All Projects → gengyanlei → segmentation_pytorch

gengyanlei / segmentation_pytorch

Licence: other
semantic segmentation pytorch 语义分割

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to segmentation pytorch

Segmentation models.pytorch
Segmentation models with pretrained backbones. PyTorch.
Stars: ✭ 4,584 (+6448.57%)
Mutual labels:  unet, pspnet, deeplab-v3-plus
Segmentation models
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
Stars: ✭ 3,575 (+5007.14%)
Mutual labels:  unet, pspnet
TensorFlow-Advanced-Segmentation-Models
A Python Library for High-Level Semantic Segmentation Models based on TensorFlow and Keras with pretrained backbones.
Stars: ✭ 64 (-8.57%)
Mutual labels:  unet, pspnet
image-segmentation
Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available
Stars: ✭ 62 (-11.43%)
Mutual labels:  unet, pspnet
DE resnet unet hyb
Depth estimation from RGB images using fully convolutional neural networks.
Stars: ✭ 40 (-42.86%)
Mutual labels:  unet
unet pytorch
Pytorch implementation of UNet for converting aerial satellite images into google maps kinda images.
Stars: ✭ 27 (-61.43%)
Mutual labels:  unet
edge2view
This is a pix2pix demo that learns from edge and translates this into view. A interactive application is also provided that translates edge to view.
Stars: ✭ 22 (-68.57%)
Mutual labels:  hed
iconcolor
Automatic icon colorization using deep convolutional neural networks. "Towards Icon Design Using Machine Learning." In Stanford CS229, Fall 2017.
Stars: ✭ 35 (-50%)
Mutual labels:  unet
ResUNetPlusPlus
Official code for ResUNetplusplus for medical image segmentation (TensorFlow implementation) (IEEE ISM)
Stars: ✭ 69 (-1.43%)
Mutual labels:  unet
Railroad and Obstacle detection
This program detect and identify obstacle on railway. If program detect some obstacle that train must stop, program gives you warning sign. This program Also estimate riskiness of obstacle how it is negligible or not. We provide many models to you to detect railways and obstacles.
Stars: ✭ 14 (-80%)
Mutual labels:  unet
CFUN
Combining Faster R-CNN and U-net for efficient medical image segmentation
Stars: ✭ 109 (+55.71%)
Mutual labels:  unet
onnx tensorrt project
Support Yolov5(4.0)/Yolov5(5.0)/YoloR/YoloX/Yolov4/Yolov3/CenterNet/CenterFace/RetinaFace/Classify/Unet. use darknet/libtorch/pytorch/mxnet to onnx to tensorrt
Stars: ✭ 145 (+107.14%)
Mutual labels:  unet
DDUnet-Modified-Unet-for-WMH-with-Dense-Dilate
WMH segmentaion with unet, dilated_unet, and with ideas from denseNet
Stars: ✭ 23 (-67.14%)
Mutual labels:  unet
satellite-Image-Semantic-Segmentation-Unet-Tensorflow-keras
Collection of different Unet Variant suchas VggUnet, ResUnet, DenseUnet, Unet. AttUnet, MobileNetUnet, NestedUNet, R2AttUNet, R2UNet, SEUnet, scSEUnet, Unet_Xception_ResNetBlock
Stars: ✭ 43 (-38.57%)
Mutual labels:  unet
uformer-pytorch
Implementation of Uformer, Attention-based Unet, in Pytorch
Stars: ✭ 54 (-22.86%)
Mutual labels:  unet
semantic-segmentation-tensorflow
Semantic segmentation task for ADE20k & cityscapse dataset, based on several models.
Stars: ✭ 84 (+20%)
Mutual labels:  pspnet
pytorch-Deep-Steganography
core code for High-Capacity Convolutional Video Steganography with Temporal Residual Modeling
Stars: ✭ 31 (-55.71%)
Mutual labels:  unet
unet-pytorch
No description or website provided.
Stars: ✭ 18 (-74.29%)
Mutual labels:  unet
Semantic-Segmentation-PSPNet
PSPNet in tensorflow
Stars: ✭ 19 (-72.86%)
Mutual labels:  pspnet
Depth estimation
Deep learning model to estimate the depth of image.
Stars: ✭ 62 (-11.43%)
Mutual labels:  unet

Semantic Segmentation Pytorch

    author is leilei
    Restart this project from 2017-10-01 
    
    Now the 1.alpha.0 version has been basically completed, to be tested.
    TODO
    Add distributed and optimize code.

Environment

    python: 3.6+
    ubuntu16.04 or 18.04
    pytorch 1.6 (cuda10.2 docker)
    tensorboard 2.0
    scikit-learn 0.24.1

Note

  • If a black border is introduced, it will be regarded as one type, and the default is 0 !
  • label value is [1, N], 0 is black border class !
  • Not supporting distributed(NCCL), just support DataParallel.

Getting Started

Demo

Evaluation index

  • Just see metrics.py
  • Support acc, mean_precision, mean_recall, mean_iou

Support Network

Data Aug

support 
    random zoom-in/out, random noise,
    random blur, random color-jitter(brightness-contrast-saturation-hue)
    random affine, random rotate, random flip

Others

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].