Training a sparse model is no different from training a normal model. The model will maintain sparsity internally. There is no need for any additional actions other than adjusting the hyper-parameters.
sparse_model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
sparse_model.fit(x_train, y_train, batch_size=128, epochs=15, validation_split=0.1)
sparse_model.save_weights("model_sparse_0.2", save_format="tf")
Note: When calling
save_weights
, use the "tf" format to save the weights.