search

MenghaoGuo / AutoDeeplab

Pytorch Implementation the paper Auto-DeepLab Hierarchical Neural Architecture Search for Semantic Image Segmentation
https://arxiv.org/abs/1901.02985
410 stars 97 forks source link

Softmax applied twice to the archtecture parameters? #18

Closed yucornetto closed 5 years ago

yucornetto commented 5 years ago 
    weight_cells = F.softmax(self.alphas_cell, dim=-1) at line 168, 172, auto_deeplab.py
    weight_network = F.softmax (self.alphas_network, dim = -1) at line 169, 171, auto_deeplab.py

The softmax applied to archtecture parameters are called twice, wonder this is what auto-deeplab meant to do or is a bug?

Randylcy commented 5 years ago

I think there is no reason to do that, maybe a little bug