# High-precision semantic segmentation

UPerNet semantic segmentation model based on ConvNeXt-XLarge encoder, suitable for high-precision image segmentation tasks

A PyTorch-based semantic segmentation model that supports various encoder architectures, suitable for image segmentation tasks.

A PyTorch-based Unet image segmentation model supporting various encoder architectures, suitable for semantic segmentation tasks.

A PyTorch-based semantic segmentation model supporting various encoder architectures, suitable for image segmentation tasks.

PyTorch-based Unet image segmentation model supporting multiple encoder architectures and pre-trained weights

This model is an image segmentation model based on NVIDIA's MIT-B5 architecture, fine-tuned on the IDD 20K semantic segmentation dataset, suitable for road scene understanding tasks.

PyTorch-based semantic segmentation model supporting multiple encoder architectures

FPN-based image segmentation model with ResNet34 encoder, optimized for GID dataset

SegFormer is an efficient semantic segmentation model based on Transformer, with the b0 version being its lightweight implementation.

This is a Dense Prediction Transformer (DPT) model fine-tuned on the ADE20k dataset for semantic segmentation tasks.