Artly
Artly
The first convolution layer filter size is 5x5, you can change that to 21x21. Re-trian.
Yes. In the code: cmd:option('-arch', 'c9s1-32,d64,d128,R128,R128,R128,R128,R128,u64,u32,c9s1-3') So you need to use "-arch c21s1-32,d64,d128,R128,R128,R128,R128,R128,u64,u32,c9s1-3" in the training command line.
But from my experience, you do not want a very high resolution style images. That just give you too much "noise" in the generated image.
This looks like color saturation problem. One step of the network is to subtract different constant values from each of the RGB channel. Somehow, it also switchs the order of...
I did not use Torch 7. I wrote my own GPU code.
Thanks. How can I find the ROS_MASTER and ROS_IP?
this is the line in my .bashrc. export ROS_IP=192.168.0.29 192.168.55.1 2601:644:8103:5760:89d4:554b:8780:4cc1 2601:644:8103:5760:6467:b598:2740:cb24 The ip is correct. I think the messages meant the syntax of this line was not correct.
I fixed this problem. The package should be called "jetson-utils". But now it complained could not find "gst.h". How can I fix this?
I have the same problem, @LC041336 how did you download the model again?
I can not load the model file Error downloading object: demo_model/demo_model.data-00000-of-00001 (40bed66): Smudge error: Error downloading demo_model/demo_model.data-00000-of-00001 (40bed66ec5109d2620a390eb16ad04cad335406a5f33fca209dee2417381aca8): batch response: This repository is over its data quota. Account responsible for...