kiwi.systems._meta_module

Module Contents

Classes

Serializable
MetaModule	Base class for all neural network modules.

kiwi.systems._meta_module.logger

class kiwi.systems._meta_module.Serializable

subclasses

classmethod register_subclass(cls, subclass)

classmethod retrieve_subclass(cls, subclass_name)

classmethod load(cls, path)

save(self, path)

abstract classmethod from_dict(cls, *args, **kwargs)

abstract classmethod to_dict(cls, include_state=True)

class kiwi.systems._meta_module.MetaModule(config: Config)

Bases: torch.nn.Module, kiwi.systems._meta_module.Serializable

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

class Config

Bases: kiwi.utils.io.BaseConfig

Base class for all pydantic configs. Used to configure base behaviour of configs.

classmethod from_dict(cls, module_dict, **kwargs)

to_dict(self, include_state=True)

kiwi.systems.outputs.translation_language_model kiwi.systems.bert