Person-Attribute-Recognition-MarketDuke
Person-Attribute-Recognition-MarketDuke copied to clipboard
Attribute Re-Weighting Module
Is there attribute re-weighting module in the training net?
No, I did not introduce such a module into the network.
Hi. I tried to introduce the re-weighting module. But can't figure out the right values. According to the original paper
m = 28 # the number of attributes
\tilde{a} \in R^{1x28}
After the element-wise multiplication
a = c . a # R^{mx1} . R^{1xm}
a \in R^{m x m}
A global feature representation is [1, 2048]
. The paper says, a \in ([28, 28])
concatenated with the global features ([1, 2048])
.
Anyone knows how to concatenate these two features vectors.
[28, 28] x [1, 2048]
@jpainam where you able to implement this functionality ??