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

AttributeError: 'TfmCrop' object has no attribute 'tfm' #2

Open
shirishr opened this issue Dec 25, 2018 · 3 comments
Open

AttributeError: 'TfmCrop' object has no attribute 'tfm' #2

shirishr opened this issue Dec 25, 2018 · 3 comments

Comments

@shirishr
Copy link

Is there a way to eliminate this error in cell 30?
Looks like some changes have occurred in fastai repo

@Vyas9296
Copy link

Yes I am having the same issue

@Vyas9296
Copy link

This error was preceded by this warning when I ran this cell:

We create a databunch with all the data in the training set and no validation set (DatasetFormatter uses only the training set)

db = (ImageItemList.from_folder(path)
.no_split()
.label_from_folder()
.transform([crop_pad, crop_pad], size=224)
.databunch())
You can deactivate this warning by passing no_check=True.

/opt/anaconda3/lib/python3.7/site-packages/fastai/basic_data.py:226: UserWarning: There seems to be something wrong with your dataset, can't access any element of self.train_ds.
Tried: 33187,40616,29090,2216,41860...
warn(warn_msg)

@nazmiasri95
Copy link

How about update it to latest fastai version and use this ? :

tfms = [crop_pad(), crop_pad()]
db = (ImageList.from_folder(path)
                   .no_split()
                   .label_from_folder()
                   .transform(tfms=tfms, size=224)
                   .databunch())

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