xu19971109
xu19971109
The dataset config is a copy of Cityscape. 
After my constant debugging, I found that the problem came from here：  why？ I tried to enter the function but did not find the parameter operation to load checkpoint.
I’find。  I forgot to change the number of categories when I trained. The configuration file I trained was 26 categories, even though I trained with 0 and 1 labels....
I have a similar question. I need to calculate the IOU of a single picture when inference pictures, but I find that the same picture runs repeatedly with the same...
This error usually occurs around the first BATCH in the first EPOCH.
I konw! I tried to modify the version of Torch, and this problem still exists in 1.11, 1.8.1, and 1.8.0..The problem arises because the data and model output float types...
I saw it in the other comments section，you should modify _c. WORKERS = 0 in default. py