Open coordxyz opened 5 years ago
对于第四个到第8 个hourglass模块而言,他的预测结果并不是传统的方式得到的 而是通过对f这个特征首先进行1x1卷积,得到sp,sp是一个1通道的featuremap,然后这个1通道的featuremap送到M内,得到attention map,\Phi_p(它也是1通道的),然后这个attention map乘以h_1^{att}(它不是1通道,比如256个通道的)得到经过对应于某个关节点的attention map得到的特征,然后再使用一个1x1卷积得到1通道的某个关节点的热力图。
hi, I'm confused about the refined feature map. Should it be h2^att rather than h1^att? In your paper, Equ.10 describes the refined feature h2^att is generated from h1^att, but in section 5.2.4, only the h1^att is used as refined feature and to do final prediction.
This is also conflict with Figure 4 in which the h2^att is the refined feature and used for heatmap prediction.
If h1^att is the refined feature, what does the h2^att used for?
Thank you~