captum
captum copied to clipboard
pytorch
Model interpretability and understanding for PyTorch
## ❓ Questions and Help Hey all, I'm trying to apply DeepLift on a custom VGG16, but getting an IndexError. Does somebody have an Idea how to fix it? ###...
## 🐛 Bug I am trying to use LRP on a GoogleNet with a modified fc layer. Using the original GoogleNet from the Pytorch models library fails too. ## To...
## 🐛 Bug My model takes in two inputs, tensors `query` and `article`, the lengths are different but the batch size is the same. Say, query.size() is [1, 137], article.size()...
## 🐛 Bug When running tests for the optim module code I've been working on, occasionally some of the tests in other modules fail, and it looks as though that...
## ❓ 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...
Hello, I followed the example in the tutorial to use integrated gradients for my model that takes in image as well as tabular features. img_path = "/media/images/576.jpeg" feats_valid_file = "/media/feats/valid_feats_std.npy"...
I noticed a gap in our tutorials for how users can use their own models with the optim module. Bits and pieces of this information can be found across different...
## 🚀 Feature Replace the register_full_backward_hook with a forward hook and get grad values from the tensors. ## Motivation First of all, thank you for the great package. Unfortunately, I...
Attached is the full logs, ``` C:\Users\user\PycharmProjects\yolor_my\yolor_env\Scripts\python.exe C:/Users/user/PycharmProjects/yolor_my/yolor/my_test.py To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor). Person 0.65 [tensor(0.21673, device='cuda:0', requires_grad=True),...
## ❓ Questions and Help Hello. I have developed a model with three inputs types. Image, categorical data and numerical data. For Image data I've used ResNet50 for the other...
