pochih / Fcn Pytorch
π Easiest Fully Convolutional Networks
Stars: β 278
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Fcn Pytorch
Cascaded Fcn
Source code for the MICCAI 2016 Paper "Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworks and 3D Conditional Random Fields"
Stars: β 296 (+6.47%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
3dunet abdomen cascade
Stars: β 91 (-67.27%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
Pytorch Unet
Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation
Stars: β 470 (+69.06%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
Pytorch Semseg
Semantic Segmentation Architectures Implemented in PyTorch
Stars: β 3,180 (+1043.88%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
Fashion-Clothing-Parsing
FCN, U-Net models implementation in TensorFlow for fashion clothing parsing
Stars: β 29 (-89.57%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
Vnet.pytorch
A PyTorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
Stars: β 506 (+82.01%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
Keras Icnet
Keras implementation of Real-Time Semantic Segmentation on High-Resolution Images
Stars: β 85 (-69.42%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
Segmentation
Tensorflow implementation : U-net and FCN with global convolution
Stars: β 101 (-63.67%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
Pytorch Semantic Segmentation
PyTorch for Semantic Segmentation
Stars: β 1,580 (+468.35%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
Semanticsegpapercollection
Stars: β 102 (-63.31%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
semantic segmentation
Semantically segment the road in the given image.
Stars: β 91 (-67.27%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
atomai
Deep and Machine Learning for Microscopy
Stars: β 77 (-72.3%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
FCNN-example
This is a fully convolutional neural net exercise to detect houses from aerial images.
Stars: β 28 (-89.93%)
Mutual labels: semantic-segmentation, fully-convolutional-networks
label-fusion
Volumetric Fusion of Multiple Semantic Labels and Masks
Stars: β 18 (-93.53%)
Mutual labels: semantic-segmentation
Torchsat
π₯TorchSat π is an open-source deep learning framework for satellite imagery analysis based on PyTorch.
Stars: β 261 (-6.12%)
Mutual labels: semantic-segmentation
SlideSeg
A Python module that produces image patches and annotation masks from whole slide images for deep learning in digital pathology.
Stars: β 71 (-74.46%)
Mutual labels: semantic-segmentation
pointnet2 semantic
A pointnet++ fork, with focus on semantic segmentation of differents datasets
Stars: β 69 (-75.18%)
Mutual labels: semantic-segmentation
Semantic Kitti Api
SemanticKITTI API for visualizing dataset, processing data, and evaluating results.
Stars: β 272 (-2.16%)
Mutual labels: semantic-segmentation
Pytorch Deeplab
DeepLab-ResNet rebuilt in Pytorch
Stars: β 254 (-8.63%)
Mutual labels: semantic-segmentation
DDUnet-Modified-Unet-for-WMH-with-Dense-Dilate
WMH segmentaion with unet, dilated_unet, and with ideas from denseNet
Stars: β 23 (-91.73%)
Mutual labels: semantic-segmentation
π The easiest implementation of fully convolutional networks
-
Task: semantic segmentation, it's a very important task for automated driving
-
The model is based on CVPR '15 best paper honorable mentioned Fully Convolutional Networks for Semantic Segmentation
Results
Trials
Training Procedures
Performance
I train with two popular benchmark dataset: CamVid and Cityscapes
dataset | n_class | pixel accuracy |
---|---|---|
Cityscapes | 20 | 96% |
CamVid | 32 | 93% |
Training
Install packages
pip3 install -r requirements.txt
and download pytorch 0.2.0 from pytorch.org
and download CamVid dataset (recommended) or Cityscapes dataset
Run the code
- default dataset is CamVid
create a directory named "CamVid", and put data into it, then run python codes:
python3 python/CamVid_utils.py
python3 python/train.py CamVid
- or train with CityScapes
create a directory named "CityScapes", and put data into it, then run python codes:
python3 python/CityScapes_utils.py
python3 python/train.py CityScapes
Author
Po-Chih Huang / @pochih
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].