Auto Visual Inference with Computer Vision Models

[Up] [Top]

Documentation for package ‘autovi’ version 0.4.0

Help Pages

AUTO_VI AUTO_VI class environment
auto_vi AUTO_VI class environment
AUTO_VI$..init.. Initialization method
AUTO_VI$..str.. String representation of the object
AUTO_VI$auxiliary Compute auxiliary variables for the keras model
AUTO_VI$boot_vss Predict visual signal strength for bootstrapped residual plots
AUTO_VI$check Conduct a auto visual inference check with a computer vision model
AUTO_VI$check_result List of diagnostic results
AUTO_VI$feature_pca Conduct principal component analysis for features extracted from keras model
AUTO_VI$feature_pca_plot Draw a summary Plot for principal component analysis conducted on extracted features
AUTO_VI$get_data Get data out of a model object
AUTO_VI$get_fitted_and_resid Get fitted values and residuals out of a model object
AUTO_VI$likelihood_ratio Compute the likelihood ratio using the simulated result
AUTO_VI$lineup_check Conduct a auto visual inference lineup check with a computer vision model
AUTO_VI$null_method Get null residuals from a fitted model
AUTO_VI$null_vss Simulate null plots and predict the visual signal strength
AUTO_VI$plot_resid Draw a standard residual plot
AUTO_VI$p_value Compute the p-value based on the check result
AUTO_VI$rotate_resid Get rotated residuals from a fitted linear model
AUTO_VI$select_feature Select features from the check result
AUTO_VI$summary_density_plot Draw a summary density plot for the result
AUTO_VI$summary_plot Draw a summary plot for the result
AUTO_VI$summary_rank_plot Draw a summary rank plot for the result
AUTO_VI$vss Predict the visual signal strength
check_python_library_available Check python library availability
get_keras_model Download and load the keras model
KERAS_WRAPPER KERAS_WRAPPER class environment
keras_wrapper KERAS_WRAPPER class environment
KERAS_WRAPPER$..init.. Initialization method
KERAS_WRAPPER$..str.. String representation of the object
KERAS_WRAPPER$get_input_height Get keras model input image height
KERAS_WRAPPER$get_input_width Get keras model input image width
KERAS_WRAPPER$image_to_array Load an image as numpy array
KERAS_WRAPPER$list_layer_name List all layer names
KERAS_WRAPPER$predict Predict visual signal strength
list_keras_model List all available pre-trained computer vision models
remove_plot Remove a plot
save_plot Save a plot