All Projects → lhelontra → squeeze-unet

lhelontra / squeeze-unet

Licence: other
Squeeze-unet Semantic Segmentation for embedded devices

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to squeeze-unet

unet-pytorch
This is the example implementation of UNet model for semantic segmentations
Stars: ✭ 17 (-19.05%)
Mutual labels:  semantic-segmentation, u-net
Fashion-Clothing-Parsing
FCN, U-Net models implementation in TensorFlow for fashion clothing parsing
Stars: ✭ 29 (+38.1%)
Mutual labels:  semantic-segmentation, u-net
Automated-objects-removal-inpainter
Automated object remover Inpainter is a project that combines Semantic segmentation and EdgeConnect architectures with minor changes in order to remove specified object/s from list of 20 objects from all the input photos
Stars: ✭ 88 (+319.05%)
Mutual labels:  semantic-segmentation
Fast-SCNN pytorch
A PyTorch Implementation of Fast-SCNN: Fast Semantic Segmentation Network(PyTorch >= 1.4)
Stars: ✭ 30 (+42.86%)
Mutual labels:  semantic-segmentation
DeepLab-V3
Google DeepLab V3 for Image Semantic Segmentation
Stars: ✭ 103 (+390.48%)
Mutual labels:  semantic-segmentation
Semantic-Segmentation-BiSeNet
Keras BiseNet architecture implementation
Stars: ✭ 55 (+161.9%)
Mutual labels:  semantic-segmentation
SUIM
Semantic Segmentation of Underwater Imagery: Dataset and Benchmark. #IROS2020
Stars: ✭ 53 (+152.38%)
Mutual labels:  semantic-segmentation
PhotographicImageSynthesiswithCascadedRefinementNetworks-Pytorch
Photographic Image Synthesis with Cascaded Refinement Networks - Pytorch Implementation
Stars: ✭ 63 (+200%)
Mutual labels:  semantic-segmentation
BMW-IntelOpenVINO-Segmentation-Inference-API
This is a repository for a semantic segmentation inference API using the OpenVINO toolkit
Stars: ✭ 31 (+47.62%)
Mutual labels:  semantic-segmentation
flexinfer
A flexible Python front-end inference SDK based on TensorRT
Stars: ✭ 83 (+295.24%)
Mutual labels:  semantic-segmentation
super-gradients
Easily train or fine-tune SOTA computer vision models with one open source training library
Stars: ✭ 429 (+1942.86%)
Mutual labels:  semantic-segmentation
PyTorch-Deep-Image-Steganography
A PyTorch implementation of image steganography utilizing deep convolutional neural networks
Stars: ✭ 71 (+238.1%)
Mutual labels:  u-net
temporal-depth-segmentation
Source code (train/test) accompanying the paper entitled "Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach" in CVPR 2019 (https://arxiv.org/abs/1903.10764).
Stars: ✭ 20 (-4.76%)
Mutual labels:  semantic-segmentation
wasr network
WaSR Segmentation Network for Unmanned Surface Vehicles v0.5
Stars: ✭ 32 (+52.38%)
Mutual labels:  semantic-segmentation
MobileUNET
U-NET Semantic Segmentation model for Mobile
Stars: ✭ 39 (+85.71%)
Mutual labels:  semantic-segmentation
kitti deeplab
Inference script and frozen inference graph with fine tuned weights for semantic segmentation on images from the KITTI dataset.
Stars: ✭ 26 (+23.81%)
Mutual labels:  semantic-segmentation
DeepWay.v2
Autonomous navigation for blind people
Stars: ✭ 65 (+209.52%)
Mutual labels:  u-net
deeplabv3plus-keras
deeplabv3plus (Google's new algorithm for semantic segmentation) in keras:Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Stars: ✭ 67 (+219.05%)
Mutual labels:  semantic-segmentation
CVPR2021 PLOP
Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation
Stars: ✭ 102 (+385.71%)
Mutual labels:  semantic-segmentation
adversarial-attacks
Code for our CVPR 2018 paper, "On the Robustness of Semantic Segmentation Models to Adversarial Attacks"
Stars: ✭ 90 (+328.57%)
Mutual labels:  semantic-segmentation

Squeeze-unet Semantic Segmentation for embedded devices

The model is inspired by Squeezenet and U-Net.

camvid, is used as a Dataset.

Example of predicted image.

Requirements

  • Keras 2

About network

As a typical U-Net architecture, it has encoder and decoder parts, which consist of fire modules proposed by squeezenet.

TODO

  • Report speed vs accuracy.
  • link for download camvid dataset converted by cvision.
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].