I am reading the tf-DeepLab codes with backbone nas_hnasnet from the paper Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation published at CVPR 2019. I have confused with the network layer defined as "backbone=[0, 0, 0, 1, 2, 1, 2, 2, 3, 3, 2, 1]" in nas_network.py. Is it supposed to be sought automatically? Why it is pre-defiend and not changed along the training?
Asked
Active
Viewed 58 times
0
-
Are you looking at minified source code or something? – T J Oct 16 '19 at 11:57
-
No, the codes are from the tensorflow deeplab library. I am just confused with the network architecture searching part. – JJTT Oct 17 '19 at 01:02