Wrong predictions

[markkdev]

Hi,

I followed the process of setup, downloaded checkpoints for vgg16.pth, latest.pth for global attr.

Anytime I run the demo I get the same output no matter the image.

[ Top3 Prediction ]
print
lace
knit
[ Top5 Prediction ]
print
lace
knit
sleeve
maxi
[ Top10 Prediction ]
print
lace
knit
sleeve
maxi
shirt
denim
chiffon
floral
striped

Looking for a guide on what I could be doing wrong?

Appreciate it and thanks for you work.

[markkdev]

I also get this error anytime I run attr predict with roi

python3 ./demo/test_predictor.py --input demo/attr_pred_demo1.jpg
Traceback (most recent call last):
File "./demo/test_predictor.py", line 57, in
main()
File "./demo/test_predictor.py", line 51, in main
attr_prob = model(img_tensor, attr=None, landmark=None, return_loss=False)
File "/root/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 539, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/mmfashion-0.1.0+aea9b23-py3.6.egg/mmfashion/models/predictor/base.py", line 41, in forward
return self.forward_test(img, landmark)
File "/usr/local/lib/python3.6/dist-packages/mmfashion-0.1.0+aea9b23-py3.6.egg/mmfashion/models/predictor/base.py", line 29, in forward_test
return self.simple_test(img[0], landmark[0])
TypeError: 'NoneType' object is not subscriptable

[xu1718191411]

For my experience,I remove the mmfashion package by pip uninstall mmfashion
and indicate the path of mmfashion by adding the following code at test_predictor.py

import sys
sys.path.append("/home/Source/mmfashion")

[markkdev]

still fails at

mmfashion/models/predictor/base.py", line 29, in forward_test
return self.simple_test(img[0], landmark[0])
TypeError: 'NoneType' object is not subscriptable

Thanks for the suggestion though

[veralauee]

Based on your error information, it seems the model uses "roi-pooling" instead of "global pooling", because of "landmark[0]". Would you plz check which config file you used when testing?

[ldm903]

In

Based on your error information, it seems the model uses "roi-pooling" instead of "global pooling", because of "landmark[0]". Would you plz check which config file you used when testing?

Do you mean it does not support roi resnet in test_predictor.py?

[tantao14]

maybe it need a input landmark instead of None, but i dont't know how to generate the landmark of single image

[markkdev]

@veralauee
When I use checkpoint: 'checkpoint/Predict/resnet/roi/latest.pth'
config: 'configs/attribute_predict/roi_predictor_resnet_attr.py'
Thats when I got the NoneType error.

When I use checkpoint: 'checkpoint/Predict/resnet/global/latest.pth'
config: 'configs/attribute_predict/global_predictor_resnet_attr.py'
I get the same predictions for any images.

[ashwath98]

Did you resolve this issue?

[PhantomKidding]

@markkdev How did you resolve it? I encountered the same. Firstly, I use vgg16 for global and get similar results regardless of images. Then I switch to ROI for landmark and get same error thrown.

[markkdev]

Never found a solution to this issue.

[liuziwei7]

Thanks for the feedback. We will update the attribute prediction model soon.

[swayam18]

Yeah, same issue. Would be great to know if there is a timeline for the prediction model to be updated

[knowlen]

also getting the (same) wrong predictions on my own held out images.

[Lytua]

#32 (comment)

I got the same problems. @markkdev did you find any solutions?

[gvisniuc]

Same issues, getting the same results for all external images, is there any transform that needs to be applied to the image perhaps?

[Debangshu132]

wrong predictions all the time :(

[veralauee]

We just updated the attribute-prediction tasks. Please use
python test tools/test_cate_attr_predictor.py \ --config configs/category_attribute_predict/roi_predictor_vgg.py \ --checkpoint checkpoint/CateAttrPredict/vgg/roi/latest.pth

Since the prior dataset just implements the coarse labeling, that leads to the wrong prediction. We relabeled a more compact and accurate dataset for attribute prediction.