Run Error Or Get Error Result

1、when I run Landmark pooling script,get error like this:

Traceback (most recent call last):
  File "mmfashion/demo/test_attr_predictor.py", line 62, in <module>
    main()
  File "mmfashion/demo/test_attr_predictor.py", line 54, in main
    attr_prob = model(
  File "/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File “mmfashion/models/predictor/base.py", line 46, in forward
    return self.forward_test(img, landmark)
  File "mmfashion/mmfashion/models/predictor/base.py", line 29, in forward_test
    return self.simple_test(img[0], landmark[0])
  File "mmfashion/models/predictor/roi_predictor.py", line 52, in simple_test
    attr_pred = self.aug_test(x, landmark)
  File "mmfashion/models/predictor/roi_predictor.py", line 60, in aug_test
    local_x = self.roi_pool(x, landmark)
  File "python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "mmfashion/models/roi_pool/roi_pooling.py", line 51, in forward
    landmarks = landmarks.view(batch_size, self.num_lms, 2)
RuntimeError: shape '[1, 8, 2]' is invalid for input of size 1

2、when I run global pooling script,get not good result like this: img:demo/imgs/attr_pred_demo2.jpg checkpoint:AttributePrediction/VGG-16_GlobalPooling_Cross-Entropy.pth config:configs/attribute_predict_coarse/global_predictor_vgg_attr.py result:

[ Top3 Attribute Prediction ]
sleeve
knit
striped
[ Top5 Attribute Prediction ]
sleeve
knit
striped
denim
maxi
[ Top10 Attribute Prediction ]
sleeve
knit
striped
denim
maxi
stripe
print
lace
wash
shirt

other also get error like this, what should I do ?

open-mmlab / mmfashion

Run Error Or Get Error Result #124