zllrunning / Face Parsing.pytorch
Licence: mit
Using modified BiSeNet for face parsing in PyTorch
Stars: ✭ 838
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Face Parsing.pytorch
Cvat
Powerful and efficient Computer Vision Annotation Tool (CVAT)
Stars: ✭ 6,557 (+682.46%)
Mutual labels: semantic-segmentation
Pytorch Segmentation Toolbox
PyTorch Implementations for DeeplabV3 and PSPNet
Stars: ✭ 691 (-17.54%)
Mutual labels: semantic-segmentation
Sota Point Cloud
🔥Deep Learning for 3D Point Clouds (IEEE TPAMI, 2020)
Stars: ✭ 778 (-7.16%)
Mutual labels: semantic-segmentation
Light Weight Refinenet
Light-Weight RefineNet for Real-Time Semantic Segmentation
Stars: ✭ 619 (-26.13%)
Mutual labels: semantic-segmentation
Adaptsegnet
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
Stars: ✭ 654 (-21.96%)
Mutual labels: semantic-segmentation
Gscnn
Gated-Shape CNN for Semantic Segmentation (ICCV 2019)
Stars: ✭ 720 (-14.08%)
Mutual labels: semantic-segmentation
Efficient Segmentation Networks
Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)
Stars: ✭ 579 (-30.91%)
Mutual labels: semantic-segmentation
Efficientdet Pytorch
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
Stars: ✭ 906 (+8.11%)
Mutual labels: semantic-segmentation
Pytorch segmentation
Semantic segmentation models, datasets and losses implemented in PyTorch.
Stars: ✭ 674 (-19.57%)
Mutual labels: semantic-segmentation
Labelme
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Stars: ✭ 7,742 (+823.87%)
Mutual labels: semantic-segmentation
Randla Net
🔥RandLA-Net in Tensorflow (CVPR 2020, Oral)
Stars: ✭ 637 (-23.99%)
Mutual labels: semantic-segmentation
Pytorch 3dunet
3D U-Net model for volumetric semantic segmentation written in pytorch
Stars: ✭ 765 (-8.71%)
Mutual labels: semantic-segmentation
Label Studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Stars: ✭ 7,264 (+766.83%)
Mutual labels: semantic-segmentation
Deeplab Pytorch
PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC
Stars: ✭ 787 (-6.09%)
Mutual labels: semantic-segmentation
Pytorch Deeplab Resnet
DeepLab resnet v2 model in pytorch
Stars: ✭ 584 (-30.31%)
Mutual labels: semantic-segmentation
Lightnet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 698 (-16.71%)
Mutual labels: semantic-segmentation
Medicaldetectiontoolkit
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
Stars: ✭ 917 (+9.43%)
Mutual labels: semantic-segmentation
Semantic Segmentation Editor
Web labeling tool for bitmap images and point clouds
Stars: ✭ 894 (+6.68%)
Mutual labels: semantic-segmentation
Deeplab v3
Tensorflow Implementation of the Semantic Segmentation DeepLab_V3 CNN
Stars: ✭ 768 (-8.35%)
Mutual labels: semantic-segmentation
face-parsing.PyTorch
Contents
Training
-
Prepare training data: -- download CelebAMask-HQ dataset
-- change file path in the
prepropess_data.py
and run
python prepropess_data.py
- Train the model using CelebAMask-HQ dataset: Just run the train script:
$ CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 train.py
If you do not wish to train the model, you can download our pre-trained model and save it in res/cp
.
Demo
- Evaluate the trained model using:
# evaluate using GPU
python test.py
Face makeup using parsing maps
Hair | Lip | |
---|---|---|
Original Input | ||
Color |
References
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].