Spaces:

dhits
/

weed_classifier

Running

dmitryhits commited on May 11, 2023

Commit

a350d92

1 Parent(s): d2def97

changes article

Files changed (1) hide show

app.py CHANGED Viewed

@@ -25,7 +25,7 @@ These classes represent common plant species in Danish agriculture at different
  A pretrained ResNet34  model was fine-tuned using fastai vision library. The error rate achived on the validation dataset is 2.5% after 4 epochs.
 Currently the model does not generalize well on the out-of-domain images. Probably because of the specificity of the dataset.
 The images in the dataset are of a single plant taken from the top and on a single background of a grit surface. Some images have barcode labels that might be unique to the particular plant.
-The last two images in the examples are not from the dataset. They are getting wrongly classified as <b>Common Chickweed</b> even though they are <b>Small-flowered Cranesbill</b> (compare with the second image in the examples)
 <p style='text-align: center'><a href='https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial' target='_blank'>Blog post</a></p>
 </div>"""

  A pretrained ResNet34  model was fine-tuned using fastai vision library. The error rate achived on the validation dataset is 2.5% after 4 epochs.
 Currently the model does not generalize well on the out-of-domain images. Probably because of the specificity of the dataset.
 The images in the dataset are of a single plant taken from the top and on a single background of a grit surface. Some images have barcode labels that might be unique to the particular plant.
+The last two images in the examples are not from the dataset. They are getting wrongly classified as <b>Scentless Mayweed</b> even though they are <b>Small-flowered Cranesbill</b> (compare with the second image in the examples)
 <p style='text-align: center'><a href='https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial' target='_blank'>Blog post</a></p>
 </div>"""