evendrow / face-reconstruction Goto Github PK
View Code? Open in Web Editor NEW[Paper] Repository for “Realistic Face Reconstruction from Deep Embeddings," published in NeurIPS PriML 2021.
[Paper] Repository for “Realistic Face Reconstruction from Deep Embeddings," published in NeurIPS PriML 2021.
Reproduction (Google Colab):
!git clone https://github.com/NVlabs/stylegan2-ada-pytorch.git
!git -C stylegan2-ada-pytorch reset --hard 6f160b3d22b8b178ebe533a50d4d5e63aedba21d
import sys
sys.path.insert(0, './stylegan2-ada-pytorch')
!pip install ninja
!git clone https://github.com/evendrow/face-reconstruction.git
!git -C face-reconstruction reset --hard 794c1a9d7729abbfecf0692138fe643f69bc04b2
!pip install facenet-pytorch==2.5.2
!wget https://nvlabs-fi-cdn.nvidia.com/stylegan2-ada-pytorch/pretrained/ffhq.pkl face-reconstruction/
!python face-reconstruction/main.py --setup
Output:
/usr/local/lib/python3.7/dist-packages/facenet_pytorch/models/utils/detect_face.py:183: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
batch_boxes, batch_points = np.array(batch_boxes), np.array(batch_points)
/usr/local/lib/python3.7/dist-packages/facenet_pytorch/models/mtcnn.py:339: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
boxes = np.array(boxes)
/usr/local/lib/python3.7/dist-packages/facenet_pytorch/models/mtcnn.py:340: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
probs = np.array(probs)
/usr/local/lib/python3.7/dist-packages/facenet_pytorch/models/mtcnn.py:341: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
points = np.array(points)
Appears to be thrown when MTCNN is called:
Line 108 in 794c1a9
from the generation method:
Line 125 in 794c1a9
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.