AIbase
EN
Home
M6xl7qv
M

M6xl7qv

Developed by Diamantis99
PyTorch-based Unet image segmentation model supporting multiple encoder architectures and pre-trained weights
Image Segmentation
Safetensors
Open Source License:MIT#High-precision semantic segmentation#ResNet152 encoder#Medical image processing
Downloads 52
Release Time : 4/9/2025

Model Overview

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

Model Features

Flexible encoder selection
Supports multiple encoder architectures (e.g., ResNet152) and pre-trained weights (e.g., ImageNet)
Configurable decoder
Customizable decoder parameters including channel count, batch normalization, attention mechanisms, etc.
High performance
Achieves 98.89% IoU on the IPD dataset

Model Capabilities

Image segmentation
Semantic segmentation
Medical image analysis
Satellite image parsing

Use Cases

Medical imaging
Organ segmentation
Used for organ identification and segmentation in CT/MRI scans
High-precision segmentation results with 98.89% IoU
Remote sensing
Land cover classification
Identification and segmentation of different land types in satellite images
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase