search

Dootmaan / DSRL

Implementation of CVPR 2020 Dual Super-Resolution Learning for Semantic Segmentation
MIT License
95 stars 17 forks source link

dataset instructions #11

Open SB2020-eye opened 3 years ago

SB2020-eye commented 3 years ago

Hi. I'm a noob.

I'm able to follow your clear instructions so far. (Thanks!)

I'm not sure exactly about the datasets I need.

I downloaded "checkpoint.pth.tar" and put it in my "pytorch-deeplab-xception" folder. Is that correct? Is that enough? Is this the folder that contains all the datasets referenced in mypath.py?

Any assistance would be so much appreciated.

All the best.

Dootmaan commented 3 years ago

Hi there, sry for the long time waiting. I have been working on another project so i didn't pay much attention on this repo recent days.

I used Cityscapes in this expeiment and you can download it from here. The checkpoint.pth.tar is the pretrained weights for the model, and you can place it anywhere. Just remember to use the "-resume [path/to/weights]" when running train.py.