Hierarchical Multi-Scale Attention for Semantic Segmentation

Tags:   segmentation,cv

Attention-based semantic segmentation model


Product Description

Installation

* You can use ./Dockerfile to build an image.

Download Weights

  • Create a directory where you can keep large files. Ideally, not in this directory.

    > mkdir <large_asset_dir>

    Download/Prepare Data

    Running the code

    Run inference on Cityscapes

    Dry run:

    This will just print out the command but not run. It's a good way to inspect the commandline.

    Real run:

    Run inference on Mapillary

    Dump images for Cityscapes

    This will dump network output and composited images from running evaluation with the Cityscapes validation set.

    Run inference and dump images on a folder of images

    You should end up seeing images that look like the following:

    alt text

    Train a model

    Train cityscapes, using HRNet + OCR + multi-scale attention with fine data and mapillary-pretrained model

    The first time this command is run, a centroid file has to be built for the dataset. It'll take about 10 minutes. The centroid file is used during training to know how to sample from the dataset in a class-uniform way.

    Train SOTA default train-val split



Contact Us

Interested? Leave us a message by clicking the button below and our team will contact you soon to configure your system.

By: Xpress AI

Published: 2021-10-22