zhoujinhai

farthest_point_sample is used to grouping layer in SA

> Hi @ismaelGomez87 , > > > My meshes have 480 edges each. I could augment the resolution but not reduce it. I defined my --pool_res argument accordingly: > >...

I have some vertices that can divide my model into two parts. Can I use MeshCNN to regress these vertices? If that's OK, do you have any suggestions?

> @ha5463 yes I am working since a while on the topic to get a mask network running on a jetson tx2 > My current approach is to use mask...

you need linked to SPIRV.lib

you need change the ```python class FPN(ScriptModuleWrapper): ``` to ``` class FPN(nn.Module): ```

您的邮件已收到 谢谢

> Any update on this? @zhoujinhai Yes, It worked for me!

> What about direct build by the following code: > > ```python > from yolox.layers import FastCOCOEvalOp > FastCOCOEvalOp().jit_load() > ``` I am add this code in train.py, and get...

yes, I have tried it, and change the layers name from ```conv4_3_norm_mbox_conf``` to ```ssd_cls1conv2```, but it show that ```bias:0``` does not exist after running.