About Cutout size

[Chrisfsj2051]

Hi!

I found that in your code, you set cutout_op as iaa.Cutout(nb_iterations=(1, 5), size=[0, 0.2], squared=True), here size=[0,0.2] means the size is either 0 or 0.2 ( under imgaug 0.4.0), which is different as what is described in paper.

Maybe we should change it to iaa.Cutout(nb_iterations=(1, 5), size=(0, 0.2), squared=True) ?

[zizhaozhang]

That is a great observation. We did not notice this difference during implementation. If you would like to compare the difference and let us know that will be great.

[Chrisfsj2051]

That is a great observation. We did not notice this difference during implementation. If you would like to compare the difference and let us know that will be great.

In the process of reproducing the result of C+{GB}+Cutout under fully supervised manner, standard 1x setting in Table3, I tried to use cutout with binary {0%, 20%} and random [0%, 20%], here is the results:

method	mAP
binary {0%,20%}	35.4
random [0%, 20%]	35.6

So I think it may make a small difference.