Open ne1s0n opened 3 years ago
Can you try running the notebook from here?
https://walkwithfastai.com/EfficientNet_and_Custom_Weights
The notebooks are updated at https://github.com/walkwithfastai/walkwithfastai.github.io
Same result - you can see a screenshot here: https://ibb.co/Lg9PzWB I've actually found the error on walkwithfastai and then came here because you linked this repo in the fastai forum :)
Thanks for trying that for me! I’ll be able to look at that in a few days (it’s finals currently)
On Wed, May 5, 2021 at 3:53 AM Nelson Nazzicari @.***> wrote:
Same result - you can see a screenshot here: https://ibb.co/Lg9PzWB I've actually found the error on walkwithfastai and then came here because you linked this repo in the fastai forum :)
— You are receiving this because you commented.
Reply to this email directly, view it on GitHub https://github.com/muellerzr/Practical-Deep-Learning-for-Coders-2.0/issues/41#issuecomment-832526373, or unsubscribe https://github.com/notifications/unsubscribe-auth/AB3YCV7NITONV7CXRK63NGLTMEBQNANCNFSM44CXWODA .
With reference to file 05_EfficientNet_and_Custom_Weights.ipynb, once the learner is created, albeit not frozen, a call to
learn.summary()
generates
RuntimeError: running_mean should contain 3072 elements not 6144
instead of showing the proper summary. If ignored the later call to
learn.lr_find()
stops with the same error. I was running the code on Google Colab.