Skip to content

issues Search Results · repo:hendrycks/natural-adv-examples language:Python

Filter by

14 results
 (70 ms)

14 results

inhendrycks/natural-adv-examples (press backspace or delete to remove)

hendrycks/natural-adv-examples
How to interpret file names?

Thank you for the dataset. What are the values in a file name? For example, in this one, 0.000116_digital clock _ digital clock_0.865662, the last value seems to be the probability, what is the first value? ...
  • fugokidi
  • Opened 
    on Apr 11, 2023
  • #14

hendrycks/natural-adv-examples
Used model

Hello, thanks for the interesting work. Which resnet50 models did you use? Specifically, was the ResNet50_Weights.IMAGENET1K_V2 of pytorch https://pytorch.org/vision/main/models/generated/torchvision.models.resnet50.html ...
  • ThomasNorr
  • Opened 
    on Dec 19, 2022
  • #13

hendrycks/natural-adv-examples
Mismatch between the ImageNet-A classes reported in the paper and in the download?

Hi, thanks for providing this dataset! I downloaded ImageNet-A following the link in the README of this repository and had a look at the provided README to see which classes are available. I noticed that ...
  • expectopatronum
  • 1
  • Opened 
    on Feb 11, 2022
  • #12

hendrycks/natural-adv-examples
I just get the acc of 0.9% in your dataset when I use PVT. It's too lower that I can't believe,

I just use the code of https://www.kaggle.com/paultimothymooney/starter-kernel-for-imagenet-a-adversarial-examples and load the model in the follow waynet = pvt_medium() checkpoint = torch.load( ../input/pvt-medium/4f268100-d9ba-11eb-8129-547eacb8081d ...
  • 1104662797
  • 1
  • Opened 
    on Dec 4, 2021
  • #11

hendrycks/natural-adv-examples
Understand AUPR95 in our paper

Hello @hendrycks , In your code, you are using the model s confidence scores on two the same imagenet-o datasets. Can you explain why you do this? How do you compute the AUPR95 by two lists of confidence ...
  • giangnguyen2412
  • 4
  • Opened 
    on Oct 4, 2021
  • #10

hendrycks/natural-adv-examples
ResNet50 get 0% (not ~2% as reported in the paper)

Hey, Thanks for your such great work. I am trying to run the eval.py to and use ResNet50 pretrained to get your result in Figure 2. However, I am getting 0% accuracy for ResNet50. Can you give me your ...
  • giangnguyen2412
  • 7
  • Opened 
    on Sep 10, 2021
  • #9

hendrycks/natural-adv-examples
What structure in the file PATH_TO_IMAGENET_VAL = "./imagenet1k/val/"?

Is this folder like the structure as follows (from your code it should be like this): -n00001 emsp;-XXX.JPEG emsp;-XXX.JPEG -n00002 emsp;-XXX.JPEG emsp;-XXX.JPEG But my standard imagenet1k val dataset, ...
  • double-fire-0
  • 1
  • Opened 
    on Jul 13, 2021
  • #8

hendrycks/natural-adv-examples
Question about testing pretrained custom model.

Hi. Hendrycks. Can you provide instructions to actually test custom pretrained models?
  • wjun0830
  • Opened 
    on Jul 5, 2021
  • #7

hendrycks/natural-adv-examples
Is fine-tuning needed when evaluating on ImageNet-O?

Hi, Thanks for making the two benchmarks public. I was wondering that when evaluating OOD detection performance on ImageNet-O, did you fine-tune the model on the 200 selected classes, or just took the ...
  • zjysteven
  • 1
  • Opened 
    on Jun 3, 2021
  • #6

hendrycks/natural-adv-examples
`stable_cumsum` needs to be imported

stable_cumsum https://github.com/hendrycks/natural-adv-examples/blob/07770705658c3a1c8acce31fd9dbd68f06e297c3/calibration_tools.py#L144 needs to be imported.
  • sayakpaul
  • 2
  • Opened 
    on Mar 24, 2021
  • #5
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub