WENZHE LIU

> > Hello @SongKaixiang @Margrate ! > > Congratulations! You actually found a weakness of DARTS. Many following works, for example, ProxylessNAS, pointed out that althought DARTS is much faster...

> Or even reduce some of the layer options, because, in the searching phase, the model is K times larger than the final model (for K stands for the number...

> Hellow, @Catosine , I also train the code on my ultrasound dataset. My question is that the input of (32,32) is too small for me. So i set to...

> In the paper they mention that w48 obtained the same results as w32 on MPII. Perhaps this is the reason w48 is not included? Great thanks for your suggestion!...

@Gavin666Github @chunduri11 heyyyy there! Could you please share me your experience in how to extract RGB and flow? great thx

> > > > @Gavin666Github @chunduri11 > > heyyyy there! Could you please share me your experience in how to extract RGB and flow? great thx > > https://github.com/qijiezhao/py-denseflow.git >...

> @rrryan2016 use Imagenet pre-trained weights Yep, I used the pretrained model. :P

> exp1: no pre-trained > exp2: pre-trained > > @rrryan2016 try to conduct two exp above, show me the results. Thanks for your reply and patience. Taking the accuracy on...

``` Package Version ----------------- ------------------- backcall 0.2.0 cached-property 1.5.2 certifi 2020.12.5 cmake 3.20.2 cycler 0.10.0 decorator 4.4.2 h5py 3.2.1 imageio 2.9.0 intel-openmp 2021.2.0 ipython 7.24.1 ipython-genutils 0.2.0 jedi 0.18.0 kiwisolver...

Thanks for the concerns. But sorry, I intend to give up the version switch. 1. I guess the torch version makes little difference to the accuracy. 2. The torch version...