xiaomi-automl / fairnas Goto Github PK

Hi,

Thanks for your work. I was wondering how do you deal with gradient updates on the non-searchable stages of the model.
The searchable layers will only be updated once, but multiple forward and backward passess would then go through the tail/stem and the detection head. Would you perhaps average the gradients ? or perhaps freeze the parameters of the non-searchable stages ?

Hello!

Thanks for your amazing work! I was wondering if you will release the searching code in future, for I wish to build new model on my own dataset.

Best,

I want to know your strategy for retraining the network. Can you release training network code?

You paper say 'In order to be consistent with the previous works, we don’t employ any other tricks
like dropout [21], cutout [6] or mixup [28], although they can further improve the scores on the test set.'
https://github.com/fairnas/FairNAS/blob/418b892c17016006f9edc33fea2c50f674d86ff0/models/FairNAS_A.py#L104
Is there any misunderstanding？

你好，
我对FairNAS的理解是，在训练超网的时候，每个batch是等待所有路径 反向传播 梯度相加之后，统一进行参数更新。 我的问题是，对于超网中的每个节点，它只存在于一条路劲中，所以只会接收到一次梯度，没有相加的过程，也没有必要等所有梯度反传之后一起更新参数，请问算法中提到的梯度相加是指什么？
另外，FariNAS虽然解决了很多公平性的问题，但是是否依然存在路径先后问题？就是说对于有相同节点noda P的路径L1和L2，先训练L1的时候，节点P已经被改变，再训练L2的时候，该节点是否会影响到L2的效果？
谢谢！

Another paper EVALUATING THE SEARCH PHASE OF NEURAL ARCHITECTURE SEARCH tested FairNAS on NASBench101 but get the Kendall Tau of -0.23.

FairNAS using 13 models to evaulate the rank and get the Kendall Tau of 0.9487.

I think the number of models used in FairNAS is the way too little and can not really reflect the rank ability of FairNAS

the paper didn't offer the speed of the network compared with other lightweight network？