dataeval.utils.models.Encoder¶

class dataeval.utils.models.Encoder(input_shape, encoding_dim)¶

A simple encoder to be used in an autoencoder model.

It consists of a CNN followed by a fully connected layer.

Parameters:¶

input_shape : tuple[int, int, int]¶

Shape of the input data in CHW format.

encoding_dim : int¶

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

forward(x)¶

Perform a forward pass through the encoder.

Parameters:¶

x : torch.Tensor¶

Input tensor

Returns:¶

The encoded representation of the input tensor.

Return type:¶

torch.Tensor