teddykoker / u-noise Goto Github PK

Hello! First of all great work. While running train_noise pretrained I ran into a problem where the keys in state_dict were wrong. For example, the keys should be something like "model.downs.0.0.weight", but its giving me an error saying my keys were "util_model.model.downs.0.0.weight". I am running this on Python 3.8, was this error due to a different Python version?

I've tried many times, but the web page reminds me of a network error, or the connection is always down

Dear Teddy Koker @teddykoker and co-authors,

I would like to kindly ask you to revise the citations and update the arxiv version of your paper.

1. [6] Vinogradova, K., Dibrov, A., & Myers, G. (2020). Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13943-13944. https://doi.org/10.1609/aaai.v34i10.7244

2. They either return explanations for a part of the image [6, 7] or for a single pixel [6] or for the whole class [6].
   In :
   "There are only a few previous works that focus on segmentation interpretability [6, 7]. These works solve the problem in
   a lower resolution setup, and then up-sample to get pixel level explanation. They also only return explanations with respect
   to a single pixel [ 6] or a part of the image [7]. "

3. "Finally, for Grad-CAM, we follow [ 6, 11 ] and obtain a heatmap with respect to the convolutional layer at the bottleneck of the Utility model."

Seg-Grad-CAM, the method proposed in my peer-reviewed publication, takes the gradients with respect to the convolutional layer at the bottleneck of the U-Net and produces explanations for a) single pixel, b) class mask (all pixels belonging to the class), c) ROI (e.g. an instance).

I would really appreciate it and cite your paper in my current work.

Kind regards,
Kira

Hi! Thank you for sharing your great work! When I was studying make_ visualizations. py, I met some problems.
You define activations_ hook on line 21 of the program, but line 22 self.gradients = grads is not really initialized. So I found 36 lines of self activations_ hook will not call the function of line 21, which leads to errors in subsequent programs.
Therefore, do you have a good way to solve this problem or can you provide the latest version of the code?
Thank you very much and look forward to your reply! Best regards!