Open xinanbuyi opened 4 years ago
Hi, maybe the hyperparameters are not optimal or due to the reason of the dataset.
Hi,why is the miou lower than the paper,like pspnet,danet on cityscapes or voc2012,can we do a same results as the paper?
i have the same problem
i also
The oscillation of loss function is severe
The segmentation effect is not good when using your own dataset, and the Miou is too low
Why, I look forward to your reply