Autoencoders

Collection of Autoencoder models

skip_exec: true
skip_showdoc: true

AutoEncoder

 AutoEncoder (encoder:nimrod.modules.Encoder,
              decoder:nimrod.modules.Decoder)

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().__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 :meth:to, etc.

.. note:: As per the example above, an __init__() call to the parent class must be made before assignment on the child.

ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool
	Type	Details
encoder	Encoder	Encoder layer
decoder	Decoder	Decoder layer

enc = Encoder()
dec = Decoder()
a = AutoEncoder(enc, dec)
batch = torch.rand((10, 28*28))
y = a(batch)
print(y.shape)

torch.Size([10, 784])

ds = MNISTDataset(data_dir='../data/image/')
dl = DataLoader(ds)
b = next(iter(dl))
print(len(b), b[0].shape, b[1].shape)

2 torch.Size([1, 1, 28, 28]) torch.Size([1])

source

AutoEncoderPL

 AutoEncoderPL (autoencoder:__main__.AutoEncoder)

Hooks to be used in LightningModule.

autoencoder_pl = AutoEncoderPL(a)
b = torch.rand((5,28*28))
y = autoencoder_pl(b)
print(y.shape)

torch.Size([5, 784])