Please use this identifier to cite or link to this item:
For citation please use:
Main Title: BIM-Speed training dataset for HVAC detection using Deep Learning
Author(s): Llamas, José
Type: Generic Research Data
Abstract: Training dataset formed by two types of elements (for now) to be detected by the model using Deep Learning: Boiler and Radiator. Of the boiler type 107 images have been collected and of the radiator type 123 images. Although there are few images to get good training, it can be used as a first approximation and to evaluate the precision obtained with few training images. These images have been distributed in 80% of the images for the training phase and 20% for the test phase. All the images have the bounding box data for each element in the xml file with the same name. Additionally, 33 other images (not previously used) have been used for the validation of the tool.
Subject(s): building renovation
deep learning
training images
Issue Date: 28-Apr-2022
Date Available: 4-May-2022
Language Code: en
DDC Class: 624 Ingenieurbau
Sponsor/Funder: EC/H2020/820553 /EU/Harmonised Building Information Speedway for Energy-Efficient Renovation/BIM-SPEED
TU Affiliation(s): Verbundforschung » EU Verbundprojekte » BIM-SPEED
Appears in Collections:Technische Universität Berlin » Research Data

Files in This Item:
Training dataset for HVAC

A zip archive containing images of HVAC systems together with metadata (inclusive labels) in xml and json format. The xml files are in Pascal VOC XML format which is widely used in Deep Learning. Json files are used in COCO, also widely used. There are conversion tools from one format to another. For more information:

Format: ZIP Archive | Size: 68.55 MB
Format: Text | Size: 509 B

Item Export Bar

This item is licensed under a Creative Commons License Creative Commons