Tensorflow Custom
The tensorflow custom (tfcustom) module contains functions that process models created with the tensorflow package.
Table of Contents:
Feature Processing (tfcustom.fts)
Contains functions to extract features from a tensorflow neural network
- fns.tfcustom.fts.feature_extractor(model, lay, model_in, norm)
Function to extract the features from a given layer of a model
- Parameters
model (loaded keras model) –
lay (str) – name of a layer in model
model_in (varies) – correctly formatted model input
norm (str) – {‘ft01’, ‘all01’, ‘none’} a string to indicate which normalization methodology to use;
- Returns
ft_mat (np.ndarray[(any, any, any), float]) – an array of all features extracted from a given layer; the first two dimensions are the size of the feature; the last dimension is the number of features in a layer
See also
fns.mat.normalize_mat()for information about choices for norm
- fns.tfcustom.fts.parse_features(model, lay, features)
Function to make a list of the features to plot
Prints error message and exits program for features = [‘Grid’]
- Parameters
model (loaded keras model) –
lay (str) – name of a layer in model features (list[str]): list of features to plot, starting at feature 1
features (list[str]) –
- Returns
n_features (int) – how may features to plot
features (list[int]) – list of features to plot, starting at feature 0
Model Prints (tfcustom.prints)
Contains functions to print out lists of options for model-related input arguments
- fns.tfcustom.prints.print_layers(model)
Function that prints a list of layer names in a model
- Parameters
model (loaded keras model) –
- Returns
No Return Objects
- fns.tfcustom.prints.print_features(model, lay)
Function that prints how many features are extracted from a layer of a model
- Parameters
model (loaded keras model) –
lay (str) – name of layer to get features from
- Returns
No Return Objects
Model Checks (tfcustom.checks)
Contains functions to check that the model-related input arguments passed are valid
- fns.tfcustom.checks.check_layer(model, lay)
Function that checks if a layer name is in the model
- Parameters
model (loaded keras model) –
lay (str) – name of layer to test
- Returns
No Return Objects
- fns.tfcustom.checks.check_features(model, lay, features)
Function that checks if number of features requested are available from a layer
- Parameters
model (loaded keras model) –
lay (str) – name of layer where features will be extracted from
features (list[str]) – should be [‘Grid’], [‘All’], or a list of integers; features the script plans on extracting
- Returns
No Return Objects
Calico Functions (tfcustom.calico)
Contains functions to create a calico network and do prints/checks on the calcio network inputs
- fns.tfcustom.calico.check_calico_layer(model, lay, branch='None', catlay='None')
Function that checks if the layer is a valid selection for the split layer
- Parameters
model (loaded keras model) –
lay (str) – name of layer to test
branch (str) – key used to identify which layers are on the secondary branch; use ‘None’ if the model only has one branch
catlay (str) – name of layer where the branches of the model are concatenated use ‘None’ if the model only has one branch
- Returns
No Return Objects
- fns.tfcustom.calico.check_calico_features(model, lay, features)
Function that checks if number of features requested are available from a layer
- Parameters
model (loaded keras model) –
lay (str) – name of layer where features will be extracted from
features (str) – an integer; features the calico model scales
- Returns
No Return Objects
- fns.tfcustom.calico.layer_copy(cnnlayer, tag)
Function to create a copy of a keras layer object
Based on the layer type and configuration
Does NOT copy trained layer weights
- Parameters
cnnlayer (keras.layers) – layer to make a copy of
tag (str) – string “tag” to be appended to the name of the copied layer
- Returns
cnnlayer2 (keras.layer) – copy of cnnlayer with same type and configuration