dataeval.utils.torch.models.Autoencoder¶

class dataeval.utils.torch.models.Autoencoder(channels=3)¶

An autoencoder model with a separate encoder and decoder.

Parameters:¶

channels : int, default 3¶

Number of input channels

encode(x)¶

Encode the input tensor using the encoder.

Parameters:¶

x : torch.Tensor¶

Input tensor

Returns:¶

The encoded representation of the input tensor.

Return type:¶

torch.Tensor

forward(x)¶

Perform a forward pass through the encoder and decoder.

Parameters:¶

x : torch.Tensor¶

Input tensor

Returns:¶

The reconstructed output tensor.

Return type:¶

torch.Tensor