PSPNet implementation
thawro opened this issue · comments
Tomasz Hawro commented
I found a few inconsistencies with the original paper
- There is no dilation strategy for encoders for
PSPNet
insmp
, while authors of the paper used dilated strategy for the encoder (i.e. ResNet):
"...we use a pretrained ResNet [13] model with the dilated network strategy [3, 40] to extract the feature map."
- In the
smp
there is a dropout layer before segmentation head, while authors of the paper do not mention dropout at all (maybe because batch normalization is used) - The convolutional layer before segmentation head uses
kernel_size=1
and the convolutional layer inside segmentation head useskernel_size=3
. Shouldnt that bekernel_size=1
for segmentation head andkernel_size=3
for conv before head?
Are those modifications intentional? If so, what was the reason?
github-actions commented
This issue is stale because it has been open 60 days with no activity. Remove stale label or comment or this will be closed in 7 days.
github-actions commented
This issue was closed because it has been stalled for 7 days with no activity.