Question about the attention block.

[SongYupei]

Thanks for sharing the code of the paper. I have a question about the code in line 234-237.

DeepMultiCap/lib/model/DMCNet.py

Line 234 in 4e93adf

geo_feature = torch.cat(geo_feature, dim=0)

``
geo_feature = torch.cat(geo_feature, dim=0)
print('attention input shape:{0}'.format(geo_feature.shape))

[4, 1, 4, 320, 5000]

if self.opt.coarse_part:
geo_feature = self.attention(geo_feature, self.feature_fusion)
# [1, 1, 4, 320, 5000]
print('attention output shape:{0}'.format(geo_feature.shape))
``
the shape[0] of geo_feature is become from 4 to1, but geo_feature.shape[0] is level number, it is not the viewr number become one.
Any one can help me understand the probelem?