Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
-
Updated
Aug 21, 2024 - Python
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
Smoke detection via semantic segmentation using Baseline U-Net model & LinkNet and image augmentation
The 4th place and the fastest solution of the Lyft Perception Challenge (Image semantic segmentation with PyTorch)
Lots of semantic image segmentation implementations in Tensorflow/Keras
Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available
Minecraft Plugin for Connect, allows tunneled player connections from Connect Network to join Spigot/Paper server and Velocity/BungeeCord proxy, even in online mode!
Pytorch Convolution neural network for semantic segmentation
Rasa breast cancer radiology AI chatbot to help doctor segment lesions using Unity, Keras Attention UNet, LinkNet, etc
All my Python code used for the Kaggle HuBMAP Semantic Segmentation competition
Detecção de linhas de plantio em plantações de cana-de-açúcar utilizando deep learning
Brain MRI segmentation using segmentation models
Image Segmentation of Brain Tumors using Convolutional Neural Networks. Implemented U-Net and LinkNet architectures.
Very high resolution image pre-processing and semantic segmentation (Potsdam Dataset)
Flask app to segment bio-medical images.
one-stage and two-stage detectors and segmentation-based detectors
Segmentation models with pretrained backbones. PyTorch. for Google Colab cell motility segmentation example.
An initial phase segmentation using LinkNet on the skin lesion dataset managed by VISION AND IMAGE PROCESSING LAB, University of Waterloo. Public dataset on Kaggle at https://www.kaggle.com/datasets/mahmudulhasantasin/university-of-waterloo-skin-cancer-db-80-10-10/.
Road Segmentation Using Aerial Images
Add a description, image, and links to the linknet topic page so that developers can more easily learn about it.
To associate your repository with the linknet topic, visit your repo's landing page and select "manage topics."