face-parsing.PyTorch
pix2pixHD
| face-parsing.PyTorch | pix2pixHD | |
|---|---|---|
| 4 | 6 | |
| 2,092 | 6,530 | |
| - | 0.5% | |
| 0.0 | 0.0 | |
| 12 months ago | 11 months ago | |
| Python | Python | |
| MIT License | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
face-parsing.PyTorch
-
How to do Human Head Segmentation from images?
Segmentation of head / body - I'd either use mediapipe pose and make something cleverly cut where I wanted based on the landmarks, or I'd use pytorch face parsing if you want to be very exact. I found both of these fairly easy to get to run.
-
[P] I made FaceShop! Instance segmentation + CGAN for editing faces (badly)
BiSeNet
Uses a mix of instance segmentation (BiSeNet) and conditional GAN, and is heavily inspired by the Pix2PixHD and DeepSIM papers. Will have more details when I wake up!
-
[P] Face make up powerd by deep learning | change color of lips, eyes and eyeglasses
I've developed a demo of human face make-up. The main tech used is face parsing.To get lips, eyes and eyeglasses mask, I perform face parsing based on face-parsing.PyTorch. After that, color changing is done in HSV color space.
pix2pixHD
- How do I run more than 200 epochs in training a Pix2PixHD model?
-
NVIDIA DLSS Now Available in Over 150 Games, Including Dying Light 2 Stay Human, Sifu and Phantasy Star Online 2 New Genesis
Well, maybe not, considering things like pix2pix can generate detail from just solid shapes and colors.
-
Image to hand drawn
Sources: U2Net, ArtLine, Pix2PixHD, APDrawingGAN
-
[P] I made FaceShop! Instance segmentation + CGAN for editing faces (badly)
Pix2PixHD (from DeepSIM)
Uses a mix of instance segmentation (BiSeNet) and conditional GAN, and is heavily inspired by the Pix2PixHD and DeepSIM papers. Will have more details when I wake up!
-
How to access a class object when I use torch.nn.DataParallel()?
I used Pix2PixHD implementation in GitHub if you want to see the full code.
What are some alternatives?
Pytorch-UNet - PyTorch implementation of the U-Net for image semantic segmentation with high quality images
pytorch-CycleGAN-and-pix2pix - Image-to-Image Translation in PyTorch
segmentation_models.pytorch - Segmentation models with pretrained backbones. PyTorch.
awesome-colab-notebooks - Collection of google colaboratory notebooks for fast and easy experiments
mmsegmentation - OpenMMLab Semantic Segmentation Toolbox and Benchmark.
sofgan - [TOG 2022] SofGAN: A Portrait Image Generator with Dynamic Styling
SemanticSegmentation - A framework for training segmentation models in pytorch on labelme annotations with pretrained examples of skin, cat, and pizza topping segmentation
generative-inpainting-pytorch - A PyTorch reimplementation for paper Generative Image Inpainting with Contextual Attention (https://arxiv.org/abs/1801.07892)
deepface - A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
contrastive-unpaired-translation - Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
CelebAMask-HQ - A large-scale face dataset for face parsing, recognition, generation and editing.
CycleGAN - Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.