mtconv not improve acc compare with depthwise ，is the training data too small matter？

[l2009312042]

it is a great job ,thanks for sharing ! the following is my test result , from this ,the acc is not improve ,can you give me some advice how to improve the acc ?

data	model	acc	size
google	net12	96.6	1.3m
google	net6	96.7	785kb
google	net12_mt_noconvert	96.56	2.41m
google	net12_mt_convert	96.56	1.78m
google	net6_mt_noconvert	96.75	1.31m
google	net6_mt_convert	96.75	0.99m

[Interlagos]

Thanks for your attention to our work.

We recommend training TENet with the default hyper-parameters in this repo, especially the weight decay is set to 4e-5 instead of 1e-4, which affects the result a lot.

We retrain the following models 10 times, respectively. Here is the result:

	TENet12_MTConv	TENet12	TENet6_MTConv	TENet6
no.1	96.7543	96.6569	96.7218	96.5920
no.2	96.9815	96.4946	96.7868	96.3648
no.3	97.1438	96.3973	96.6245	96.3973
no.4	96.8517	96.2025	96.2999	96.4946
no.5	96.8814	96.5271	96.2350	96.4622
no.6	96.5920	96.8192	96.6569	96.7868
no.7	96.5324	96.8841	97.1762	96.2674
no.8	96.6569	96.4622	96.4297	96.6245
no.9	97.0464	96.5271	96.5271	96.5271
no.10	96.6569	96.4946	96.7543	96.5271
mean	96.8097	96.5466	96.6212	96.5044

Hope it can help you.

[l2009312042]

thanks for your advice