You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Mar 17, 2022. It is now read-only.
Hello guido
The first I would like to know is that since fast.ai is built on the pytorch framework, can we convert a model built on fast.ai into keras using the pytorch_to_keras function which you've written?
The second thing is that I actually tried converting an image classification model built on fast.ai into keras. A new model file was also created named temp.h5(as mentioned in the function), which is a keras model file. But when I tested the newly obtained keras model on my test dataset, it gave exactly same score for each category for every image.
It would be really great of you if you could help me with this issue.
Thank you!
The text was updated successfully, but these errors were encountered:
Hello guido
The first I would like to know is that since fast.ai is built on the pytorch framework, can we convert a model built on fast.ai into keras using the pytorch_to_keras function which you've written?
The second thing is that I actually tried converting an image classification model built on fast.ai into keras. A new model file was also created named temp.h5(as mentioned in the function), which is a keras model file. But when I tested the newly obtained keras model on my test dataset, it gave exactly same score for each category for every image.
It would be really great of you if you could help me with this issue.
Thank you!
The text was updated successfully, but these errors were encountered: