Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add new CIFAR100 standard model #167

Open
harsmac opened this issue Jan 26, 2024 · 2 comments
Open

Add new CIFAR100 standard model #167

harsmac opened this issue Jan 26, 2024 · 2 comments

Comments

@harsmac
Copy link

harsmac commented Jan 26, 2024

Hi,
Thanks for creating this repository. I just had one request: Could we add the Standard model for CIFAR100? Like a WideResNet28-10, just like how it exists for CIFAR10?

The weights are available here: https://drive.google.com/file/d/12pATFGjsDN1Tq4p-S0-rO59sX-F_O2ol/view?usp=sharing
or : https://github.com/alexrame/mixmo-pytorch?tab=readme-ov-file

@fra31
Copy link
Member

fra31 commented Jan 27, 2024

Hi,

it should be possible to add it. However it might be problematic to take models from other repositories without at least asking the authors (unless you're one of them), e.g. because of licences. I'd say the easiest would be to train a new model with the model definition currently in the model zoo. If you already had such checkpoint, and its evaluation, it'd be great, and probably quick to add.

@linghunwhp
Copy link

When loading a model, it downloads from Google Drive, it downloads a .pt file but just contains html content of download verification page like the following screenshot. And then, it leads to some errors when loading the downloaded model. Do you know how to fix this problem?
By the way, did you provide models with the TensorFlow framework or do you have a method to transfer the Pytorch model to the Tensorflow model?

download_verification

Traceback (most recent call last):
File "D:\My_Project\ContextFuzz\AdvTrainedModelFuzzing.py", line 57, in
model = load_model(model_name='Carmon2019Unlabeled', model_dir=ae_trained_model_path, dataset='cifar10', threat_model='Linf')
File "C:\Users\haipewang5\Anaconda3\envs\tensorflow_11\lib\site-packages\robustbench\utils.py", line 147, in load_model
checkpoint = torch.load(model_path, map_location=torch.device('cpu'))
File "C:\Users\haipewang5\Anaconda3\envs\tensorflow_11\lib\site-packages\torch\serialization.py", line 1040, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "C:\Users\haipewang5\Anacond
a3\envs\tensorflow_11\lib\site-packages\torch\serialization.py", line 1258, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, '<'.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants