Is there a way for the eyes to look in the same direction as the model? I dont know how to make it seem more real if the eyes are always looking at the camera, which in B in the picture is doing. Is there an extra setting, or is my training data bad?
Search found 12 matches
- Tue Dec 03, 2019 3:21 am
- Forum: Training Discussion
- Topic: Eye tracking?
- Replies: 1
- Views: 1846
- Fri Oct 04, 2019 8:55 pm
- Forum: Training Discussion
- Topic: Loss Function
- Replies: 1
- Views: 3117
Loss Function
Whats the difference between all the loss functions? and which one will give me the best results? Also, does Penalize Mask Loss improve results?
- Thu Oct 03, 2019 1:41 am
- Forum: Training Support
- Topic: PC crash
- Replies: 11
- Views: 7272
- Wed Oct 02, 2019 3:06 am
- Forum: Training Support
- Topic: PC crash
- Replies: 11
- Views: 7272
Re: PC crash
Hmmm, changing the batchsize is unlikely to cause shutdown issues. Lowering the mem clock speed is more likely. However, the important thing is it works now :) My PC is kind of weird, if it doesn't like something then it shuts down. e.g. batch size too high? shutdown. batch size too small? shut dow...
- Tue Oct 01, 2019 2:11 am
- Forum: Training Support
- Topic: PC crash
- Replies: 11
- Views: 7272
Re: PC crash
Vega FE can easily use 450w and your i5 6600K can easily use 200. Beyond that, many PSUs struggle with peak load and sudden voltage demands which can cause crashes. Unfortunately, we can't do anything to prevent or control hardware issues like this. If you want to try troubleshooting the first step...
- Sun Sep 29, 2019 11:37 pm
- Forum: Training Support
- Topic: PC crash
- Replies: 11
- Views: 7272
- Sun Sep 29, 2019 11:20 pm
- Forum: Training Support
- Topic: PC crash
- Replies: 11
- Views: 7272
- Sun Sep 29, 2019 11:14 pm
- Forum: Training Support
- Topic: PC crash
- Replies: 11
- Views: 7272
PC crash
When I'm training on RealFace, my PC just randomly decides to turn off and stays off until I press the start button. When I take a closer look, I get error code 0x00000000 and no reason. What can be the cause? Running AMD Vega FE with Intel i5 6600k and 4x2 HyperX ram
- Fri Sep 27, 2019 12:20 am
- Forum: Training Discussion
- Topic: dfl-H128 taking forver to train
- Replies: 3
- Views: 4605
Re: dfl-H128 taking forver to train
The following is a simplified explanation. There is more to it than this (the structure of the model etc), but to keep it in simple terms, I will talk purely in terms of resolution. H128 has double the resolution. of the original model. You would think that this would mean it would take twice as lo...
- Thu Sep 26, 2019 11:38 pm
- Forum: Training Discussion
- Topic: dfl-H128 taking forver to train
- Replies: 3
- Views: 4605
dfl-H128 taking forver to train
To get 100 iterations, it would take 6:45 on my Vega FE. To get 100000 iterations with batch size of 32, it would take almost 5 days. None of the other training methods do this like the original. For original, 100000 iters it would take 16.666 hours with the same setup of batch size of 32. Is H128 s...
- Tue Sep 24, 2019 9:18 pm
- Forum: Hardware
- Topic: Optimizations for Vega FE?
- Replies: 3
- Views: 4147
- Tue Sep 24, 2019 4:15 am
- Forum: Hardware
- Topic: Optimizations for Vega FE?
- Replies: 3
- Views: 4147
Optimizations for Vega FE?
Just wondering if there are any ways to optimize my Vega FE in training to either give me better results or faster results.