search

qinenergy / corda

[ICCV 2021] Code for our paper Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
71 stars 12 forks source link

how to use DACS #14

Closed yuheyuan closed 12 months ago

yuheyuan commented 1 year ago

In your paper use DACS as baseline. However, DACS don't propose the SYNTHIA->CITYSCAPES trainning. So, I want to ask you how you use trainning DACS. I read you code. Should I need to delete all code which use depth in trainning. because I need to use DACS in SYNTHIA->CITYSCAPES to obtain data in my work image

Another question, When trainning finished, predictions direction will be created and some test pictures saved here.Where Can I find the code about it.

Maybe it's too long because this work is finished two years ago.You may forget some details. I will be very appreciated if you reply me !

qinenergy commented 1 year ago

You can use directly the DACS code, a few lines need to be modified. Please see the discussion below in the DACS repo https://github.com/vikolss/DACS/issues/4

The saving of the test image is in the evaluation code. https://github.com/qinenergy/corda/blob/5896b77169ecef95f7c5f6ecc71a8f757291a505/evaluateUDA.py#L201.