April 12, 2021 Dataset Open Access

Quentin Geissmann

DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.4680119">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Dataset"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.4680119</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.4680119"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-6546-4306">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0001-6546-4306</dct:identifier>
        <foaf:name>Quentin Geissmann</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of British Columbia</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Sticky Pi -- Machine Learning Data, Configuration and Models</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2021</dct:issued>
    <dcat:keyword>instect traps</dcat:keyword>
    <dcat:keyword>behavioral ecology</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-04-12</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/4680119"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/4680119</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.4680118"/>
    <dct:description>&lt;p&gt;&lt;strong&gt;Dataset for the Machine Learning section of the Sticky Pi project (https://doc.sticky-pi.com/)&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;Contains the dataset for the three algorithms described in the publication: Universal Insect Detector, Siamese Insect Matcher and Insect Tuboid Classifier.&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Universal Insect Detector:&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;`universal_insect_detector/` contains training/validation data, configuration files to train the model, and the model as trained and used for publication.&lt;/p&gt; &lt;ul&gt; &lt;li&gt;`data/` &amp;ndash; A set of svg images that contain the embedded jpg raw image, and a set of non-intersecting polygon around the labelled insects&lt;/li&gt; &lt;li&gt;`output/` &lt;ul&gt; &lt;li&gt;`model_final.pth` &amp;ndash; the model as trained for the publication&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;li&gt;`config/` &lt;ul&gt; &lt;li&gt;`config.yaml` &amp;ndash; The configuration file defining the hyperparameters to train the model as well as the taxonomic labels&lt;/li&gt; &lt;li&gt;`config.yaml `&amp;ndash; The configuration file defining the hyperparameters to train the model&lt;/li&gt; &lt;li&gt;`mask_rcnn_R_101_C4_3x.yaml` &amp;ndash; the base configuration file from which config is derived&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;/ul&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Siamese Insect Matcher&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;`siamese_insect_matcher/` contains training/validation data, configuration files to train the model, and the model as trained and used for publication.&lt;/p&gt; &lt;ul&gt; &lt;li&gt;`data/` &amp;ndash; a set of svg images that contain two embedded jpg raw images vertically stacked corresponding to two frames in a series. Each predicted insect is labelled as a polygon. Insects that are labelled as the same instance, between the two frames, are grouped (i.e. SVG group). The filename of each image is `&amp;lt;device&amp;gt;.&amp;lt;datetime_frame_1&amp;gt;.&amp;lt;datetime_frame_2&amp;gt;.svg`&lt;/li&gt; &lt;li&gt;`output/` &lt;ul&gt; &lt;li&gt;`model_final.pth` &amp;ndash; the model as trained for the publication&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;li&gt;`config/` &lt;ul&gt; &lt;li&gt;`config.yaml` &amp;ndash; The configuration file defining the hyperparameters to train the model as well as the taxonomic labels&lt;/li&gt; &lt;li&gt;`config.yaml` &amp;ndash; The configuration file defining the hyperparameters to train the model&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;/ul&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;&lt;strong&gt;Insect Tuboid Classifier:&lt;/strong&gt;&lt;/p&gt; &lt;p&gt;`insect_tuboid_classifier/` contains images of insect tuboid, a database file describing their taxonomy, a configuration file to train the model, and the model as trained and used for publication.&lt;/p&gt; &lt;ul&gt; &lt;li&gt;`data/` &lt;ul&gt; &lt;li&gt;`database.db`: a sqlite file with a single table `ANNOTATIONS`. The table maps a unique identifier of each tuboid (tuboid_id) to a set of manually annotated taxonomic variables.&lt;/li&gt; &lt;li&gt;A directory tree of the form: `&amp;lt;series_id&amp;gt;/&amp;lt;tuboid_id&amp;gt;/`. Each terminal directory contains: &lt;ul&gt; &lt;li&gt; &lt;ul&gt; &lt;li&gt;`tuboid.jpg` &amp;ndash; a jpeg image made of 224 x 224 tiles representing all the shots in a tuboid, left to right, top to bottom &amp;ndash; might be padded with empty images&lt;/li&gt; &lt;li&gt;`metadata.txt` &amp;ndash; a csv text file with columns: &lt;ul&gt; &lt;li&gt; &lt;ul&gt; &lt;li&gt;parrent_image_id &amp;ndash; &amp;lt;device&amp;gt;.&amp;lt;UTC_datetime&amp;gt;&lt;/li&gt; &lt;li&gt;X &amp;ndash; the X coordinates of the object centroid&lt;/li&gt; &lt;li&gt;Y &amp;ndash; the Y coordinates of the object centroid&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;li&gt;scale &amp;ndash; The scaling factor applied between the original and image and the 224 x 224 tile (&amp;gt;1 =&amp;gt; image was enlarged)&lt;/li&gt; &lt;li&gt;`context.jpg` &amp;ndash; a representation of the first whole image of a series, with a box around the first tuboid shot (this is for debugging/labelling purposes)&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;li&gt;`output/` &lt;ul&gt; &lt;li&gt;`model_final.pth` &amp;ndash; the model as trained for the publication&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;li&gt;config/ &lt;ul&gt; &lt;li&gt;`config.yaml` &amp;ndash; The configuration file defining the hyperparameters to train the model as well as the taxonomic labels&lt;/li&gt; &lt;/ul&gt; &lt;/li&gt; &lt;/ul&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4680119"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4680119"/>
        <dcat:byteSize>6860304663</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4680119/files/insect-tuboid-classifier.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4680119"/>
        <dcat:byteSize>1093649148</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4680119/files/siamese-insect-matcher.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4680119"/>
        <dcat:byteSize>1058469613</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4680119/files/universal-insect-detector.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>