Evolvable ResNet

An evolvable version of the ResNet architecture for image observation spaces.

Parameters

class agilerl.modules.resnet.EvolvableResNet(*args, **kwargs)

Evolvable module that implements the architecture presented in ‘Deep Residual Learning for Image Recognition’. Designed to train CNN’s more successfully by introducing residual connections that skip one or more layers.

Paper: https://arxiv.org/abs/1512.03385

Parameters:

  • input_shape (List[int]) – Input shape of the neural network

  • num_outputs (int) – Output layer dimension

  • channel_size (int) – A list of integers representing the number of channels in each convolutional layer

  • kernel_size (int) – A list of integers representing the kernel size of each convolutional layer

  • stride_size (int) – A list of integers representing the stride size of each convolutional layer

  • num_blocks (int) – Number of residual blocks that compose the network

  • output_activation (str, optional) – Output activation layer, defaults to None

  • scale_factor (int) – Scale factor for the network, defaults to 4

  • min_blocks (int) – Minimum number of residual blocks that compose the network, defaults to 1

  • max_blocks (int) – Maximum number of residual blocks that compose the network, defaults to 4

  • min_channel_size (int) – Minimum number of channels in each convolutional layer, defaults to 32

  • max_channel_size (int) – Maximum number of channels in each convolutional layer, defaults to 256

  • device (str, optional) – Device for accelerated computing, ‘cpu’ or ‘cuda’, defaults to ‘cpu’

  • name (str, optional) – Name of the network, defaults to ‘resnet’

add_block() → None

Adds a hidden layer to neural network. Falls back on add_channel() if max hidden layers reached.

add_channel(numb_new_channels: int | None = None) → Dict[str, int]

Remove channel from hidden layer of convolutional neural network.

Parameters:

numb_new_channels (int, optional) – Number of channels to add to hidden layer, defaults to None

Returns:

Dictionary containing the hidden layer and number of new channels

Return type:

Dict[str, Union[int, None]]

change_activation(activation: str, output: bool = False) → None

We currently do not support changing the activation function of the ResNet.

Parameters:

  • activation (str) – Activation function to use.

  • output (bool, optional) – Flag indicating whether to set the output activation function, defaults to False

create_resnet(input_shape: List[int], channel_size: int, kernel_size: int, stride_size: int, num_blocks: int, scale_factor: int) → Sequential

Creates and returns a convolutional neural network.

Parameters:

  • in_channels (int) – The number of input channels.

  • channel_size (List[int]) – A list of integers representing the number of channels in each convolutional layer.

  • kernel_size (List[int]) – A list of integers representing the kernel size of each convolutional layer.

  • stride_size (List[int]) – A list of integers representing the stride size of each convolutional layer.

  • num_blocks (int) – The number of residual blocks in the CNN.

  • scale_factor (int) – The scale factor for the CNN.

Returns:

The created convolutional neural network.

Return type:

nn.Sequential

forward(x: ndarray | Dict[str, ndarray] | Tuple[_SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes], ...] | Tensor | Dict[str, Tensor] | Tuple[Tensor, ...]) → Tensor

Returns output of neural network.

Parameters:

x (torch.Tensor) – Neural network input

Returns:

Neural network output

Return type:

torch.Tensor

property net_config: Dict[str, Any]

Returns model configuration in dictionary.

recreate_network(shrink_params: bool = False) → None

Recreates neural networks.

Parameters:

shrink_params (bool, optional) – Flag indicating whether to shrink the parameters, defaults to False

remove_block() → None

Removes a hidden layer from neural network. Falls back on add_channel() if min hidden layers reached.

remove_channel(numb_new_channels: int | None = None) → Dict[str, int]

Remove channel from hidden layer of convolutional neural network.

Parameters:

numb_new_channels (int, optional) – Number of channels to add to hidden layer, defaults to None

Returns:

Dictionary containing the hidden layer and number of new channels

Return type:

Dict[str, Union[int, None]]