A layer config is an object returned from get_config() that contains the
configuration of a layer or model. The same layer or model can be
reinstantiated later (without its trained weights) from this configuration
using from_config(). The config does not include connectivity information,
nor the class name (those are handled externally).
get_config(object)from_config(config)
Layer or model object
Object with layer or model configuration
get_config() returns an object with the configuration,
from_config() returns a re-instantation of hte object.
Other model functions: compile,
evaluate_generator, evaluate,
fit_generator, fit,
get_layer,
keras_model_sequential,
keras_model, pop_layer,
predict.keras.engine.training.Model,
predict_generator,
predict_on_batch,
predict_proba,
summary.keras.engine.training.Model,
train_on_batch
Other layer methods: count_params,
get_input_at, get_weights,
reset_states