You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
-----------------------------------------------------------------------------
## upsample tensor 'src' to have the same spatial size with tensor 'tar'
def _upsample_like(src,tar):
src = F.upsample(src,size=tar.shape[2:],mode='bilinear')
return src
------------------------------------------------------------------------------
It is used start from line 88: hx6dup = _upsample_like(hx6d,hx5), which upsamples tensor hx6d to the same spatial size (h,w) of hx5, the batch_size and the channel numbers are kept the same.
On Jun 20, 2020, at 8:31 AM, tongxiaozhong14 ***@***.***> wrote:
Thank you for your answer, but how should this be used? I didn’t find any specific application in your U_2 code
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
Thank you for your answer, but how should this be used? I didn’t find any specific application in your U_2 code
The text was updated successfully, but these errors were encountered: