Computer vision

也是，fusion模块必须是固定的。

Thank you for your kind help, yes, depthwise separable convolution maybe need even more channels, and it is difficult to replace ModulatedConv2d. Let me try FastGAN

I have the same question, do you find the answer?

i have the same problem

hi@PINTO0309 @duangenquan , thank you all for your reply, I will write the environment in detail. But for the error message, that is the full text.

@a2sheppy

@JohnnyHopp could you please share your pretrained model? thank you

"--tune_from", "checkpoint/anycost-multires_ffhq-1024_distill/stylegan2-ffhq-config-f.pt", "--teacher_ckpt", "checkpoint/anycost-multires_ffhq-1024_distill/stylegan2-ffhq-config-f.pt" "--data_path", "/my/FFHQ/path..." other options are exactly same with your train_anycost_multires_adach_ffhq.sh

can anyone turn yolo v3 models into caffe? I could pay for it

hi,thank you, I have checked the pre-defined values before the main, and debug to see the device type and device id, they are OK. and i also added clock related...