deeplab-v3-plus

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

DeepLab v3+ model in PyTorch. Support different backbones.

Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)

[CVPR2020] f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation https://arxiv.org/abs/2001.10331

PyTorch implementation for semantic segmentation (DeepLabV3+, UNet, etc.)

LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation

DeepGlobe Land Cover Classification Challenge遥感影像语义分割

DeepLabV3+ implemented in TensorFlow2.0

semantic segmentation pytorch 语义分割

Real-time semantic image segmentation on mobile devices

Pytorch implementation and extension of "DocUnet: Document Image Unwarping via A Stacked U-Net"

图像分割算法deeplab_v3+，基于tensorflow，中文注释，摄像头可用

This is an ongoing re-implementation of DeepLab_v3_plus on pytorch which is trained on VOC2012 and use ResNet101 for backbone.

TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation

deeplabv3plus (Google's new algorithm for semantic segmentation) in keras：Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Using deepLabv3+ to segment humans

DeepLabV3+ with squeeze and excitation network for human image segmentation in TensorFlow 2.5.0

Base on tensorrt version 8.2.4, compare inference speed for different tensorrt api.

Try to implement deeplab v3+ on pytorch according to offical demo.

3クラス(肌、服、髪)のセマンティックセグメンテーションを実施するモデル(A model that performs semantic segmentation of 3 classes(skin, clothes, hair))