aiops/ContraLSP/hmm/main.py [245:335]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        attr["gate_mask"] = _attr.to(device)
        print_results(attr["gate_mask"], true_saliency)

    if "fit" in explainers:
        generator = JointFeatureGeneratorNet(rnn_hidden_size=6)
        trainer = Trainer(
            max_epochs=200,
            accelerator=accelerator,
            devices=device_id,
            log_every_n_steps=10,
            deterministic=deterministic,
            logger=TensorBoardLogger(
                save_dir=".",
                version=random.getrandbits(128),
            ),
        )
        explainer = Fit(
            classifier,
            generator=generator,
            features=x_test,
            trainer=trainer,
        )
        attr["fit"] = explainer.attribute(x_test, show_progress=True)

    if "gradient_shap" in explainers:
        explainer = TimeForwardTunnel(GradientShap(classifier.cpu()))
        attr["gradient_shap"] = explainer.attribute(
            x_test.cpu(),
            baselines=th.cat([x_test.cpu() * 0, x_test.cpu()]),
            n_samples=50,
            stdevs=0.0001,
            task="binary",
            show_progress=True,
        ).abs()
        classifier.to(device)

    if "integrated_gradients" in explainers:
        explainer = TimeForwardTunnel(IntegratedGradients(classifier))
        attr["integrated_gradients"] = explainer.attribute(
            x_test,
            baselines=x_test * 0,
            internal_batch_size=200,
            task="binary",
            show_progress=True,
        ).abs()

    if "lime" in explainers:
        explainer = TimeForwardTunnel(Lime(classifier))
        attr["lime"] = explainer.attribute(
            x_test,
            task="binary",
            show_progress=True,
        ).abs()

    if "augmented_occlusion" in explainers:
        explainer = TimeForwardTunnel(
            TemporalAugmentedOcclusion(
                classifier, data=x_train, n_sampling=10, is_temporal=True
            )
        )
        attr["augmented_occlusion"] = explainer.attribute(
            x_test,
            sliding_window_shapes=(1,),
            attributions_fn=abs,
            task="binary",
            show_progress=True,
        ).abs()

    if "occlusion" in explainers:
        explainer = TimeForwardTunnel(TemporalOcclusion(classifier))
        attr["occlusion"] = explainer.attribute(
            x_test,
            sliding_window_shapes=(1,),
            baselines=x_train.mean(0, keepdim=True),
            attributions_fn=abs,
            task="binary",
            show_progress=True,
        ).abs()

    if "retain" in explainers:
        retain = RetainNet(
            dim_emb=128,
            dropout_emb=0.4,
            dim_alpha=8,
            dim_beta=8,
            dropout_context=0.4,
            dim_output=2,
            loss="cross_entropy",
        )
        explainer = Retain(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



aiops/ContraLSP/switchstate/main.py [240:330]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        attr["gate_mask"] = _attr.to(device)
        print_results(attr["gate_mask"], true_saliency)

    if "fit" in explainers:
        generator = JointFeatureGeneratorNet(rnn_hidden_size=6)
        trainer = Trainer(
            max_epochs=200,
            accelerator=accelerator,
            devices=device_id,
            log_every_n_steps=10,
            deterministic=deterministic,
            logger=TensorBoardLogger(
                save_dir=".",
                version=random.getrandbits(128),
            ),
        )
        explainer = Fit(
            classifier,
            generator=generator,
            features=x_test,
            trainer=trainer,
        )
        attr["fit"] = explainer.attribute(x_test, show_progress=True)

    if "gradient_shap" in explainers:
        explainer = TimeForwardTunnel(GradientShap(classifier.cpu()))
        attr["gradient_shap"] = explainer.attribute(
            x_test.cpu(),
            baselines=th.cat([x_test.cpu() * 0, x_test.cpu()]),
            n_samples=50,
            stdevs=0.0001,
            task="binary",
            show_progress=True,
        ).abs()
        classifier.to(device)

    if "integrated_gradients" in explainers:
        explainer = TimeForwardTunnel(IntegratedGradients(classifier))
        attr["integrated_gradients"] = explainer.attribute(
            x_test,
            baselines=x_test * 0,
            internal_batch_size=200,
            task="binary",
            show_progress=True,
        ).abs()

    if "lime" in explainers:
        explainer = TimeForwardTunnel(Lime(classifier))
        attr["lime"] = explainer.attribute(
            x_test,
            task="binary",
            show_progress=True,
        ).abs()

    if "augmented_occlusion" in explainers:
        explainer = TimeForwardTunnel(
            TemporalAugmentedOcclusion(
                classifier, data=x_train, n_sampling=10, is_temporal=True
            )
        )
        attr["augmented_occlusion"] = explainer.attribute(
            x_test,
            sliding_window_shapes=(1,),
            attributions_fn=abs,
            task="binary",
            show_progress=True,
        ).abs()

    if "occlusion" in explainers:
        explainer = TimeForwardTunnel(TemporalOcclusion(classifier))
        attr["occlusion"] = explainer.attribute(
            x_test,
            sliding_window_shapes=(1,),
            baselines=x_train.mean(0, keepdim=True),
            attributions_fn=abs,
            task="binary",
            show_progress=True,
        ).abs()

    if "retain" in explainers:
        retain = RetainNet(
            dim_emb=128,
            dropout_emb=0.4,
            dim_alpha=8,
            dim_beta=8,
            dropout_context=0.4,
            dim_output=2,
            loss="cross_entropy",
        )
        explainer = Retain(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -