cff-version: 1.2.0
abstract: "<p>The dataset contains images of the discarded fish on the conveyor belt and annotations. Annotations are prepared in YOLO format, i.e. separate text files, containing fish species label, object bounding box annotation, weight and occlusion level. Annotation per individual fish is written in a separate row of the file.</p><p>Additionally, we provide weight file (.pt) for the best performing Detection-Weight2 model.</p>"
authors:
  - family-names: Sokolova
    given-names: Maria
  - family-names: Cordova
    given-names: Manuel
  - family-names: Nap
    given-names: Henk
  - family-names: van Helmond
    given-names: Edwin
  - family-names: Mans
    given-names: Michiel
  - family-names: Vroegop
    given-names: Arjan
  - family-names: Mencarelli
    given-names: Angelo
  - family-names: Kootstra
    given-names: Gert
    orcid: "https://orcid.org/0000-0002-2579-4324"
title: "Data underlying the publication: An integrated end-to-end deep neural network for automated detection of discarded fish species and their weight estimation."
keywords:
version: 2
identifiers:
  - type: doi
    value: 10.4121/a6d5a40e-0358-47cf-9ec1-335df0e4a3c3.v2
license: CC BY 4.0
date-released: 2024-06-11