ConvertedModel {innsight}

Converted torch-based model

Description

This class stores all layers converted to torch in a module which can be used like the original model (but torch-based). In addition, it provides other functions that are useful for interpreting individual predictions or explaining the entire model. This model is part of the class Converter and is the core for all the necessary calculations in the methods provided in this package.

Usage

ConvertedModel(modules_list, graph, input_nodes, output_nodes, dtype = "float")

Arguments

modules_list

(list)
A list of all accepted layers created by the Converter class during initialization.

graph

(list)
The graph argument gives a way to pass an input through the model, which is especially relevant for non-sequential architectures. It can be seen as a list of steps in which order the layers from modules_list must be applied. The list contains the following elements:

• ⁠$current_nodes⁠
  This list describes the current position and the number of the respective intermediate values when passing through the model. For example, list(1,3,3) means that in this step one output from the first layer and two from the third layer (the numbers correspond to the list indices from the modules_list argument) are available for the calculation of the current layer with index used_node.

• ⁠$used_node⁠
  The index of the layer from the modules_list argument which will be applied in this step.

• ⁠$used_idx⁠
  The indices of the outputs from current_nodes, which are used as inputs of the current layer (used_node).

• ⁠$times⁠
  The frequency of the output value, i.e., is the output used more than once as an input for subsequent layers?
  

input_nodes

(numeric)
A vector of layer indices describing the input layers, i.e., they are used as the starting point for the calculations.

output_nodes

(numeric)
A vector of layer indices describing the indices of the output layers.

dtype

(character(1))
The data type for all the calculations and defined tensors. Use either 'float' for torch::torch_float or 'double' for torch::torch_double.

Method forward()

The forward method of the whole model, i.e., it calculates the output y=f(x) of a given input x. In doing so, all intermediate values are stored in the individual torch modules from modules_list.

Usage

self(x,
     channels_first = TRUE,
     save_input = FALSE,
     save_preactivation = FALSE,
     save_output = FAlSE,
     save_last_layer = FALSE)

Arguments

x

The input torch tensor for this model.

channels_first

If the input tensor x is given in the format 'channels first', use TRUE. Otherwise, if the channels are last, use FALSE and the input will be transformed into the format 'channels first'. Default: TRUE.

save_input

Logical value whether the inputs from each layer are to be saved or not. Default: FALSE.

save_preactivation

Logical value whether the preactivations from each layer are to be saved or not. Default: FALSE.

save_output

Logical value whether the outputs from each layer are to be saved or not. Default: FALSE.

save_last_layer

Logical value whether the inputs, preactivations and outputs from the last layer are to be saved or not. Default: FALSE.

Return

Returns a list of the output values of the model with respect to the given inputs.

Method update_ref()

This method updates the intermediate values in each module from the list modules_list for the reference input x_ref and returns the output from it in the same way as in the forward method.

Usage

self$update_ref(x_ref,
                channels_first = TRUE,
                save_input = FALSE,
                save_preactivation = FALSE,
                save_output = FAlSE,
                save_last_layer = FALSE)

Arguments

x_ref

Reference input of the model.

channels_first

If the tensor x_ref is given in the format 'channels first' use TRUE. Otherwise, if the channels are last, use FALSE and the input will be transformed into the format 'channels first'. Default: TRUE.

save_input

Logical value whether the inputs from each layer are to be saved or not. Default: FALSE.

save_preactivation

Logical value whether the preactivations from each layer are to be saved or not. Default: FALSE.

save_output

Logical value whether the outputs from each layer are to be saved or not. Default: FALSE.

save_last_layer

Logical value whether the inputs, preactivations and outputs from the last layer are to be saved or not. Default: FALSE.

Return

Returns a list of the output values of the model with respect to the given reference input.

Method set_dtype()

This method changes the data type for all the layers in modules_list. Use either 'float' for torch::torch_float or 'double' for torch::torch_double.

Usage

self$set_dtype(dtype)

Arguments

dtype

The data type for all the calculations and defined tensors.