DeepMTP package

Subpackages

Submodules

DeepMTP.branch_models module

class DeepMTP.branch_models.ConvNet(*args: Any, **kwargs: Any)

Bases: Sequential

A convolutional neural network that is based on resnet.

forward(v)
class DeepMTP.branch_models.MLP(*args: Any, **kwargs: Any)

Bases: Sequential

A standard fully connected feed-forward neural network.

forward(v)

DeepMTP.dataset module

DeepMTP.hpo_worker module

DeepMTP.main module

DeepMTP.main_streamlit module

DeepMTP.random_search_streamlit module

class DeepMTP.random_search_streamlit.RandomSearch(base_worker, configspace, budget=1, max_num_epochs=100, direction='min', verbose=False)

Bases: object

Implements the basic Random search HPO method. Nothing fancy, just a for loop over randomly generated configurations.

get_norm_val(val, min_val, max_val)
get_run_summary()
run_optimizer()

DeepMTP.simple_hyperband module

class DeepMTP.simple_hyperband.HyperBand(base_worker, configspace, eta=3, max_budget=1, direction='min', verbose=False)

Bases: object

Implements a basic version of the Hyperband HPO method. One cool thing about it is that I reduced the training time by continuing to train later configurations instead of starting from scratch each time.

calculate_hyperband_iters(R, eta, verbose=False)
get_run_summary()
run_optimizer()

DeepMTP.simple_hyperband_streamlit module

class DeepMTP.simple_hyperband_streamlit.HyperBand(base_worker, configspace, eta=3, max_budget=1, direction='min', verbose=False)

Bases: object

Implements a basic version of the Hyperband HPO method. One cool thing about it is that I reduced the training time by continuing to train later configurations instead of starting from scratch each time.

calculate_hyperband_iters(R, eta, verbose=False)
get_norm_val(val, min_val, max_val)
get_run_summary()
run_optimizer()

DeepMTP.tests module

Module contents