visonpon

@gddingcs @soumith I also encounter this problem. but my batch size is 1 and my gpu memory is sufficient .

@gddingcs @zhuaichun @soumith my cudnn version is 5.1 and i have installed the latest cutorch , i really don't know why. since it has confused me some days , hope...

@bhack @yosinski the above three steps to visualize my own network also have some problems: running ` python ./crop_max_patches.py ./output.pkl ./deploy.txt ./caffemodel ./img_val ./val.txt ./unit_jpg/vis/max_im conv2` i got en error...

`assert args.do_maxes or args.do_deconv……`,'specify at least one do_*option to output.' what's that mean to specify? @yosinski

Hi @ak9250 @HideUnderBush, I have written a [colab](https://github.com/visonpon/colab-for-UI2I_via_StyleGAN2/blob/main/colab/style.py) that works fine, hope it helps ~

I also have the same confuse as @vincentwei0919 , and also look forward to have a demo.py to show how to inference on images or video. thanks~

Hi, I also encountered this problem. I have tried to save the fitting time by commending the `generateMesh `and some functions from `meshTrackingProj.h` to not save the rendered mesh png...

as you can see from the below,left is detec,right is repro.although detec result are fine ,but the repro only has one person.  the error in reprojection process seem because...

Hi @leodilla ,I try to use xvfb-run, but get another problem, hope you help. since I use this project on virtual machine, my command is` xvfb-run -a ./binvox -d -88...

also hope that can provide some scripts for visualize,thanks~