kiwi.systems.decoders.linear

Module Contents

Classes

LinearDecoder

Base class for all neural network modules.

class kiwi.systems.decoders.linear.LinearDecoder(inputs_dims, config)

Bases: kiwi.systems._meta_module.MetaModule

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.

hidden_size :int = 250

Size of hidden layer

dropout :confloat(ge=0.0, le=1.0) = 0.0

bottleneck_size :int = 100

size(self, field=None)

forward(self, features: Dict[str, torch.Tensor], batch_inputs: MultiFieldBatch)

kiwi.systems.decoders.estimator kiwi.systems.decoders.nuqe