Question about reshape_patch function

[Prevalenter]

what the role of reshape_patch in core/utils/preprocess?
I found that adding the patch_size parameter can significantly speed up the training process and reduce the cuda memory.

And I test function reshape_patch using the code following:

    img = cv2.imread('cat.jpeg', 0)
    img = img[np.newaxis, np.newaxis, :, :, np.newaxis]
    img_patched = reshape_patch(img, 3)

and I show the img(a gray image) and img_patched:

So is this function used to reduce the spatial resolution of the image?

And thanks for your good work!

[wuhaixu2016]

Yes, this operation is to reduce the spatial resolution, but it still keeps the complete information by adding the number of channels.

[Prevalenter]

Thansk for your answer！
And I did not find the description of this operation in the paper. Does this operation refer to other codes? or proposed by your team?

[wuhaixu2016]

I think this is a widely-used idea in computer vision, such as super-resolution. We implemented this operation ourselves in this paper.

[Prevalenter]

ok, thanks for your answer.