purse1996
purse1996
same problem, have you solved the problem
> @verymadmatt We perform class-balance for all the experiments on Cityscapes. We only use the Cityscapes train set for training. First, could you provide more details about your environmental information?...
Sorry, I did not express clearly what I mean. Of course, class weight is useful. While no matter that LOSS.CLASS_BALANCE is True or False, class-balance weights are always in use...
So where that the param LOSS.CLASS_BALANCE used? I read the code, it seems that no matter what is CLASS_BALANCE param, the balance loss is used in the cityscape dataset.
Thank you. I test the code in the 1080TI. The inference time is very fast, but the file IO is very very slow. Can you offer some suggestions about improving...
After upsamle by sub-pix, there is an annotated code here output = slim.conv2d(x_reslut,3,[3,3])， it seems to a 3x3 convlution after upsample. When I use the convolution, the same problem happen...
In fact, I don't solve the problem and just ignore the convolution layer. If you have any idea about it, please tell me. Thank you very much. Additionally, Do you...
Do you solve the problem? I meet a similar problem, the miou decreases from 82 to 78. Thank you very much.
Thank you for your advice. Very help. I will try your suggestions and do experiments.
Thank you for your advice. I do some experiments and meet another problem. In my experiment, the smaller the reg parameter, the better the result, such as 0.01 of reg...