aiops/ContraLSP/hmm/ab_both.py [76:131]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    print("==============The sum of true_saliency is", true_saliency.sum(), "==============\n" + 70 * "=")
    # if not os.path.exists("./results/"):
    #     os.makedirs("./results/")
    # np.save('./results/true.npy', true_saliency.detach().numpy())

    # 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()

    if "gate_mask" in explainers:
        trainer = Trainer(
            max_epochs=500,
            accelerator=accelerator,
            devices=device_id,
            log_every_n_steps=2,
            deterministic=deterministic,
            logger=TensorBoardLogger(
                save_dir=".",
                version=random.getrandbits(128),
            ),
        )
        mask = GateMaskNet(
            forward_func=classifier,
            model=nn.Sequential(
                RNN(
                    input_size=x_test.shape[-1],
                    rnn="gru",
                    hidden_size=x_test.shape[-1],
                    bidirectional=True,
                ),
                MLP([2 * x_test.shape[-1], x_test.shape[-1]]),
            ),
            lambda_1=lambda_1,
            lambda_2=lambda_2,
            optim="adam",
            lr=0.01,
        )
        explainer = GateMask(classifier)
        _attr = explainer.attribute(
            x_test,
            additional_forward_args=(True,),
            trainer=trainer,
            mask_net=mask,
            batch_size=x_test.shape[0],
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



aiops/ContraLSP/switchstate/ab_both.py [94:146]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    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()

    if "gate_mask" in explainers:
        trainer = Trainer(
            max_epochs=500,
            accelerator=accelerator,
            devices=device_id,
            log_every_n_steps=2,
            deterministic=deterministic,
            logger=TensorBoardLogger(
                save_dir=".",
                version=random.getrandbits(128),
            ),
        )
        mask = GateMaskNet(
            forward_func=classifier,
            model=nn.Sequential(
                RNN(
                    input_size=x_test.shape[-1],
                    rnn="gru",
                    hidden_size=x_test.shape[-1],
                    bidirectional=True,
                ),
                MLP([2 * x_test.shape[-1], x_test.shape[-1]]),
            ),
            lambda_1=lambda_1,
            lambda_2=lambda_2,
            optim="adam",
            lr=0.01,
        )
        explainer = GateMask(classifier)
        _attr = explainer.attribute(
            x_test,
            additional_forward_args=(True,),
            trainer=trainer,
            mask_net=mask,
            batch_size=x_test.shape[0],
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -