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

doubt about featurizer tensor size #80

Open
pmnerfed opened this issue Feb 22, 2019 · 1 comment
Open

doubt about featurizer tensor size #80

pmnerfed opened this issue Feb 22, 2019 · 1 comment

Comments

@pmnerfed
Copy link

pmnerfed commented Feb 22, 2019

Hi,
According to the code, the tensor created is tensor[0][init_idx][attr_idx] = 1.0.
Can you please elaborate on why its not tensor[0][attr_idx][init_idx] = 1.0(axis 1 and 2 swapped).

file : repair/featurize/initattfeat.py@12
From what I understand,
if each row in the tensor should be for an attribute, it should be the axis=1 not 2.
The axis =2 should be for valid value for the attribute the row corresponds to.

Hope that makes sense.
If my thinking is wrong, could you please help me out here?
`

@fatangare
Copy link

I believe it is because all featurized tensors are concatenated in later stage. If you have diff dimensions for initattfeat feature , tensors can't be concatenated.

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

2 participants