Lucas Hervier comments

Results 8 comments of


                                            Lucas Hervier

typing: create custom type, protocol, etc.. that would fit better our classes

It is a good point, but then we have to make sure the type we use are necessary AND sufficient. Because, it is nice that a user can understand the...

[Feature Request] map_to_interpret_space function for Lime and Kernel Shap

You want to change the default `map_to_interpret_space` function for LIME & KernelSHAP for images inputs to watershed. But from my understanding this new function need to be parametrized for EACH...

Handle model that are aggregation of models

Sorry for the delay and I hope it is not too late but can you also provide a minimal code leading to this error ? It is to be able...

Handle model with tensor that has channel first

Hi Adrien! Would a wrapper such as the one used in this [example](https://deel-ai.github.io/xplique/callable.html) fix it ?

Handle model with tensor that has channel first

With the PR #132,we introduce a wrapper in [`pytorch.py`](https://github.com/deel-ai/xplique/blob/master/xplique/wrappers/pytorch.py) file. You can take inspiration of this wrapper to handle channel first models

Handle model that are aggregation of models

Since there is no more activity on this issue and no answers to @AntoninPoche's comment, I will mark this issue resolved. If anyone has the same issue, feel free to...

[Enhancement] - Add new attribution method

Hi! First, I apologize for the delay in our answer. We have read your paper and we would appreciate integrating it in Xplique. Unfortunately, our team is quite busy as...

RuntimeError during Gradient Computation with Custom YOLOv7 Model Wrapper in PyTorch for Xplique Object Detection Explainability

Hey there, I am gonna investigate it. Could you please provide your code to get: `processed_tf_inputs` and `man_bounding_box`? Also, you said that you use a custom Yolov7. But can you...