yamle.models.convnet module

class yamle.models.convnet.ConvNetModel(conv_hidden_dims, linear_hidden_dims, normalization, activation='relu', *args, **kwargs)

Bases: BaseModel

This class is used to create a convolutional model similar to LeNet.

It combines convolutional layers, followed each time by pooling layers, ended with fully connected layers.

The first input layer is a Convolution, followed by normalization and ReLU, otherwise we used the Conv2dNormActivation classes and LinearNormActivation classes. The output is only a linear layer, followed by the OutputActivation class.

Parameters:

• inputs_dim (Tuple[int, int, int]) – The input dimensions.

• conv_hidden_dims (List[int]) – The dimensions of the convolutional hidden layers.

• linear_hidden_dims (List[int]) – The dimensions of the linear hidden layers.

• outputs_dim (int) – The dimension of the output.

• normalization (Optional[str]) – The normalization to use. Either ‘batch’, ‘layer’, ‘instance’ or None.

• activation (Optional[str]) – The activation to use. Either ‘relu’, ‘sigmoid’, ‘tanh’ or None.

• task (str) – The task to perform. Either ‘classification’ or ‘regression’. The task determined is softmax is used for the output layer.

tasks = ['classification', 'regression']

forward(x, staged_output=False, input_kwargs={}, output_kwargs={})

This method is used to perform a forward pass through the model.

The input is expected to be of shape (batch_size, inputs_dim). The output is of shape (batch_size, outputs_dim).

Parameters:

• x (torch.Tensor) – The input to the model.

• staged_output (bool) – If True, the output is a tuple of the last layer and the hidden layers.

• input_kwargs (Dict[str, Any]) – The kwargs for the input layer.

• output_kwargs (Dict[str, Any]) – The kwargs for the output layer.

Return type:

Union[Tensor, Tuple[Tensor, List[Tensor]]]

final_layer(x, **output_kwargs)

This function is used to get the final layer output.

Return type:

Tensor

add_method_specific_layers(method, **kwargs)

This method is used to add method specific layers to the model.

Parameters:

method (str) – The method to use.

Return type:

None

static add_specific_args(parent_parser)

This method is used to add the model specific arguments to the parent parser.

Return type:

ArgumentParser

training: bool

class yamle.models.convnet.ResidualConvNetModel(inputs_dim, outputs_dim, task, conv_hidden_dims=[32, 128], linear_hidden_dims=[128, 128], normalization='batch')

Bases: ConvNetModel

This class is used to create a residual convolutional network.

training: bool