

Image Classifer

class ImageClassifier

Class that represents the classifier for images.

The following pretrained CNNs from Keras can be used as base model:

base_model_name: Name of Keras base model.
n_classes: Number of classes.
learning_rate: Learning rate for training phase.
dropout_rate: Fraction set randomly.
loss: A loss function as one of two parameters to compile the model.
weights: Pretrained weights the model architecture is loaded with (default imagenet).

def __init__(base_model_name, n_classes, learning_rate, dropout_rate, loss, weights)

Inits ImageClassifier object.

Loads Keras base_module specified by base_model_name.

def get_base_layers()

Gets layers of classifiers' base model

def get_preprocess_input()

Gets preprocess_input of classifiers' base_module

def set_learning_rate(learning_rate)

sets classifiers' learning_rate

def build()

Builds classifiers' model.

The following steps will be performed in sequence:

def compile()

Configures classifiers' model for training.

def fit_generator(**kwargs)

Trains classifiers' model on data generated by a Python generator.

generator: Input samples from a data generator on which to train the model.
validation_data: Input samples from a data generator on which to evaluate the model.
epochs: Number of epochs to train the model.
initial_epoch: Epoch at which to start training.
verbose: Verbosity mode.
use_multiprocessing: Use process based threading.
workers: Maximum number of processes.
max_queue_size: Maximum size for the generator queue.
callbacks: List of callbacks to apply during training.

def predict_generator(data_generator, **kwargs)

Generates predictions for the input samples from a data generator.

def summary()

Summarizes classifiers' model.