huangyangyu / adnet Goto Github PK
View Code? Open in Web Editor NEWADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment [Official, ICCV 2021]
Home Page: https://arxiv.org/pdf/2109.05721.pdf
License: MIT License
ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment [Official, ICCV 2021]
Home Page: https://arxiv.org/pdf/2109.05721.pdf
License: MIT License
First, Thanks for your great work!
I found such an error after i download wflw-model from this link
loss_lambda: 2.0
device_id: -1
device: cpu
use_gpu: False
Traceback (most recent call last):
File "evaluate.py", line 266, in <module>
mode=args.mode)
File "evaluate.py", line 214, in evaluate
alignment = Alignment(config_name, work_dir, model_path, dl_framework, device_ids)
File "evaluate.py", line 117, in __init__
net.load_state_dict(checkpoint["net"])
File "/home/rzhang/anaconda3/envs/python37/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1224, in load_state_dict
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for StackedHGNetV1:
Unexpected key(s) in state_dict: "pre.2.1.filt", "hgs.0.pool1.1.filt", "hgs.0.low2.pool1.1.filt", "hgs.0.low2.low2.pool1.1.filt", "hgs.0.low2.low2.low2.pool1.1.filt", "hgs.1.pool1.1.filt", "hgs.1.low2.pool1.1.filt", "hgs.1.low2.low2.pool1.1.filt", "hgs.1.low2.low2.low2.pool1.1.filt", "hgs.2.pool1.1.filt", "hgs.2.low2.pool1.1.filt", "hgs.2.low2.low2.pool1.1.filt", "hgs.2.low2.low2.low2.pool1.1.filt", "hgs.3.pool1.1.filt", "hgs.3.low2.pool1.1.filt", "hgs.3.low2.low2.pool1.1.filt", "hgs.3.low2.low2.low2.pool1.1.filt".
my command is
python evaluate.py --mode=nme --config_name=alignment --model_path=model/wflw/train.pkl --metadata_path=data/WFLW/WFLW_annotations --image_dir=data/WFLW/WFLW_images --device_ids=-1
and i changed the code self.data_definition = "WFLW"
in alignment.py
@huangyangyu could you help me to fix this bug?
Hi! Thanks for your work!
I would like to run the pretrained model on a single image without downloading any datasets to get the landmarks prediction. Unfortunately I did not find a way how to do that in README. Could you please describe how to do that?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.