Researcher.YuanYuhui

@Gaoyiminggithub It seems that [link ](https://github.com/Cadene/pretrained-models.pytorch) is not trained on COCO. I am wondering whether could you share the checkpoints of the **Aligned** Xception (instead of Xception) trained on COCO.

@Gaoyiminggithub Thanks for your quick reply, could you provide me the pytorch version or we can load the weights of the tensorflow models (in the Figure as below) directly? 

@Gaoyiminggithub Thanks for your help. I am wondering if you could share with me the mentioned COCO trained model.

@Gaoyiminggithub Thanks~

@Gaoyiminggithub Why do you comment the BN operation during the "Exit flow" as below? ``` # Exit flow x = self.block20(x) x = self.conv3(x) # x = self.bn3(x) x =...

@Gaoyiminggithub Got it~ Besides, it would be great if you could share with me the converted Pytorch model based on the official ImageNet based tensorflow models. Besides, I want to...

I am trying the solution by Ross. [Solution](https://github.com/facebookresearch/Detectron/commit/47e457a581c2623aeaf18156ad3c0b0eb56c9cd8) I will report the results latter.

@Redaimao I have solved this problem. I use the Res50-FPN as the backbone.

Sorry for the inconvenience. First, your reproduced performance of **81.54%** is already comparable with our previous best result (based on this code base) on the Cityscapes validation set. The performance...

Please check Section 2.2 the original [Cityscapes paper](https://arxiv.org/pdf/1604.01685.pdf) and it is an official (default) scheme to only consider 19 out of the 34 categories for the semantic segmentation task. Here...