kellurian

This could be a great resource, because there are lots of options that I think the devs assume we know about (or could be just me) because many have been...

Yeah, default values would help. For my part, I don't often see much difference in the types of masks when I have tried different ones, so I usually do just...

@andenixa Thank you so much for your advice, I think this is golden. Of course, your answers generate more questions: 1. I have a 1080 TI and almost always train...

So I had originally changed the originalhiresmodel.py file with these parameters(somebody suggested this change for lower cards in the Issues discussion): ENCODER_DIM = 512 x = Dense(dense_shape * dense_shape *...

What's the encoder DIM actually do? How much does it affect output? I've had better results than with the original trainer. Also, my question in regard to 256x256 was is...

I tried to increase the image shape, but got this error: Exception in thread Thread-1: Traceback (most recent call last): File "c:\users\sean\anaconda3\Lib\threading.py", line 916, in _bootstrap_inner self.run() File "c:\users\sean\anaconda3\Lib\threading.py", line...

Ok, so I have a different question, now about the sort tool(currently using the gui version). So if you want to use it on the images from the video that...

I tried it , couldn’t even get 1 batch to run. 1080Ti with 11 gb of ram. Out of memory Sent from my iPhone > On Jul 28, 2018, at...