What is the expected output for the VGG(Attribute Prediction) model on the demo images

[ashwath98]

These are the results I'm getting for the three demo images
1.
print
lace
knit
sleeve
floral

lace
knit
print
sleeve
striped

print
lace
knit
sleeve
striped

Which seems wrong
what is the suggested fix?

This is the command I am running
!python demo/test_predictor.py --input demo/imgs/attr_pred_demo3.jpg --checkpoint checkpoints/latest.pth

latest.pth is the VGG backbone global pooling model
and I have used list_attr_clothing.txt file provided on the deepfashion site

[veralauee]

It is not fixed. 1, 2, 3 are different. It is possibly that "print" in the dataset are major attribute, so the pretrained model has some bias.

[ashwath98]

Okay. Thank you for the clarification 😊

[veralauee]

Will close the issue.