about train？ about segnext

[uyzhang]

You need to put the pre-trained weight under the corresponding folder.

[uyzhang]

You need to put the pre-trained weight under the corresponding folder.

And You need to load the pre-trained weight by changing local_configs/segnext/base/segnext.base.512x512.tusimple.160k.py like other configs.

[Onehundred0906]

i change the weight's path in code of' local_configs/segnext/base/segnext.base.512x512.tusimple.160k.py' like the first picture,

but when i train my dataset, the result is showed like the second picture , is very Irregular. emmm, thank you very much for bothering you for my question ！

[Onehundred0906]

my data has only 2 classes(background and road_line), in my opinion, the dataset_config should be correct! thanks very much.

[uyzhang]

If you modify your dataset according to ade20k, you may ignore the label 0.

[Onehundred0906]

ooo, thanks, maybe this is a cause, but if i need to consider the background based the dataset ade20k, and i can modify where code ?

[Onehundred0906]

thanks i have found the error and it has been trained normally, the reduce_zero_label should be False in my dataset config