dataeval.utils.models.Decoder¶

class dataeval.utils.models.Decoder(input_shape, encoding_dim, encoding_shape)¶

A simple decoder to be used in an autoencoder model.

Parameters:¶

input_shape : tuple[int, ...]¶

Shape of the original input data in CHW format.

encoding_dim : int¶

The size of the 1D array that emerges from the fully connected layer.

encoding_shape : tuple[int, ...]¶

Shape of the encoded input data.

forward(x)¶

Perform a forward pass through the decoder.

Parameters:¶

x : torch.Tensor¶

The encoded tensor.

Returns:¶

The reconstructed output tensor.

Return type:¶

torch.Tensor