ronslos
ronslos
Hi, I have the exact same issue. I have installed the conda environment as instructed and trained the network according with the default parameters and it doesn't converge to anything...
Here are all the packages I am using currently.  I have not made any changes to the original code besides changing the name of the dataset and setting the...
1. I am running Ubuntu 16.04 2. My python version is 3.6 3. I ran run.py from the SpectralNet root directory I have downgraded to tensorflow 1.4.0 cpu only as...
It's working on mac. I wonder, what could cause it to vary between OS's? Thanks!
I'm still working with your code. I managed to run the example datasets given in your code, but when I build my own dataset following an example given in your...
I have the same problem. The image grid that is saved to the directory PGGanCeleba are all cropped as shown above.
Hi, I figured out my mistake. I was training on the original CelebA dataset and not on the cropped version that you supply with your code. Thanks for the help!
Hi, I am also eager to test GroundingDINO-L as the reported results are quite amazing. Any news regarding when the weights are expected to be published?