Cytosine
Do you try with torch.unsqueeze() ? This function could change the dimention.
hi @xjhcassy just to be quick: i am NOT the author of this work. But I did play with the code for a while.
@xjhcassy I also talked to someone in this field: as you have noticed, AutoML is very young and it is not very "auto". i.e. those parameters you mentioned are tuned...
@xjhcassy BTW if you are thinking of applied automl to your own task, then it is a very good idea to start as you mentioned in the blackened words.
@xjhcassy In addition, there are following works of DARTS, such as Progressive DARTS, Partial Channel DARTS, FairDARTS. I think they all on github. Sorry for replying in parts. Good luck:)...
I also compared the DARTS with ResNet. And I found the same. I think this could be fixed by switching the search space with more efficient ones. GL, PF
Well, here is the thing: DARTS is fast ONLY when searching for models but it is indeed very slow when retrain searched models. Best,
> It takes a long time to search architecture and train from start. If I use other code with Resnet to train from start. It only takes 1/5 time of...
> Does DARTS_V2 in genotypes.py mean the architecture of DARTS(second order) ? From my understanding, Yes.
Hello, In general, a larger batch size usually converges faster than a smaller dataset, while the latter usually can reach a higher accuracy than the former. GL,