Semantic image segmentation is the task of classifying each pixel in an image from a predefined set of classes.

In this tutorial, you will:

• Perform inference with 10 well-known semantic segmentors
• Fine tune semantic segmentors on a custom dataset
• Design and train your own semantic segmentation model

This work is based on MMSegmentation: OpenMMLab segmentation toolbox and benchmark.

Here is how to load a pretrained model, perfrom inference and vizualize the results.

model = init_segmentor(config, checkpoint, device='cuda:0')
result = inference_segmentor(model, img)
model.show_result(img, result, out_file='result.jpg', win_name=m_name)

Segmentor	Result
FCN
U-net
PSPNet
DeepLabV3
UPerNet
CCNet
FastFCN
SETR
Segmenter
SegFormer

• Select a semantic segmentation model: SEgmentation TRansformer SETR
• Add a new dataset class: Scene Understanding Datasets
• Create a config file.
• Conduct training and evaluation.

• Select a semantic segmentation model: UPerNet Unified Perceptual Parsing for Scene Understanding
• Replabe the ResNet backbone with a new one: ConvNeXt A ConvNet for the 2020s
• Config the heads.
• Add a new dataset class: Scene Understanding Datasets
• Conduct training and evaluation.

Regards!