Target image resolution and Python environment
amandamer opened this issue · comments
Hi Sergi,
I would like to know if the target image used during the transfer learning process could have non-isotropic resolution.
Another question: part of the code is written in C? Is it ok to run the code in a Python environment?
Kind regards!
Hi @amandamer,
Theoretically you can change the patch size to non-isotropic resolutions.
But take into account that the pre-trained model has been trained with
isotropic resolucion so the results may be weird.
The code is 100% python.
take care,
s
…On Wed, 27 Jan 2021 at 16:17, amandamer ***@***.***> wrote:
Hi Sergi,
I would like to know if the target image used during the transfer learning
process could have non-isotropic resolution.
Another question: part of the code is written in C? Is it ok to run the
code in a Python environment?
Kind regards!
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#17>, or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABIKMQRFV32BNKUNQOJYB73S4AVB7ANCNFSM4WVN3FDA>
.
Ah ok, thank you so much for the reply!
Do you recommend some software/tool to change the resolution of ground truth images?