Faceswap Forum

artisan

Unfortunately this falls down at the last steps, as the data is reshuffled every epoch. However, it may just be as simple as re-feeding the worst performing batch(es) per epoch /x iterations. Although, that feels slightly less refined than tracking which individual images are contributing most to l...

artisan

Do batches always contain the same group of face images? I'm making the mistake of brainstorming without intricate knowledge of the software under the hood. A caveat born of enthusiasm—and I know how annoying that can be. :) Recording the following so my hours of having a confused look while browsin...

artisan

Ayorex wrote: ↑Wed Sep 14, 2022 8:29 pm
setup in windows 10
installed python : 3.8 32 bit

Ah. In that case, confusing indeed.

artisan

It's complaining that you installed the 32-bit version.

Try using the Windows installer for a 64-bit version?

artisan

I'm not sure if the deep learning algorithm already has what I will describe, or alternative algos that would have the same effect, or if this is simply a bad idea. Sharing for discussion. Precursor: I notice while training that in the preview, while some face swaps are doing fantastic, among them a...

artisan

Is there any such thing as a variable input (face size) model?

I know some models have configurable input sizes. However, is there any model that would handle different sized inputs (without rescaling to a fixed input)?

artisan

Very cool. Definitely helps understand the distribution of original face sizes! I didn't even realize that the original face size data was maintained once extracting to a specific size.

artisan

I just changed my project folder configuration.

Model+
--> Model

Model+ keeps the main directory tidy. By saving the model into "Model", all the snapshots falls inside of Model+. That works well enough for me.

artisan

I don't see the option to output detected faces at whatever size is detected (non-uniform output).

But I suppose running extraction multiple times with a high size setting, and changing minimum size from high to low to count how many are output each time. Not every elegant.

artisan

The resolution of the source video matters, of course. However, where the subject (beholder of a human face) is positioned within the video frame determines the actual resolution of the face image extracted, prior to saving at the specified output size . Movie clips with high quality close ups will ...

artisan

Re: https://forum.faceswap.dev/viewtopic.php?p=5888#p5888 I'm adding some info I found on the topic that is likely the best answer to my question: The input resolution to the model is separate from the size of the extracted faces Try not to think of the extracted faces as the training images, rather...

artisan

Per the extraction guide: Size: This is the size of the image holding the extracted face. Generally 512px will be fine for most models. This is the size of the full head extracted image. When training a 'sub-crop' of this image will be used depending on the centering you have chosen. For 'face' cent...

artisan

Is the default for where model snapshots are saved, at (a) the same level as the directory containing the model, as opposed to (b) within the model directory itself? My thought is that the snapshots might be best stored within a directory called "Snapshots" with the directory specified for...

artisan

Sounds like you're making some progress. I was hoping the M1 would be able to run FS. TBD.

Faceswap Forum

Search found 14 matches

Re: Dynamic algorithmic input source trimming while training

Re: Dynamic algorithmic input source trimming while training

Re: Faceswap installation not working on my PC.

Re: Faceswap installation not working on my PC.

Dynamic algorithmic input source trimming while training

Re: Matching extraction "size" configuration with selected model type

Re: Extraction Analysis Tool (for optimal output size based on source videos)

Re: Model Snapshots saved at same directory level as model directory?

Re: Extraction Analysis Tool (for optimal output size based on source videos)

Extraction Analysis Tool (for optimal output size based on source videos)

Re: Model Snapshots saved at same directory level as model directory?

Matching extraction "size" configuration with selected model type

Model Snapshots saved at same directory level as model directory?

Re: Working on Faceswap for M1 Mac