package caisar

  1. Overview
  2. Docs
A platform for characterizing the safety and robustness of artificial intelligence based software

Install 

dune-project
 Dependency

git.frama-c.com Readme Changelog Edit opam file Versions (7)

Authors

  1. L
    LAISER team, Software Safety and Security Laboratory, CEA-List

Maintainers

  1. L
    LAISER team, Software Safety and Security Laboratory, CEA-List

Sources

caisar-1.0.tbz
sha256=cd24b647565aaa4bb82d46c195c692d56ba0ad4b39bc86ef6baaf2d7a08c92a5
sha512=073761d95d6d8f6eb6f687643054297eb47db5d5bdc3a72ba42bf1509ab76415d485f536e5e42c11bd59c972ab7ad72e398d19af6e74c4f0778f28ef5bf4935e

doc/caisar.nnet/Nnet/index.html

Module NnetSource

Sourcetype t = private {
  1. n_layers : int;
    (*

    Number of layers.

    *)
  2. n_inputs : int;
    (*

    Number of inputs.

    *)
  3. n_outputs : int;
    (*

    Number of outputs.

    *)
  4. max_layer_size : int;
    (*

    Maximum layer size.

    *)
  5. layer_sizes : int list;
    (*

    Size of each layer.

    *)
  6. min_input_values : float list option;
    (*

    Minimum values of inputs.

    *)
  7. max_input_values : float list option;
    (*

    Maximum values of inputs.

    *)
  8. mean_values : (float list * float) option;
    (*

    Mean values of inputs and one value for all outputs.

    *)
  9. range_values : (float list * float) option;
    (*

    Range values of inputs and one value for all outputs.

    *)
  10. weights_biases : float list list;
    (*

    All weights and biases of NNet model.

    *)
}

NNet model metadata.

Sourceval parse : ?permissive:bool -> string -> (t, string) Result.t

Parse an NNet file.

  • parameter permissive

    false by default. When set, parsing does not fail on non available information, which are set to None instead.