Comments (5)
Thank you very much! I think this pretrained model of celebA (https://github.com/FacePerceiver/facer/releases/download/models-v1/face_parsing.farl.celebm.main_ema_181500_jit.pt) is good.
Thanks. It works for me.
I just change the url of pretrain_settings in file '~/anaconda3/envs/fran/lib/python3.9/site-packages/facer/face_parsing/farl.py', line 14. like below
pretrain_settings = {
'lapa/448': {
'url': [
# original
# 'https://github.com/FacePerceiver/facer/releases/download/models-v1/face_parsing.farl.lapa.main_ema_136500_jit191.pt',
'https://github.com/FacePerceiver/facer/releases/download/models-v1/face_parsing.farl.celebm.main_ema_181500_jit.pt',
],
'matrix_src_tag': 'points',
'get_matrix_fn': functools.partial(get_face_align_matrix,
target_shape=(448, 448), target_face_scale=1.0),
'get_grid_fn': functools.partial(make_tanh_warp_grid,
warp_factor=0.8, warped_shape=(448, 448)),
'get_inv_grid_fn': functools.partial(make_inverted_tanh_warp_grid,
warp_factor=0.8, warped_shape=(448, 448)),
'label_names': ['background', 'face', 'rb', 'lb', 're',
'le', 'nose', 'ulip', 'imouth', 'llip', 'hair']
}
}
then i got the face and neck mask.
from facer.
Why there are not 19 segmentation classes with celebA_HQ model? And there are less than 12 segmentation classes for the provided model in facer?
from facer.
The CelebAMaskHQ is not yet ready to use. Please refer to #8 (comment)
from facer.
Thank you very much! I think this pretrained model of celebA (https://github.com/FacePerceiver/facer/releases/download/models-v1/face_parsing.farl.celebm.main_ema_181500_jit.pt) is good.
from facer.
Hi, celebm face parsing model is available , try it out here
from facer.
Related Issues (20)
- How to color ears using "farl/lapa/448" model?
- Warning triggered whenever I'm using the forward pass the second time HOT 1
- The predicted semantic mask has a slight offset. HOT 2
- How to get whole face parsing network structure
- How to get the face parsing result for the whole input image? HOT 1
- can you provide 'farl/celebm/448' face parsing jit model for pytorch 1.9.1?
- Stable diffusion webui extension
- Fine Tuning the model on personal dataset HOT 1
- timm missing from requirements.txt
- Questions about what labels mean HOT 1
- gpu memory and latency time HOT 3
- Regarding the occlusion problem of glasses and left and right eyes in faceparsing results
- What are indices of upper lip and lower lip in output?
- Instructions on coverting to ONNX HOT 1
- Keyerror HOT 1
- How to fine tune face attribute recognition on my own dataset?
- A bug happened when I use face parser to calculate loss HOT 2
- Incomplete segmentation results of Celebm model inference faceparsing HOT 1
- lazy wrapper should be called at most once
- Some questions about faceparsing
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from facer.