number of candidates for best-of-N selection
refinement_steps (int, default: 0) – Number of iterative refinement passes
generator (Generator | None, default: None) – Optional torch.Generator for reproducible sampling

Returns:

Fully generated sequence [batch_size, seq_len]

Return type:

generated

Raises:

ValueError – If temperature <= 0, num_steps < 1, or critic config invalid.

Note

When use_critic=True and critic is provided, generation uses the CriticGuidedGenerator for quality-improved sampling. This requires a trained token critic model.

inpaint_anomalies(x, likelihood_threshold=0.005, temperature=1.0, top_k=None)[source][source]

Inpaint using bidirectional context by detecting and replacing anomalous tokens.

Parameters:

x (Int[Tensor, 'batch seq']) – Input sequence [batch_size, seq_len]
likelihood_threshold (float, default: 0.005) – Tokens with likelihood below this are considered anomalous
temperature (float, default: 1.0) – Sampling temperature for replacements
top_k (int | None, default: None) – If set, only sample from top-k logits

Returns:

Sequence with anomalies replaced [batch_size, seq_len]

Return type:

inpainted

T_destination = ~T_destination

add_module(name, module)[source]

Add a child module to the current module.

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

Parameters:

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

Return type:

None

apply(fn)[source]

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).

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

Example:

>>> @torch.no_grad()
>>> def init_weights(m):
>>>     print(m)
>>>     if type(m) is 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()[source]

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

buffers(recurse=True)[source]

Return an iterator over module buffers.

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

Example:

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

call_super_init: bool = False

children()[source]

Return an iterator over immediate children modules.

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

ckpt_wrapper(module)[source]: Wrapper for gradient checkpointing.

compile(*args, **kwargs)[source]

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.

Return type:: None

cpu()[source]

Move all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

cuda(device=None)[source]

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.

Note

This method modifies the module in-place.

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

detect_anomalies(x, likelihood_threshold=0.005, **forward_kwargs)[source]

Detect anomalies by finding low likelihood tokens.

Parameters:

x (Tensor) – Input sequence [batch_size, seq_len]
likelihood_threshold (float, default: 0.005) – Threshold for marking tokens as anomalous
**forward_kwargs – Additional arguments for forward pass

Returns:

Binary mask of detected anomalies [batch_size, seq_len]

Return type:

anomaly_mask

property device: torch.device: Return the device of model parameters.

double()[source]

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

dump_patches: bool = False

eval()[source]

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.

Returns:: self
Return type:: Module

extra_repr()[source]

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()[source]

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

get_buffer(target)[source]

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

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

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

get_extra_state()[source]

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.

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

get_parameter(target)[source]

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

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

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

get_submodule(target)[source]

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.

Parameters:: target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
Returns:: The submodule referenced by target
Return type:: torch.nn.Module
Raises:: AttributeError – If 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()[source]

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

ipu(device=None)[source]

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.

Note

This method modifies the module in-place.

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

load_state_dict(state_dict, strict=True, assign=False)[source]

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

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

Warning

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

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
strict (bool, optional) – whether to strictly enforce that the keys in state_dict match the keys returned by this module’s state_dict() function. Default: True
assign (bool, optional) – When 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 Parameter for which the value from the module is preserved. Default: False

Returns:

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

Return type:

NamedTuple with missing_keys and unexpected_keys fields

Note

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

modules(remove_duplicate=True)[source]

Return an iterator over all modules in the network.

Parameters:: remove_duplicate (bool, default: True) – whether to remove the duplicated module instances in the result or not.
Yields:: Module – a module in the network
Return type:: Iterator[Module]

Note

Duplicate modules are returned only once by default. 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)[source]

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.

Note

This method modifies the module in-place.

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

named_buffers(prefix='', recurse=True, remove_duplicate=True)[source]

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

Parameters:

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

Yields:

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

Return type:

Iterator[tuple[str, Tensor]]

Example:

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

named_children()[source]

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

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

Example:

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

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

named_modules(memo=None, prefix='', remove_duplicate=True)[source]

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

Parameters:

memo (set[Module] | None, default: None) – a memo to store the set of modules already added to the result
prefix (str, default: '') – a prefix that will be added to the name of the module
remove_duplicate (bool, default: True) – 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)[source]

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

Parameters:

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

Yields:

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

Return type:

Iterator[tuple[str, Parameter]]

Example:

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

parameters(recurse=True)[source]

Return an iterator over module parameters.

This is typically passed to an optimizer.

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

Example:

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

register_backward_hook(hook)[source]

Register a backward hook on the module.

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

Returns:: a handle that can be used to remove the added hook by calling handle.remove()
Return type:: torch.utils.hooks.RemovableHandle
Parameters:: hook (Callable[[Module, tuple[Tensor, ...] | Tensor, tuple[Tensor, ...] | Tensor], tuple[Tensor, ...] | Tensor | None])

register_buffer(name, tensor, persistent=True)[source]

Add a buffer to the module.

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

Buffers can be accessed as attributes using given names.

Parameters:

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

Return type:

None

Example:

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

register_forward_hook(hook, *, prepend=False, with_kwargs=False, always_call=False)[source]

Register a forward hook on the module.

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

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

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

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

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

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided hook will be fired before all existing forward hooks on this torch.nn.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:

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

Return type:

torch.utils.hooks.RemovableHandle

register_forward_pre_hook(hook, *, prepend=False, with_kwargs=False)[source]

Register a forward pre-hook on the module.

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

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

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

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

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

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing forward_pre hooks on this torch.nn.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:

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

Return type:

torch.utils.hooks.RemovableHandle

register_full_backward_hook(hook, prepend=False)[source]

Register a backward hook on the module.

The hook will be called every time the gradients with respect to a module are computed, and its firing rules are as follows:

Ordinarily, the hook fires when the gradients are computed with respect to the module inputs.

If none of the module inputs require gradients, the hook will fire when the gradients are computed with respect to module outputs.

If none of the module outputs require gradients, then the hooks will not fire.

The hook should have the following signature:

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

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

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

Warning

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

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward hooks on this torch.nn.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:

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

Return type:

torch.utils.hooks.RemovableHandle

register_full_backward_pre_hook(hook, prepend=False)[source]

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, ...], Tensor or None

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

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

Warning

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

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward_pre hooks on this torch.nn.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:

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

Return type:

torch.utils.hooks.RemovableHandle

register_load_state_dict_post_hook(hook)[source]

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

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

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

The given incompatible_keys can be modified inplace if needed.

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

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

register_load_state_dict_pre_hook(hook)[source]

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

Parameters:: hook (Callable) – Callable hook that will be invoked before loading the state dict.

register_module(name, module)[source]

Alias for add_module().

Parameters:

name (str)
module (Optional[Module])

Return type:

None

register_parameter(name, param)[source]

Add a parameter to the module.

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

Parameters:

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

Return type:

None

register_state_dict_post_hook(hook)[source]

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)[source]

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)[source]

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.

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

set_chunk_size(chunk_size)[source]

Set or disable sequence chunking.

Parameters:: chunk_size (int | None)

set_extra_state(state)[source]

Set extra state contained in the loaded state_dict.

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

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

set_submodule(target, module, strict=False)[source]

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

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.

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.)
module (Module) – The module to set the submodule to.
strict (bool, default: False) – 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.

Return type:

None

share_memory()[source]

See torch.Tensor.share_memory_().

Return type:: Self

state_dict(*args, destination=None, prefix='', keep_vars=False)[source]

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

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

Note

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

Warning

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

Warning

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

Parameters:

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

Returns:

a dictionary containing a whole state of the module

Return type:

dict

Example:

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

to(*args, **kwargs)[source]

Move and/or cast the parameters and buffers.

This can be called as

to(device=None, dtype=None, non_blocking=False)[source]

to(dtype, non_blocking=False)[source]

to(tensor, non_blocking=False)[source]

to(memory_format=torch.channels_last)[source]

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

See below for examples.

Note

This method modifies the module in-place.

Parameters:

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

Returns:

self

Return type:

Module

Examples:

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

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

to_empty(*, device, recurse=True)[source]

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

Parameters:

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

Returns:

self

Return type:

Module

train(mode=True)[source]

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.

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

type(dst_type)[source]

Casts all parameters and buffers to dst_type.

Note

This method modifies the module in-place.

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

update_rotary_cache(seq_length)[source]

Pre-compute and cache rotary embeddings for given sequence length.

Parameters:: seq_length (int)
Return type:: None

xpu(device=None)[source]

Move all model parameters and buffers to the XPU.

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

Note

This method modifies the module in-place.

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

zero_grad(set_to_none=True)[source]

Reset gradients of all model parameters.

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

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

training: bool

class medlatents.sampling.MaskGITScheduler(num_steps=None, mask_schedule=None, temp_schedule='cosine', start_temp=1.0, end_temp=0.7, confidence_weight=0.3, schedule_power=2.0, halton_base=2, max_unmask_per_step=0.25, num_iterations=None, schedule=None)[source][source]

Bases: object

Advanced scheduler for MaskGIT-style generation.

Combines: - Flexible masking schedules (cosine, linear, sqrt, power, halton) - Temperature annealing - Confidence-based adaptation

Parameters:

num_steps (int | None, default: None)
mask_schedule (str | None, default: None)
temp_schedule (str, default: 'cosine')
start_temp (float, default: 1.0)
end_temp (float, default: 0.7)
confidence_weight (float, default: 0.3)
schedule_power (float, default: 2.0)
halton_base (int, default: 2)
max_unmask_per_step (float | None, default: 0.25)
num_iterations (int | None, default: None)
schedule (str | None, default: None)

__init__(num_steps=None, mask_schedule=None, temp_schedule='cosine', start_temp=1.0, end_temp=0.7, confidence_weight=0.3, schedule_power=2.0, halton_base=2, max_unmask_per_step=0.25, num_iterations=None, schedule=None)[source][source]

Parameters:

num_steps (int | None, default: None)
mask_schedule (str | None, default: None)
temp_schedule (str, default: 'cosine')
start_temp (float, default: 1.0)
end_temp (float, default: 0.7)
confidence_weight (float, default: 0.3)
schedule_power (float, default: 2.0)
halton_base (int, default: 2)
max_unmask_per_step (float | None, default: 0.25)
num_iterations (int | None, default: None)
schedule (str | None, default: None)

property num_iterations: int

step(logits, tokens, mask, step, temperature=None)[source][source]

Perform one step of MaskGIT generation.

Uses a fixed K_MAX for topk to enable torch.compile(fullgraph=True). Final step uses a separate codepath that unmasks all remaining tokens without calling topk.

Parameters:

logits (Tensor) – [batch, seq_len, vocab_size] model output
tokens (Tensor) – [batch, seq_len] current token sequence
mask (Tensor) – [batch, seq_len] True for positions to update
step (int) – current step number
temperature (float | None, default: None) – optional override for temperature

Returns:

updated token sequence mask: updated mask (fewer positions still masked)

Return type:

tokens

get_mask_ratio(step)[source][source]

Get mask ratio for a given step.

CONTRACT: - mask_ratio is the fraction of tokens that should REMAIN masked - mask_ratio must decay from ~1.0 (step=0) to ~0.0 (step=T-1) - All schedules must return values in [0, 1] - progress is defined as step/(num_steps-1) so final step has progress=1.0

The unmask_ratio = 1 - mask_ratio represents the fraction of currently-masked tokens to unmask at this step.

Parameters:: step (int) – Current step (0-indexed, must be < num_steps)
Return type:: float
Returns:: mask_ratio in [0, 1], decaying from ~1 at step=0 to ~0 at step=T-1

get_temperature(step)[source][source]

Parameters:: step (int)
Return type:: float

get_mask(logits, current_tokens, mask_token, step)[source][source]

Parameters:

logits (Tensor)
current_tokens (Tensor)
mask_token (int)
step (int)

Return type:

Tensor

class medlatents.sampling.maskgit.KLASSGenerator(scheduler, kl_threshold=0.01, min_steps=3, max_steps=None, window_size=2)[source][source]

Bases: object

KL-Adaptive Stability Sampling (KLASS) for MaskGIT and masked diffusion.

Dynamically stops generation when predictions stabilize, rather than using a fixed number of steps. Can significantly speed up inference.

Reference: “KL-Guided Fast Inference in Masked Diffusion Models” (arXiv:2511.05664)

Parameters:

scheduler (MaskGITScheduler) – Base MaskGITScheduler for masking and temperature
kl_threshold (float, default: 0.01) – Stop when KL divergence falls below this threshold
min_steps (int, default: 3) – Minimum number of steps before early stopping
max_steps (int | None, default: None) – Maximum number of steps (hard limit)
window_size (int, default: 2) – Number of steps to average KL over

__init__(scheduler, kl_threshold=0.01, min_steps=3, max_steps=None, window_size=2)[source][source]

Parameters:

scheduler (MaskGITScheduler)
kl_threshold (float, default: 0.01)
min_steps (int, default: 3)
max_steps (int | None, default: None)
window_size (int, default: 2)

should_stop(step, kl_divergence)[source][source]

Determine if generation should stop based on KL divergence.

Uses tensor operations to avoid GPU->CPU sync in the hot sampling loop.

Parameters:

step (int) – Current step number
kl_divergence (Tensor) – KL divergence tensor (scalar)

Return type:

bool

Returns:

True if generation should stop, False otherwise

generate(model, initial_tokens, mask_token)[source][source]

Generate tokens with KL-guided early stopping.

Uses fixed-iteration loop (no Python breaks for compile-friendliness).

Parameters:

model (Module) – Model that takes (tokens, mask_ratio) and returns logits
initial_tokens (Tensor) – [batch, seq_len] initial tokens (typically all masked)
mask_token (int) – Mask token ID

Returns:

[batch, seq_len] generated tokens metrics: Dict with generation statistics

Return type:

tokens

class medlatents.sampling.maskgit.TokenCritic(hidden_size=512, num_heads=8, depth=6, vocab_size=1024, mlp_ratio=4.0, dropout=0.1)[source][source]

Bases: torch.nn.modules.module.Module

Binary classifier that predicts whether tokens are real or generated.

Used during MaskGIT generation to score candidate tokens and enable: 1. Rejection sampling: Reject low-confidence samples 2. Iterative refinement: Re-mask and regenerate poorly-scored tokens 3. Quality-guided selection: Pick best samples from multiple candidates

The critic shares architecture with the generator but has a binary output head.

Usage:

critic = TokenCritic(hidden_size=512, num_heads=8, depth=6, vocab_size=1024)

# During generation, score candidate tokens scores = critic(candidate_tokens) # [batch, seq_len, 1]

# Use scores to filter or refine low_quality_mask = scores.squeeze(-1) < threshold tokens[low_quality_mask] = mask_token # Re-mask for another pass

Parameters:

hidden_size (int, default: 512)
num_heads (int, default: 8)
depth (int, default: 6)
vocab_size (int, default: 1024)
mlp_ratio (float, default: 4.0)
dropout (float, default: 0.1)

__init__(hidden_size=512, num_heads=8, depth=6, vocab_size=1024, mlp_ratio=4.0, dropout=0.1)[source][source]

Initialize token critic.

Parameters:

hidden_size (int, default: 512) – Transformer hidden dimension
num_heads (int, default: 8) – Number of attention heads
depth (int, default: 6) – Number of transformer layers
vocab_size (int, default: 1024) – Vocabulary size for token embedding
mlp_ratio (float, default: 4.0) – MLP expansion ratio
dropout (float, default: 0.1) – Dropout rate

forward(tokens, return_hidden=False)[source][source]

Score tokens as real or generated.

Parameters:

tokens (Tensor) – Input tokens [batch, seq_len]
return_hidden (bool, default: False) – Also return hidden states

Returns:

Per-token scores [batch, seq_len, 1] (higher = more likely real) hidden: (optional) Hidden states [batch, seq_len, hidden_size]

Return type:

scores

compute_loss(real_tokens, fake_tokens, real_mask=None, fake_mask=None)[source][source]

Compute critic training loss.

Parameters:

real_tokens (Tensor) – Ground truth tokens [batch, seq_len]
fake_tokens (Tensor) – Generated tokens [batch, seq_len]
real_mask (Tensor | None, default: None) – Optional mask for real tokens (True = include in loss)
fake_mask (Tensor | None, default: None) – Optional mask for fake tokens

Return type:

dict[str, Tensor]

Returns:

Dict with ‘loss’, ‘real_acc’, ‘fake_acc’

T_destination = ~T_destination

add_module(name, module)[source]

Add a child module to the current module.

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

Parameters:

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

Return type:

None

apply(fn)[source]

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).

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

Example:

>>> @torch.no_grad()
>>> def init_weights(m):
>>>     print(m)
>>>     if type(m) is 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()[source]

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

buffers(recurse=True)[source]

Return an iterator over module buffers.

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

Example:

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

call_super_init: bool = False

children()[source]

Return an iterator over immediate children modules.

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

compile(*args, **kwargs)[source]

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.

Return type:: None

cpu()[source]

Move all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

cuda(device=None)[source]

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.

Note

This method modifies the module in-place.

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

double()[source]

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

dump_patches: bool = False

eval()[source]

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.

Returns:: self
Return type:: Module

extra_repr()[source]

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()[source]

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

get_buffer(target)[source]

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

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

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

get_extra_state()[source]

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.

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

get_parameter(target)[source]

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

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

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

get_submodule(target)[source]

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.

Parameters:: target (str) – The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.)
Returns:: The submodule referenced by target
Return type:: torch.nn.Module
Raises:: AttributeError – If 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()[source]

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

ipu(device=None)[source]

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.

Note

This method modifies the module in-place.

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

load_state_dict(state_dict, strict=True, assign=False)[source]

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

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

Warning

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

Parameters:

state_dict (dict) – a dict containing parameters and persistent buffers.
strict (bool, optional) – whether to strictly enforce that the keys in state_dict match the keys returned by this module’s state_dict() function. Default: True
assign (bool, optional) – When 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 Parameter for which the value from the module is preserved. Default: False

Returns:

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

Return type:

NamedTuple with missing_keys and unexpected_keys fields

Note

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

modules(remove_duplicate=True)[source]

Return an iterator over all modules in the network.

Parameters:: remove_duplicate (bool, default: True) – whether to remove the duplicated module instances in the result or not.
Yields:: Module – a module in the network
Return type:: Iterator[Module]

Note

Duplicate modules are returned only once by default. 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)[source]

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.

Note

This method modifies the module in-place.

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

named_buffers(prefix='', recurse=True, remove_duplicate=True)[source]

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

Parameters:

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

Yields:

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

Return type:

Iterator[tuple[str, Tensor]]

Example:

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

named_children()[source]

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

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

Example:

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

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

named_modules(memo=None, prefix='', remove_duplicate=True)[source]

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

Parameters:

memo (set[Module] | None, default: None) – a memo to store the set of modules already added to the result
prefix (str, default: '') – a prefix that will be added to the name of the module
remove_duplicate (bool, default: True) – 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)[source]

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

Parameters:

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

Yields:

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

Return type:

Iterator[tuple[str, Parameter]]

Example:

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

parameters(recurse=True)[source]

Return an iterator over module parameters.

This is typically passed to an optimizer.

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

Example:

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

register_backward_hook(hook)[source]

Register a backward hook on the module.

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

Returns:: a handle that can be used to remove the added hook by calling handle.remove()
Return type:: torch.utils.hooks.RemovableHandle
Parameters:: hook (Callable[[Module, tuple[Tensor, ...] | Tensor, tuple[Tensor, ...] | Tensor], tuple[Tensor, ...] | Tensor | None])

register_buffer(name, tensor, persistent=True)[source]

Add a buffer to the module.

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

Buffers can be accessed as attributes using given names.

Parameters:

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

Return type:

None

Example:

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

register_forward_hook(hook, *, prepend=False, with_kwargs=False, always_call=False)[source]

Register a forward hook on the module.

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

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

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

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

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

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If True, the provided hook will be fired before all existing forward hooks on this torch.nn.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:

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

Return type:

torch.utils.hooks.RemovableHandle

register_forward_pre_hook(hook, *, prepend=False, with_kwargs=False)[source]

Register a forward pre-hook on the module.

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

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

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

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

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

Parameters:

hook (Callable) – The user defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing forward_pre hooks on this torch.nn.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:

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

Return type:

torch.utils.hooks.RemovableHandle

register_full_backward_hook(hook, prepend=False)[source]

Register a backward hook on the module.

The hook will be called every time the gradients with respect to a module are computed, and its firing rules are as follows:

Ordinarily, the hook fires when the gradients are computed with respect to the module inputs.

If none of the module inputs require gradients, the hook will fire when the gradients are computed with respect to module outputs.

If none of the module outputs require gradients, then the hooks will not fire.

The hook should have the following signature:

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

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

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

Warning

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

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward hooks on this torch.nn.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:

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

Return type:

torch.utils.hooks.RemovableHandle

register_full_backward_pre_hook(hook, prepend=False)[source]

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, ...], Tensor or None

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

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

Warning

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

Parameters:

hook (Callable) – The user-defined hook to be registered.
prepend (bool) – If true, the provided hook will be fired before all existing backward_pre hooks on this torch.nn.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:

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

Return type:

torch.utils.hooks.RemovableHandle

register_load_state_dict_post_hook(hook)[source]

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

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

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

The given incompatible_keys can be modified inplace if needed.

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

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

register_load_state_dict_pre_hook(hook)[source]

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

Parameters:: hook (Callable) – Callable hook that will be invoked before loading the state dict.

register_module(name, module)[source]

Alias for add_module().

Parameters:

name (str)
module (Optional[Module])

Return type:

None

register_parameter(name, param)[source]

Add a parameter to the module.

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

Parameters:

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

Return type:

None

register_state_dict_post_hook(hook)[source]

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)[source]

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)[source]

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.

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

set_extra_state(state)[source]

Set extra state contained in the loaded state_dict.

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

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

set_submodule(target, module, strict=False)[source]

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

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.

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.)
module (Module) – The module to set the submodule to.
strict (bool, default: False) – 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.

Return type:

None

share_memory()[source]

See torch.Tensor.share_memory_().

Return type:: Self

state_dict(*args, destination=None, prefix='', keep_vars=False)[source]

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

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

Note

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

Warning

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

Warning

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

Parameters:

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

Returns:

a dictionary containing a whole state of the module

Return type:

dict

Example:

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

to(*args, **kwargs)[source]

Move and/or cast the parameters and buffers.

This can be called as

to(device=None, dtype=None, non_blocking=False)[source]

to(dtype, non_blocking=False)[source]

to(tensor, non_blocking=False)[source]

to(memory_format=torch.channels_last)[source]

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

See below for examples.

Note

This method modifies the module in-place.

Parameters:

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

Returns:

self

Return type:

Module

Examples:

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

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

to_empty(*, device, recurse=True)[source]

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

Parameters:

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

Returns:

self

Return type:

Module

train(mode=True)[source]

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.

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

type(dst_type)[source]

Casts all parameters and buffers to dst_type.

Note

This method modifies the module in-place.

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

xpu(device=None)[source]

Move all model parameters and buffers to the XPU.

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

Note

This method modifies the module in-place.

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

zero_grad(set_to_none=True)[source]

Reset gradients of all model parameters.

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

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

training: bool

Functions

medlatents.sampling.maskgit.halton_schedule_1d(step, total_steps, base=2)[source][source]

Halton-based masking schedule for 1D sequences.

Uses the Halton sequence to ensure spatially dispersed unmasking. This is particularly useful for spatial data (e.g., image patches arranged via space-filling curves) where structure should emerge coherently.

Reference: “Halton Scheduler for Masked Generative Image Transformer” (arXiv:2503.17076)

Parameters:

step (int) – current step
total_steps (int) – total number of steps
base (int, default: 2) – Halton sequence base (default: 2)

Returns:

fraction of tokens to keep masked

Return type:

mask_ratio

medlatents.sampling.maskgit.adaptive_masking(logits, current_tokens, mask_token, step, total_steps, base_schedule='cosine', confidence_weight=0.5, temperature=1.0, schedule_power=2.0, halton_base=2)[source][source]

Hybrid masking: combine fixed schedule with confidence-based adjustment.

Parameters:

logits (Tensor) – [batch, seq_len, vocab_size] model predictions
current_tokens (Tensor) – [batch, seq_len] current token assignments
mask_token (int) – index of mask token
step (int) – current iteration
total_steps (int) – total iterations
base_schedule (str, default: 'cosine') – base schedule type (‘cosine’, ‘linear’, ‘sqrt’, ‘power’, ‘halton’)
confidence_weight (float, default: 0.5) – weight for confidence-based adjustment (0-1)
temperature (float, default: 1.0) – temperature for confidence scoring
schedule_power (float, default: 2.0) – power for power schedule
halton_base (int, default: 2) – base for halton schedule

Returns:

[batch, seq_len] boolean mask

Return type:

mask

MaskGIT

Architecture

Basic Usage

Training

Generation

Advanced Features

Halton Scheduler (Spatially-Dispersed Unmasking)

KLASS Early Stopping

Token Critic

Masking Strategies

Confidence-Based Masking

Random Masking

Curriculum Masking

API Reference

Classes

Functions

See Also