Faceswap Forum

What was the full command you ran?

You train until you are happy with the previews. You can view the previews with a pop up window by passing the -p flag, or you can write the preview to the faceswap folder with the -w flag and view it there

Ok. This is a really strange bug that we haven't managed to get to the bottom of. I won't go into the details, but this should fix the issue. Please confirm if it does: Go Start > Anaconda Prompt In the command window that opens enter the following: conda activate faceswap pip install plaidml-keras=...

Ok. There is an issue that FFMPEG sometimes just hangs when attempting to get the frame count. There isn't a lot we can do to stop the hang, but I have implemented a timeout, so that this will no longer block Faceswap from running. Please update to the latest code and let me know if this fixes your ...

I'm unlikely to post a video, sorry. I just don't have the time to make it at the moment.

That's too long.... Can I ask, were you extracting from a video? If so, there appears to be an inconsistent bug in one of the libraries we rely on for reading from videos. I am going to see if I can build a workaround.... In the meantime, you can use the Effmpeg tool (Tools tab > Effmpeg) to extract...

Honestly?

I haven't started either of them yet. Your best resources for these currently are USAGE.md in the github repo or the pinned topics in the relevant channels on our Discord Server.

I'm not sure what it is you're asking?

You should be performing the extraction process separately for your "A" and "B" facesets. These shouldn't be merged with each other.

Also, training takes a long time and needs a lot if images. See https://faceswap.dev/forum/app.php/faqpage

We have identified a potential issues on certain batch-sizes.

It still doesn't explain your CPU usage (although, that may be numpy doing multiprocessing in the background).

When we have a bit of time, we are going to review the data augmentation code to see if we can optimize it a bit better.

I can't talk for cloud based options, as I don't use them, but as to your "preview" issue, if you use the -w flag, it will write out a preview to your faceswap folder every save iteration, that you can pull down and check the progress.

Thanks for this.

I am currently having GPU issues, so I will have to wait for some parts to arrive before I can run my tests.

Off the top of my head, these figures seem reasonable though.

Ok. I'm away from my PC at the moment, and don't have the figures on the top of my head. I will double check though and get back to you tomorrow.

I would expect CPU usage. Image augmentation is processor intensive, and it has to do it on 64 (32 x 2) images at a time. This is all done on CPU prior to feeding to the GPU. I would not expect it to use your full CPU... As I said before, I don't know how that would even be possible in the current t...

Ok, you're going to need to excuse me, because I use Linux... but.... Those grabs don't really make sense. Python, by it's nature, is a single-threaded application. You have to jump through quite a lot of hoops to get multi-processing to work (trust me, I have jumped through a lot of those!). For th...

Ok, this is strange.... Extract Can feasibly max CPU as it leverages multi-processing quite heavily. Training really shouldn't.... It spins off 2 processes (one each for data augmentation on each of the sides) and also the main process. If you are using the GUI then that will also use another proces...

In the first instance, try a reboot. This normally means something has gone wrong in Cuda/cuDNN which needs a reboot to fix.

Can you open a new topic and post the crash_report (from your facewap folder) there please.

Also, please mark my post previous as "Answer" (the tick icon)

I'm going to lock this one off as it's solved

Ok, it looks like you have no Conda packages installed..... What I suggest is deleting that environment and then creating a new one and running setup.py. This will install everything correctly for you: In the following code replace <envname> with the name of your faceswap environment. (Most likely &...

It will depend a lot on the model.

The most important thing is quality of data.

Which model are you using?

You should try using the preview tool to set your convert settings prior to convert.

Ok, the most likely thing is a Tensorflow conflict somewhere. Running setup.py should not install a tensorflow version higher than is supported..... system python + conda can conflict.... If you're comfortable setting up a virtual environment in your system python, then removing Conda, installing th...

Faceswap Forum

Search found 2674 matches

Re: How can I tell progress of training

Re: [AMD] AttributeError: '_Settings' object has no attribute 'prohibit_winograd'

Re: Extraction stuck on "Status: Executing - extract.py" in GUI

Re: [Guide] Extraction - A Workflow

Re: Extraction stuck on "Status: Executing - extract.py" in GUI

Re: How is the status of training/convert guide?

Re: why do merge and where to go next

Re: CPU Load is 100% and ~40% GPU

Re: Using Cloud GPU Hardware

Re: CPU Load is 100% and ~40% GPU

Re: CPU Load is 100% and ~40% GPU

Re: CPU Load is 100% and ~40% GPU

Re: CPU Load is 100% and ~40% GPU

Re: CPU Load is 100% and ~40% GPU

Re: Failed to get convolution algorithm : CRASH

Re: the script just quits without any error!

Re: the script just quits without any error!

Re: Converting a Video/Images [Help with blurred faces]

Re: Converting a Video/Images [Help with blurred faces]

Re: the script just quits without any error!