modules package

modules.graph_functions module

modules.helper_ML_functions module

modules.helper_ML_functions.evaluate_model(model: torch.nn.Module, shots: int) → dict

Store the bits strings from the model in a dictionary

Parameters:

• model (torch.nn.Module)

• shots (int)

Return type:

dict

modules.helper_ML_functions.find_device() → torch.device

Find out if we are using a GPU or CPU

Return type:

torch.device

modules.helper_ML_functions.get_ready_to_train(sdl, model: torch.nn.Module) → tuple

Prepare for training by setting up the target, criterion, and optimizer

Parameters:

model (torch.nn.Module)

Return type:

tuple

modules.helper_ML_functions.set_up_input_hot_start(sdl, device: torch.device, bin_hot_start_list: list, print_results: bool = False) → torch.Tensor

If ML and Hot Start set the initial input to the hot start data

Parameters:

• device (torch.device)

• bin_hot_start_list (list)

• print_results (bool)

Return type:

torch.Tensor

modules.helper_ML_functions.set_up_input_no_hot_start(sdl, device: torch.device) → torch.Tensor

If ML and no Hot Start set the initial input to zero OR 0.5, depending on the mode

Parameters:

device (torch.device)

Return type:

torch.Tensor

modules.helper_ML_functions.train_model(num_epochs: int, model: torch.nn.Module, my_input: torch.Tensor, target: torch.Tensor, criterion: torch.nn.Module, optimizer: torch.optim.Optimizer, print_results: bool = False, print_frequency: int = 10) → tuple

Train the model for a number of epochs

Parameters:

• num_epochs (int)

• model (torch.nn.Module)

• my_input (torch.Tensor)

• target (torch.Tensor)

• criterion (torch.nn.Module)

• optimizer (torch.optim.Optimizer)

• print_results (bool)

• print_frequency (int)

Return type:

tuple

modules.helper_functions_tsp module

modules.test_ML_functions module

modules.test_quantum_function module

modules.test_tsp_helper module

Module contents

modules.helper_results module