Ah perfect.
Missed it.
Thnx!
Search found 16 matches
- Wed Dec 21, 2022 1:20 pm
- Forum: General Discussion
- Topic: Reverse Swap
- Replies: 2
- Views: 1806
Re: Reverse Swap
- Wed Dec 21, 2022 10:38 am
- Forum: General Discussion
- Topic: Reverse Swap
- Replies: 2
- Views: 1806
Reverse Swap
Is it possible to do a reverse swap?
So I train face B on top of face A now, but can I switch that and use the same model to put face a on face b?
In essence all that is needed is in the model..
- Mon Dec 12, 2022 1:27 pm
- Forum: Training Discussion
- Topic: Possible to turn Fc off?
- Replies: 3
- Views: 859
Re: Possible to turn Fc off?
The settings are a bit confusing tbh.
If I set Shared Fc to none but leave Split Fc unchecked, do I have a Shared Fc or not?
- Mon Dec 12, 2022 9:46 am
- Forum: Training Discussion
- Topic: Possible to turn Fc off?
- Replies: 3
- Views: 859
Possible to turn Fc off?
Is it possible to only have Gblock as an Fc and turn the regular Fc off?
If Shared Fc is set to None a Split Fc is created by default I noticed.
- Wed Dec 07, 2022 11:02 am
- Forum: Training Discussion
- Topic: Filtersize
- Replies: 1
- Views: 859
Filtersize
- Fri Dec 02, 2022 2:50 pm
- Forum: Training Discussion
- Topic: output size vs encoder input
- Replies: 1
- Views: 1398
output size vs encoder input
Does it makes sense to have a higher output size then the input layer of the encoder?
Like when I set output size to 1024 but scale the fs_original encoder to 25 (512), is the output actually gonna be 1024?
Or is it in essence training on 512 and upscaling it to 1024 with no extra detail.
- Wed Nov 30, 2022 2:19 pm
- Forum: Training Discussion
- Topic: Phaze-A, 2080Ti
- Replies: 9
- Views: 3002
Re: Phaze-A, 2080Ti
I just started running dny 1024 on 48gb with Full fc, Split fc, Split Gblock and Split Decoders at bs 12.
Little stunned myself tbh.
- Wed Nov 23, 2022 1:55 pm
- Forum: Training Discussion
- Topic: [Guide] Introducing - Phaze-A
- Replies: 89
- Views: 192336
Re: [Guide] Introducing - Phaze-A
- Tue Nov 22, 2022 12:50 pm
- Forum: Training Support
- Topic: Are Extracted faces downsized to match output Size?
- Replies: 5
- Views: 1976
Re: Are Extracted faces downsized to match output Size?
Interesting.
Besides output size, does the max input resolution of the encoder also have an effect on the resizing?
I see efficientnet_v2 had a max input of 480px.
So I assume the input to the encoder is resized to 480px if I feed it higher resolution faces.
Even if I have an output size of 512.
- Tue Nov 22, 2022 12:10 pm
- Forum: Training Support
- Topic: Are Extracted faces downsized to match output Size?
- Replies: 5
- Views: 1976
Re: Are Extracted faces downsized to match output Size?
- Tue Nov 22, 2022 11:01 am
- Forum: Training Support
- Topic: Are Extracted faces downsized to match output Size?
- Replies: 5
- Views: 1976
Are Extracted faces downsized to match output Size?
I ask because this is the case in DFL.
- Mon Nov 21, 2022 9:57 am
- Forum: Training Discussion
- Topic: Convert in training settings
- Replies: 1
- Views: 946
Convert in training settings
Can someone explain why there is the option to adjust the convert batchsize in the global training settings?
Has this to do with the convert that is showing in the preview?
- Sat Nov 19, 2022 9:52 am
- Forum: General Discussion
- Topic: Where are the biases?
- Replies: 3
- Views: 1668
Re: Where are the biases?
I see. Thanks for clearing that up.
Then, just to see if I understand the NN correctly;
Is the first layer of nodes in the encoder the amount of pixels of the image times 3? (for each rgb channel)
So that each node contains an r, g or b value of a single pixel?
- Wed Nov 16, 2022 3:31 pm
- Forum: General Discussion
- Topic: Where are the biases?
- Replies: 3
- Views: 1668
Where are the biases?
- Mon Nov 07, 2022 7:22 pm
- Forum: Training Support
- Topic: Model settings not updated after training swap
- Replies: 3
- Views: 1005
Re: Model settings not updated after training swap
Yes, I checked the state.json file.
But they are not the same as in the Training settings in the GUI.
I guess I should have saved them as a preset upon creation.
- Sat Nov 05, 2022 2:47 pm
- Forum: Training Support
- Topic: Model settings not updated after training swap
- Replies: 3
- Views: 1005