Han Xiao

Thanks for answering my question! But how to merge the multi-scale testing results? It seems the scripts don't include this. After scaling,the outputs are also of different scales. Shall I...

Great! Thank you very much.

Sorry to bother again. I tried and the accuracy achieved 80.00%,still cannot achieve 82.8%. I think my method may not be correct. Did you mean resizing and averaging outputs of...

Thanks for your reply! I understand. I believe using Mapillary dataset for pre-training would be very beneficial because of the domain similarity. But have you tried not using Mapillary data?...

Hi, I met the same problem. The reproduced accuracy is 64.74%, which is much lower than the result in the paper. Have you solved this problem?

Hi, I also met the similar problem. I think the problem is caused by upsampling by 4,which makes the two sizes not match. I just used low_res_input = F.interpolate(input=low_res_input, size=high_res_input.size()[2:4],...

Hi, I also met the similar problem. I think the problem is caused by upsampling by 4,which makes the two sizes not match. I just used low_res_input = F.interpolate(input=low_res_input, size=high_res_input.size()[2:4],...