ShawDa / Unet Rgb
unet for rgb images semantic segmentation
Stars: ✭ 44
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Unet Rgb
Labelme
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Stars: ✭ 7,742 (+17495.45%)
Mutual labels: semantic-segmentation
3d Semantic Segmentation For Scene Parsing
A new approach for the real time 3D semantic segmentation based on feature abstract and deep learning method
Stars: ✭ 13 (-70.45%)
Mutual labels: semantic-segmentation
Pytorch Auto Drive
Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, SAD, PRNet, RESA, LSTR...) based on PyTorch 1.6 with mixed precision training
Stars: ✭ 32 (-27.27%)
Mutual labels: semantic-segmentation
Deeplab Pytorch
PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC
Stars: ✭ 787 (+1688.64%)
Mutual labels: semantic-segmentation
Face Parsing.pytorch
Using modified BiSeNet for face parsing in PyTorch
Stars: ✭ 838 (+1804.55%)
Mutual labels: semantic-segmentation
Pytorch 3dunet
3D U-Net model for volumetric semantic segmentation written in pytorch
Stars: ✭ 765 (+1638.64%)
Mutual labels: semantic-segmentation
Seg Mentor
TFslim based semantic segmentation models, modular&extensible boutique design
Stars: ✭ 43 (-2.27%)
Mutual labels: semantic-segmentation
Kaggle Carvana Image Masking Challenge
Top 15% ranked solution to the Carvana Image Masking Challenge on Kaggle
Stars: ✭ 13 (-70.45%)
Mutual labels: semantic-segmentation
Deeplabv3 Plus
Tensorflow 2.3.0 implementation of DeepLabV3-Plus
Stars: ✭ 32 (-27.27%)
Mutual labels: semantic-segmentation
Semantic Segmentation Editor
Web labeling tool for bitmap images and point clouds
Stars: ✭ 894 (+1931.82%)
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 (+1984.09%)
Mutual labels: semantic-segmentation
Enet Sad pytorch
Pytorch implementation of "Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)"
Stars: ✭ 30 (-31.82%)
Mutual labels: semantic-segmentation
Sota Point Cloud
🔥Deep Learning for 3D Point Clouds (IEEE TPAMI, 2020)
Stars: ✭ 778 (+1668.18%)
Mutual labels: semantic-segmentation
Recurrent Scene Parsing With Perspective Understanding In The Loop
parsing scene images with understanding geometric perspective in the loop
Stars: ✭ 32 (-27.27%)
Mutual labels: semantic-segmentation
Deeplab v3
Tensorflow Implementation of the Semantic Segmentation DeepLab_V3 CNN
Stars: ✭ 768 (+1645.45%)
Mutual labels: semantic-segmentation
Vocal Melody Extraction
Source code for "Vocal melody extraction with semantic segmentation and audio-symbolic domain transfer learning".
Stars: ✭ 44 (+0%)
Mutual labels: semantic-segmentation
Chainer Segnet
SegNet implementation & experiments in Chainer
Stars: ✭ 42 (-4.55%)
Mutual labels: semantic-segmentation
Midv 500 Models
Model for document segmentation trained on the midv-500-models dataset.
Stars: ✭ 31 (-29.55%)
Mutual labels: semantic-segmentation
unet-rgb
Keras(TF backend) implementation of unet for RGB pictures.
Overview
Requirement
- OpenCV
- Python 2.7
- Tensorflow-gpu
- Keras
Data
You can download all data here:https://pan.baidu.com/s/1WqmR-9jodyyUnLRCK6pcVw password: 533h
CamVid Data:https://github.com/preddy5/segnet/tree/master/CamVid
Howtouse
- extract downloaded data to corresponding directories
- run
python data.pyto generate 3 .npy files or you can download them to npydata - run
python unet.pyto train, you can change hyperparameters on your own situation - run
python test2mask2pic.pyto get test results(pictures)
Results
After training about 30 epochs, loss goes to about 0.005.The results seems OK! But the edges look a bit rough. I think that is Unet's own limitation.
Camvid
- run
python data_camvid.py - run
python unet_camvid.py - run
python predict_camvid.py
After 50 epochs training, loss goes to about 4e-04 and acc is 0.9644.
About
Unet is mostly used in medical areas. I used this model for semantic segmentation of satellite remote sensing images in real work and the result is not bad. I think one of the reason is that it's a coarse-grained task like medical image analysis. Of course, enough labeled images are necessary.
Reference
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].