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

[In-the-wild Faces Dataset] Removing alpha channel in load_image() #16

Open
wants to merge 3 commits into
base: master
Choose a base branch
from

Conversation

RooseveltAdvisors
Copy link

@RooseveltAdvisors RooseveltAdvisors commented Aug 25, 2017

Training failing on In-the-wild Faces dataset which you can find the download link in the Datasets section of this site (https://susanqq.github.io/UTKFace/)

The error message I saw was as follows:

could not broadcast input array from shape (128,128,3) into shape (128,128)

This error could potentially result from load_image returning a M * N * 4 matrix if there is a RGBA image in the batch.

Yuan Zhao added 2 commits August 25, 2017 13:59
Training failing on `In-the-wild Faces` dataset which you can find the download link in the Datasets section of this site (https://susanqq.github.io/UTKFace/)

The error message I saw was as follows:
```
could not broadcast input array from shape (128,128,3) into shape (128,128)
```

This error could potentially result from `load_image` returning a 128*128*4 matrix where the 4th is the alpha when there is a RGBA image in the batch.
@RooseveltAdvisors RooseveltAdvisors changed the title Remove alpha channel in load_image() [In-the-wild Faces Dataset] Remove alpha channel in load_image() Aug 25, 2017
@RooseveltAdvisors RooseveltAdvisors changed the title [In-the-wild Faces Dataset] Remove alpha channel in load_image() [In-the-wild Faces Dataset] Removing alpha channel in load_image() Aug 25, 2017
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

Successfully merging this pull request may close these issues.

1 participant