look for "block_composition"

[Fish08042]

hello!
i find your code have this "from datasets.dct_resize.block_composition import block_composition",but i cant find "dct_resize"in datasets

[luowei0701]

same question ,have you solved it ?

[Fish08042]

same question ,have you solved it ?

i havent~

[BeBeBerr]

Same problem here... @calmevtime Are there any missing files for the training code?

[kaix90]

The block_composition function is obsolete. Please comment out the line and it should be fine.

…

Sent from my iPhone

On Dec 9, 2020, at 5:18 AM, Luyuan Wang ***@***.***> wrote:  Same problem here... @calmevtime Are there any missing files for the training code? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[BeBeBerr]

The block_composition function is obsolete. Please comment out the line and it should be fine.
…

Thank you for your kindly reply. However, there are multiple places require datasets.dct_resize. For example, in cvfunctional.py line 19:

from datasets.dct_resize.resize_dct_opencv import resize_dct

It seems that this function is necessary. What should I do to fix that?

[ivylinden]

same problem

[ivylinden]

class UpsampleDCT(object):
def init(self, L=1, M=1, N=8, T=None, debug=False):
self.L, self.M = L, M
self.T = T
self.N = N
self.debug = debug

    self.A1 = block_composition(L, N)
    self.A2 = block_composition(M, N)

[ghost]

是否可以重新上传datasets.dct_resize文件，万分感谢

[SystemErrorWang]

@calmevtime it seems the function "block_composition" is necessary in UpsampleDCT. would you please upload the dct_resize.py file, and also clarify the meaning of L, M, and N?

[ar-roy]

Has anyone figured out their own implementation of dct_resize?