-
Notifications
You must be signed in to change notification settings - Fork 74
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
Not able to run dawn_mod.py #9
Comments
I get the same error. |
Yup looks like you need to set trn_sampler at the ModelData level now. Inside torch_loader function: |
I am getting the same error with fastai_imagenet.py. Should I open another issue? |
To me it seems as though extra arguments are passed to the stepper through **kwargs - arguments that it is not supposed to receive. |
I got the same error with fastai_imagenet.py too. Did anyone solve this problem yet? |
Use the fastai git checkout mentioned in the readme (e.g do a git reset --hard SHA1) and then the rest should work. |
@brettkoonce I did git reset --hard SHA1, but I got this error. fatal: ambiguous argument 'SHA1': unknown revision or path not in the working tree. I tried this command both in fastai/ git directory and imagenet-fast directory. Can you link the readme file you are referring to? |
Run Here is the README Brett mentioned. |
@nebfield Thanks! |
Hi Folks, thank you for doing this great work at fastai.
I am trying to reproduce the following
and I am getting this error:
Any ideas? Has the API for fastai changed? I used pip install for all the dependencies and fastai itself.
The text was updated successfully, but these errors were encountered: