distilling path issue about hfnet HOT 4 CLOSED

Dear Author:
when I run the code (db = [hfnet.inference(i) for i in images_db]) of demo.ipynb,it report next error：InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: You must feed a value for placeholder tensor 'Placeholder' with dtype float and shape [?,?,3]
[[{{node Placeholder}}]]
[[strided_slice_38/_587]]
(1) Invalid argument: You must feed a value for placeholder tensor 'Placeholder' with dtype float and shape [?,?,3]
[[{{node Placeholder}}]]
0 successful operations.
0 derived errors ignored.
May I know how to solve this issue? Many thanks.

from hfnet.

This indeed seems to be a bug, let me check this. In the meantime, you can comment out the assert and manually copy the files after export.

from hfnet.

Dear Author:
when I run the code (db = [hfnet.inference(i) for i in images_db]) of demo.ipynb,it report next error：InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: You must feed a value for placeholder tensor 'Placeholder' with dtype float and shape [?,?,3]
[[{{node Placeholder}}]]
[[strided_slice_38/_587]]
(1) Invalid argument: You must feed a value for placeholder tensor 'Placeholder' with dtype float and shape [?,?,3]
[[{{node Placeholder}}]]
0 successful operations.
0 derived errors ignored.
May I know how to solve this issue? Many thanks.

the shape of Input image must be 3 channels, check it.

from hfnet.

Closing this issue due to inactivity. I am currently not able to provide support for this codebase. Feel free to reopen.

from hfnet.