Open csBob123 opened 2 years ago
Hi, I did not use the KITTI semantic labels for training but only the ones from Cityscapes.
Hi, I did not use the KITTI semantic labels for training but only the ones from Cityscapes.
Hi, Thank you for your reply. The number of classes on Cityscape is 19, but I found the final output of 'segdecoder' has 20 classes(20 channels).
Could I know the reason and its impacts?
Thank you for your attention.
Hi,
the 20th class is the background class. It is essentially not trained, as in the wieghted cross-entropy loss its weight is set to 0. For the evaluation only the 19 classes of the Cityscapes dataset are considered. In theory it should not really matter, if you only train 19 classes or 19 classes + 1 background class, if the weight of the background class in the loss is set to 0.
Hi @klingner I had a small query about which part of Cityscapes Dataset to download. Up to my understanding we have to use the gtFine_trainvaltest.zip. But it has 30 classes and @csBob123 said the model is trained on 20. Is that okay or do I need to change anything in the code in order to do the segmentation training?
Thanks in Advance :)
Hi, the Cityscapes dataset has 30 classes, but only 19 of them are used for training and the other classes are set to background when training. Effectively, I always use the 19 classes as defined by Cityscapes.
Okay. Thanks for clearing up the query. :)
Could I know whether you use the KITTI semantic labels for the training? I guess you only use the semantic labels on Cityscapes.
Thank you for your work.