V5

Model definition not used in any publication

class doc_octopy.models.definitions.raul_net.offline.v5.RaulNetV5(learning_rate, cnn_layer_sizes, mlp_layer_sizes, nr_of_kernels_for_extraction, nr_of_outputs)

Model definition not used in any publication

Parameters:

• learning_rate (float)

• cnn_layer_sizes (Sequence[int])

• mlp_layer_sizes (Sequence[int])

• nr_of_kernels_for_extraction (int)

• nr_of_outputs (int)

example_input_array

Used for creating a summery and checking if the model architecture is valid.

Type:

torch.Tensor

learning_rate

The learning rate.

Type:

float

forward(inputs)

Same as torch.nn.Module.forward.

Parameters:

• *args – Whatever you decide to pass into the forward method.

• **kwargs – Keyword arguments are also possible.

Returns:

Your model’s output

Return type:

Tensor

class doc_octopy.models.definitions.raul_net.offline.v5.Transpose(dim0, dim1)

Circular padding layer

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Parameters:

• dim0 (int)

• dim1 (int)

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

Return type:

Tensor