-
Congratulations on your work and I am very interested in your paper. I am a novice and I would like to follow the tutorial to reproduce your tutorial. When working on task-specific student model disti…
-
### 🚀 The feature, motivation and pitch
I'm working on vectorizing gradient computations with torch.func for vision explainability. I was able to use `torch.func.grad` and `torch.func.vmap` to comp…
-
I have 606 protein sequences from uniprot. I tried running `TSignal` as follows and ran into the following issue @Dumitrescu-Alexandru
```
python main.py --test_seqs uniprot_all_true_forSignalPep…
-
Hi, there are so many errors while executing the baseline results.
For example I'm trying to run dynamask, In saliency_exp_synth.py there is a line "from txai.models.modelv6_v2 import Modelv6_v2"
…
-
I have successfully run your project and attempted to apply the imagePerturbationSaliency and imageSarfa methods provided by you to my own pre-trained DQN model. I've noticed that as the model's perfo…
-
I would like to understand why my model detected a certain object (mask) as having class A rather than class B. Is there a way to do it with MMDetection? If not, are there libraries that can process M…
-
Dear DeepFRI developers,
There seems to be an error in the saliency maps when the latest release and the downloadable models are used. For example in the case of 2PE5 in the Nat. Comms paper for the…
ga01 updated
3 months ago
-
Hello @annahedstroem,
It is possible that I am confusing something or calling the function incorrectly but if not, then I think there might be a mistake in how Sensitivity-n is calculated.
### Descr…
-
Hi! How did you calculate the corresponding salicency map for every input?
-
Hi, thanks for the great work!
When i set `results = saliency.get_image_saliency_results(model, img, input_tensor, prediction_tensor), methods=['gradcam', 'smooth_grad']` in [`cnn_pred_explain.ipyn…