Comments (14)
@visonpon I used the model of MIAEF128, output the images having the mask. Do you solve the problem?
from deepfacelab.
@shliang0603 upload your workspace to google drive, provide link, we will check
from deepfacelab.
@iperov Hi, I have uploaded my workspace to google driver. Can you give me some advice ?
from deepfacelab.
give me link to download
from deepfacelab.
@iperov Sorry,I forgot it. workspace link is https://drive.google.com/open?id=1VBn8okCp--HngOK2AuN2lAgCSYmcxF_y
from deepfacelab.
@shliang0603 are you training with jpg images ?
from deepfacelab.
@shliang0603 I am checking your workspace now...
from deepfacelab.
@shliang0603 I converted your video without any problems https://youtu.be/6M9MJiIaANo
First, there was no extracted dst faces in data_dst folder. So I did new extract from data_dst.mkv via DLIB extractor.
Then I used this convert options:
hist match,
masked hist match
erode 30
blur 60
from deepfacelab.
Thanks for your answering. I saw the converted video, it's very good. Then I convert it again according to your requirements, but there are still problem.
In my workspace dictionary have existed extracting images in worksapce/data_dst/aligned
In my worklspace/data_dst/merged dir, Many composite images have shadows. Can you help me to check what the problem is
from deepfacelab.
Enter digit when choose mode, 1 or 2 , 3 , 4.
Also I have no such artefacts at any modes with your workspace.
May be problem in linux :( I have no linux to support it.
from deepfacelab.
@iperov Thanks for your again. I run the MIAEF128 in linux server (2 GPU : 1080Ti). My windows gpu is GTX1050Ti, it can't run the MIAEF128 model. Do you run MIAEF128 model in windows ?
from deepfacelab.
my 6GB run miaef128 fine.
from deepfacelab.
Hi, @shliang0603 sorry i haven't find a solution for this confused question
from deepfacelab.
this bug is only linux specific. You can do minimal reproduce.
from deepfacelab.
Related Issues (20)
- error when extracting deepfake files zip after downloading
- Can't parse "center" error immediately upon starting training
- Head Replace - Crop size for face extraction
- Extract xseg masks?
- Problems Relative to installation of "DeepFaceLab"
- The problem of face recognition in lateral and lower projections
- traceback(most recent call last) HOT 1
- .
- Test
- Training speed.
- Training speed
- Eye and mouth priority bad after 144k
- ask help for the model file
- XSeg training stops after loading all samples (no errors)
- not working on AMD GPU
- Merger Issues All of a Sudden?!
- Merger Issues All of a Sudden?!
- Don't work bat file HOT 1
- it no longer will extract face set data even for the default face sets
- Error: OOM when allocating tensor of shape PLEASE HELP!
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepfacelab.