Vision: It seems there is no upsampling operations in the implementation of Deeplabv3?

Created on 11 Feb 2020  路  1Comment  路  Source: pytorch/vision

Hi, guys,
I am learning about the the implementation of Deeplabv3 today,
and I find that it seems, there is no upsampling operations in deeplabv3.py,
so where is the upsampling operations of Deeplabv3 model?

Any answer or idea will be appreciated!

models question semantic segmentation

Most helpful comment

Hi,

The upsampling is present in the base class, see https://github.com/pytorch/vision/blob/819b2e9f39648711ab06562fc8f03ad001cf10be/torchvision/models/segmentation/_utils.py#L25

Let us know if you have further questions!

>All comments

Hi,

The upsampling is present in the base class, see https://github.com/pytorch/vision/blob/819b2e9f39648711ab06562fc8f03ad001cf10be/torchvision/models/segmentation/_utils.py#L25

Let us know if you have further questions!

Was this page helpful?
0 / 5 - 0 ratings