Enes Aygun
Reputation: 11
While working on binary image classification, the class mode set to binary incorrectly labels the images, but does it correct on categorical
I am currently working on a binary image classification. My problem is that when i use data augmentation, it incorrectly labels the images when it is set to binary.
The things i have tried:
Looked for incorrectly labeled classes on images before augmenting my data. Here is nothing wrong however.
Changed the class mode to categorical. This works, however i am not working on a multi-class classification.
Tried playing with the image data generator. Nothing worked.
Looked for classification imbalances. Also nothing wrong.
What could I try more? Should i just use categorical class mode on my generator?
Upvotes: 1
Views: 31
Answers (0)
Related Questions
- Resnet50 for binary classification predicts all the images to be of the same class
- Determining the splitting ratio when augmenting image data
- What should be the class mode for training a multilabel classification model?
- Data augmentation is not generated İmages
- Why does binary accuracy give high accuracy while categorical accuracy give low accuracy, in a multi-class classification problem?