aiops/ContraLSP/switchstate/ab_count.py [39:110]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
):
    # If deterministic, seed everything
    if deterministic:
        seed_everything(seed=seed, workers=True)

    # Get accelerator and device
    accelerator = device.split(":")[0]
    print(accelerator)
    device_id = 1
    if len(device.split(":")) > 1:
        device_id = [int(device.split(":")[1])]

    # Create lock
    lock = mp.Lock()

    # Load data
    switch = Switch(n_folds=5, fold=fold, seed=seed)

    # Create classifier
    classifier = SpikeClassifierNet(
        feature_size=3,
        n_state=2,
        hidden_size=200,
        regres=True,
        loss="cross_entropy",
        lr=0.0001,
        l2=1e-3,
    )

    # Train classifier
    trainer = Trainer(
        max_epochs=50,
        accelerator=accelerator,
        devices=device_id,
        deterministic=deterministic,
        logger=TensorBoardLogger(
            save_dir=".",
            version=random.getrandbits(128),
        ),
    )
    if is_train:
        trainer.fit(classifier, datamodule=switch)
        if not os.path.exists("./model/"):
            os.makedirs("./model/")
        th.save(classifier.state_dict(), "./model/classifier_{}_{}".format(fold, seed))
    else:
        classifier.load_state_dict(th.load("./model/classifier_{}_{}".format(fold, seed)))

    # Get data for explainers
    with lock:
        x_train = switch.preprocess(split="train")["x"].to(device)
        x_test = switch.preprocess(split="test")["x"].to(device)
        y_test = switch.preprocess(split="test")["y"].to(device)
        true_saliency = switch.true_saliency(split="test").to(device)

    print("==============The sum of true_saliency is", true_saliency.sum(), "==============\n" + 70 * "=")

    # # Switch to eval
    classifier.eval()
    classifier.zero_grad()

    # Set model to device
    classifier.to(device)

    # Disable cudnn if using cuda accelerator.
    # Please see https://captum.ai/docs/faq#how-can-i-resolve-cudnn-rnn-backward-error-for-rnn-or-lstm-network
    # for more information.
    if accelerator == "cuda":
        th.backends.cudnn.enabled = False

    # Create dict of attributions
    attr = dict()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



aiops/ContraLSP/switchstate/main.py [53:124]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
):
    # If deterministic, seed everything
    if deterministic:
        seed_everything(seed=seed, workers=True)

    # Get accelerator and device
    accelerator = device.split(":")[0]
    print(accelerator)
    device_id = 1
    if len(device.split(":")) > 1:
        device_id = [int(device.split(":")[1])]

    # Create lock
    lock = mp.Lock()

    # Load data
    switch = Switch(n_folds=5, fold=fold, seed=seed)

    # Create classifier
    classifier = SpikeClassifierNet(
        feature_size=3,
        n_state=2,
        hidden_size=200,
        regres=True,
        loss="cross_entropy",
        lr=0.0001,
        l2=1e-3,
    )

    # Train classifier
    trainer = Trainer(
        max_epochs=50,
        accelerator=accelerator,
        devices=device_id,
        deterministic=deterministic,
        logger=TensorBoardLogger(
            save_dir=".",
            version=random.getrandbits(128),
        ),
    )
    if is_train:
        trainer.fit(classifier, datamodule=switch)
        if not os.path.exists("./model/"):
            os.makedirs("./model/")
        th.save(classifier.state_dict(), "./model/classifier_{}_{}".format(fold, seed))
    else:
        classifier.load_state_dict(th.load("./model/classifier_{}_{}".format(fold, seed)))

    # Get data for explainers
    with lock:
        x_train = switch.preprocess(split="train")["x"].to(device)
        x_test = switch.preprocess(split="test")["x"].to(device)
        y_test = switch.preprocess(split="test")["y"].to(device)
        true_saliency = switch.true_saliency(split="test").to(device)

    print("==============The sum of true_saliency is", true_saliency.sum(), "==============\n" + 70 * "=")

    # # Switch to eval
    classifier.eval()
    classifier.zero_grad()

    # Set model to device
    classifier.to(device)

    # Disable cudnn if using cuda accelerator.
    # Please see https://captum.ai/docs/faq#how-can-i-resolve-cudnn-rnn-backward-error-for-rnn-or-lstm-network
    # for more information.
    if accelerator == "cuda":
        th.backends.cudnn.enabled = False

    # Create dict of attributions
    attr = dict()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -