search

meijieru / AtomNAS

[ICLR 2020]: 'AtomNAS: Fine-Grained End-to-End Neural Architecture Search'
Other
224 stars 21 forks source link

Questions about the baseline models #6

Closed colorjam closed 4 years ago

colorjam commented 4 years ago

Hi, thank you for your interesting work.

  1. Why the FLOPs of MobileNetV2 your implementation (301M) is different from the original paper (300M) in Table 1?
  2. Can you provide the pre-trained model?
meijieru commented 4 years ago

Sorry for the late reply.

  1. It has 300.xM parameters, which is rounded to 301M.
  2. We are organizing the code and a new version will be released soon, where the pre-trained model will be provided.