hankkung / auto-dynamic-deeplab Goto Github PK

I am wondering how can I visualise the best cell and best network that it found after search. After decoding, it only prints the number as following:

architecture search results: [1 2 2 2 1 1 1 0 0 0 1 1]
new cell structure: [[ 1 5]
[ 0 4]
[ 2 4]
[ 3 0]
[ 5 4]
[ 7 4]
[11 7]
[12 4]
[17 4]
[18 2]]

I would appreciate if you provide some advice about what these numbers mean or how can I visualise them similar to Fig 3 in Autodeeplab paper. Many thanks

There is no such script in the scripts directory.

Thanks

Thanks for your excellent work!

What is the difference between Dynamic-AutoDeepLab and the original auto deeplab