Base layer class providing common functionality and properties for neural network layers.
This class acts as a Python wrapper for the C++ backend, exposing layer attributes
and methods for managing layer information, device placement, and parameters.
Initializes the BaseLayer with a C++ backend instance.
-
to_cuda()[source]
Moves the layer’s parameters and computations to the CUDA device.
-
get_layer_info() → str[source]
Retrieves detailed information about the layer.
- Returns:
A string containing the layer’s information.
- Return type:
str
-
get_layer_name() → str[source]
Retrieves the name of the layer.
- Returns:
The name of the layer.
- Return type:
str
-
get_max_num_states() → int[source]
Retrieves the maximum number of states the layer can hold.
- Returns:
The maximum number of states.
- Return type:
int
-
property input_size: int[source]
Gets the input size of the layer.
-
property output_size: int[source]
Gets the output size of the layer.
-
property in_width: int[source]
Gets the input width of the layer (for convolutional layers).
-
property in_height: int[source]
Gets the input height of the layer (for convolutional layers).
-
property in_channels: int[source]
Gets the input channels of the layer (for convolutional layers).
-
property out_width: int[source]
Gets the output width of the layer (for convolutional layers).
-
property out_height: int[source]
Gets the output height of the layer (for convolutional layers).
-
property out_channels: int[source]
Gets the output channels of the layer (for convolutional layers).
-
property bias: bool[source]
Gets a boolean indicating whether the layer has a bias term.
-
property num_weights: int[source]
Gets the total number of weights in the layer.
-
property num_biases: int[source]
Gets the total number of biases in the layer.
-
property mu_w: numpy.ndarray[source]
Gets the mean of the weights (mu_w) as a NumPy array.
-
property var_w: numpy.ndarray[source]
Gets the variance of the weights (var_w) as a NumPy array.
-
property mu_b: numpy.ndarray[source]
Gets the mean of the biases (mu_b) as a NumPy array.
-
property var_b: numpy.ndarray[source]
Gets the variance of the biases (var_b) as a NumPy array.
-
property delta_mu_w: numpy.ndarray[source]
Gets the delta mean of the weights (delta_mu_w) as a NumPy array.
-
property delta_var_w: numpy.ndarray[source]
Gets the delta variance of the weights (delta_var_w) as a NumPy array.
The delta corresponds to the amount of change induced by the update step.
-
property delta_mu_b: numpy.ndarray[source]
Gets the delta mean of the biases (delta_mu_b) as a NumPy array.
This delta corresponds to the amount of change induced by the update step.
-
property delta_var_b: numpy.ndarray[source]
Gets the delta variance of the biases (delta_var_b) as a NumPy array.
This delta corresponds to the amount of change induced by the update step.
-
property num_threads: int[source]
Gets the number of threads to use for computations.
-
property training: bool[source]
Gets a boolean indicating whether the layer is in training mode.
-
property device: bool[source]
Gets a boolean indicating whether the layer is on the GPU (‘cuda’) or CPU (‘cpu’).
