captum
captum copied to clipboard
pytorch
Model interpretability and understanding for PyTorch
This PR applies the same doc improvements for Sphinx from the other PRs, to the remaining files.
I noticed that some of the tests were missing the `-> None:` type hint. This PR adds the missing type hint.
* Added the CLIP ResNet 50x4 model used in the 'Multimodal Neurons in Artificial Neural Networks' research paper: https://distill.pub/2021/multimodal-neurons/ * To make it easier to conduct research, the CLIP ResNet...
## 🚀 Feature to use capture in code it is required to get result in format of an image ## Motivation we wanna deploy captain in service but for that...
Hello I am wondering what are the negative or positive attributes says about my model. Are positive attributes are preferred over negative ones? Thanks
* Wrap all remaining `torch.__version__` calls in `version.parse`. * Remove unused version check in `typing.py`. * Expose `MaxPool2dRelaxed` to users so that tutorials using it work. * Expose `dataset` module...
This is one of the better implementations I have come up with. Let me know your thoughts. Closes https://github.com/pytorch/captum/issues/792.
This PR does the following: * Ensures loss testing coverage is as high as possible. * Simplified loss composition code with new `rmodule_op` function. * Removed the NumPy import from...
* Improved the `LaplacianImage` code as part of removing the ToDo comment. * Added `"same"` padding option to `GaussianSmoothing`. * Improved the `NaturalImage` docs. * Also removed the built-in clamp...
## ❓ Questions and Help We have a set of listed resources available on the website and FAQ: https://captum.ai/ and https://captum.ai/docs/faq . Feel free to open an issue here on...
