O

Or9ksv4

Developed by Diamantis99
PyTorch-based Unet image segmentation model supporting various encoder architectures and pre-trained weights
Downloads 78
Release Time : 4/9/2025

Model Overview

This is a PyTorch-implemented Unet architecture image segmentation model primarily used for semantic segmentation tasks. The model supports various encoder architectures (e.g., ResNet152) and pre-trained weights, with flexible decoder parameter configuration.

Model Features

Multiple encoder support
Supports mainstream encoder architectures like ResNet and can load ImageNet pre-trained weights
Flexible decoder configuration
Customizable decoder parameters including channel numbers, batch normalization, and attention mechanisms
High-performance segmentation
Achieves 94.5% IoU on the IPD dataset

Model Capabilities

Image semantic segmentation
Medical image analysis
Remote sensing image processing

Use Cases

Medical imaging
Organ segmentation
Used for organ identification and segmentation in CT/MRI images
High-precision segmentation results
Remote sensing
Land cover classification
Land use classification in satellite images
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase