search

vana77 / Market-1501_Attribute

27 hand-annotated attributes of Market-1501
283 stars 63 forks source link

implementation of the reweighthing module: how to element-wise multiplied attribute predictions score and global feature #19

Closed jpainam closed 3 years ago

jpainam commented 3 years ago

Hi, thank you for sharing the dataset. I'm trying to implement your paper in pytorch. Got some few questions. Let's suppose I'm using a 64 minibatch on Market-1501 dataset. And I use the 28 attributes (I personally have 30). Using this section, image

number of attribute m = 28
Equation 3). Is simply a Linear layer (ax + b) with bias term follow by a sigmoid.
for 64 minibatch, 
The attribute prediction score has shape [64, 28] i.e., R^{64xm}
The global image representation has shape [64, 2048]

In your paper, you said, you element-wise multiplied the two. How can you multiply the attribute prediction score ([64, 28]) with a feature representation of shape [64, 2048]. can you explain what I'm missing here? Thank you.