TF2 Deep FloorPlan Recognition using a Multi-task Network with Room-boundary-Guided Attention. Enable tensorboard, quantization, flask, tflite, docker, github actions and google colab. This repo contains a basic procedure to train and deploy the DNN model suggested by the paper 'Deep Floor Plan Recognition using a Multi-task Network with Room-boundary-Guided Attention'. It rewrites the original codes from zlzeng/DeepFloorplan into newer versions of Tensorflow and Python.
Features
- Docker for API
- Documentation available
- Examples available
- Google Colab
- It rewrites the original codes from zlzeng/DeepFloorplan into newer versions of Tensorflow and Python
Categories
Machine LearningLicense
GNU General Public License version 3.0 (GPLv3)Follow TF2DeepFloorplan
Other Useful Business Software
LinkSquares: All-in-One Contract Management Platform
LinkSquares is the leading Contract Lifecycle Management (CLM) software designed to help legal, procurement, and business operations teams master the entire contract lifecycle, from creation to execution and renewal. The platform transforms how companies manage agreements by centralizing data, automating routine work, and providing actionable insights powered by AI. This single, connected source of truth helps teams eliminate manual processes, streamline workflows, boost visibility, and ensure compliance across thousands of contracts, ultimately reducing risk and administrative burden.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of TF2DeepFloorplan!