liddle rain
liddle rain
About the reason, I find that y will be flattern in this code.But for example ExtraTree are supported for the muti-output regression.  ``` if X_train_all is not None and...
> @fengsxy @miquelduranfrigola @gmkyadav I have an idea to improve the AutoML performance for multi-output task. After AutoML.fit() finishes for one output, we could use the warm-start capability from flaml...
> >@fengsxy whether to use the first output as a feature is up to you. In either case, you can use best_config_per_estimator as a starting_point for next automl. Would you...
>> Thanks. BTW, what application do you use flaml for? > > @sonichi My data is use a lot of contious data(feature) to predict the PM2.5/PM10(contious data)
 @sonichi Hi,sonchi. I have two things to share! Today i am trying to use warm-start,but when i use muti-Reregssor with two out-put first it has some problems. And with...
> 作者您好，我这边简单复现您的VIG工作，使用PaddlePaddle框架复现了VIG-s模型。准确率为Validation Acc@1: 0.8030, Validation Acc@5: 0.9511。 项目地址：https://aistudio.baidu.com/aistudio/projectdetail/4288323?contributionType=1 感谢你们精彩的工作！ 您好我想问下 论文复现 代码训练的时间，因为原文只说了使用八台V100，但没有说时间， 我有两个疑问： 1.首先是网络的算力瓶颈在哪？因为据我所知图卷积算法以及1*1卷积并不会成位算力瓶颈，所以算力瓶颈是源自构图的地方吗？ 2.网络过程中使用KNN构图所使用的库是numpy会不会成为网络运行的瓶颈？
想问下用fairseq的话 您用了预训练参数了嘛，感激不尽！
I have cloned the newest version, but it doesn't work.
> > rameters of the final classification layer, and transformers will random initial its parameters. So you should finetune the ALBERT with your traini > > Excuse me, I can't...
同问