Weed seedling images of species common to Manitoba, Canada

<p>This dataset contains 34666 RGB-images taken from different angles and distances of weeds common in Manitoba. The imaged species common name, scientific name, and number of their images are:</p> <table> <tbody> <tr> <td><span>Echinochloa crus-galli</span></td> <td>Large Barnyard Grass</td> <td>8621</td> </tr> <tr> <td> <span>Cirsium arvense</span><span> </span> </td> <td>Canada Thistle</td> <td>4706</td> </tr> <tr> <td> <span>Brassica napus</span><span> </span> </td> <td>Volunteer Canola</td> <td>6723</td> </tr> <tr> <td> <span>Taraxacum officinale</span><span> </span> </td> <td>Dandelion</td> <td>4797</td> </tr> <tr> <td><span>Persicaria spp.</span></td> <td>Smartweed</td> <td>870</td> </tr> <tr> <td> <span>Fallopia convolvulus</span><span> </span> </td> <td>Wild Buckwheat</td> <td>4165</td> </tr> <tr> <td> <span>Avena fatua</span><span> </span> </td> <td>Wild Oat</td> <td>1218</td> </tr> <tr> <td> <span>Setaria pumila</span><span> </span> </td> <td>Yellow Foxtail</td> <td>3566</td> </tr> </tbody> </table> <p>Furthermore, this dataset contains a trained ResNet50 convolutional neural network model. It is trained to distinguish between monocots and dicots. A small collection of test datasets is included that can be used to measure the generalization capabilities of trained models.</p> <p>The single-plant dataset and all test-datasets are accompanied by a csv-file containing filenames with respective labels.</p>