-
The current implementation of integrated gradients interpolates on the entire patch mask. However, this introduces dependencies between upstream nodes and downstream nodes. Let f_k(x) denote the outpu…
-
I am trying to calculate integrated gradients for a specific model and multiple inputs in a loop. Do we need to set the model parameter and input gradients to zero manually? What is the default gradie…
-
I would like to calculate feature importances using integrated gradients, as I am hoping this calculation will be faster than the SHAP KernelExplainer. Unfortunately, the embeddding layer is non-diffe…
-
## ❓ Questions and Help
Hello! I am trying to learn about about Captum and how to use it. I am trying to use some of the Captum model interpretation tools such as Integrated Gradients (and eventu…
-
Hi, I'm trying to use Integrated Gradients on a simple DQN model in my MacBook using the MPS backend.
`model = IntegratedGradients(model)`
`attribution = xai.attribute(torch.tensor(ob, dtype = to…
-
At the moment the [`IntegratedGradients`](https://github.com/SeldonIO/alibi/blob/782ad53504d347f92c0ceb1cfbf5d1c376ceb677/alibi/explainers/integrated_gradients.py#L305) class only supports tf.keras an…
-
Hi there,
I'm trying to get explanation for a classification model (TFCamembertForSequenceClassification fine-tuned on some data) using the IntegratedGradients explainer.
I'm following this grea…
-
-
感谢作者在可解释性方面做出的优秀工作。我目前在用llama-3.1-8b做一些研究，在给transformer_lens中添加了`meta-llama/Llama-3.1-8B-Instruct`的支持代码后，运行`knowledge_eap.ipynb`，发现在第6个单元格计算`attribute(model, g, data, partial(logit_diff, loss=True, me…
-
Hey, how can I compute IG for object detection models such as yolov5 wherein the model's output will usually be (class, bboxes, score), where as certain classification models give prediction probabili…