Open CaptainEven opened 4 months ago
Hi, thanks for the excellent work! I found b0 "cityscape" semantic image size is only 1/8 of the input image size? May i ask where the problem is?
I found the 'segout' head is not equipped with a Sigmoid head, and the training is not going to converge on my observation...
Hi, thanks for the excellent work! I found b0 "cityscape" semantic image size is only 1/8 of the input image size? May i ask where the problem is?