DeepWeeds has 9 classes only

Project-AgML / AgML

AgML is a centralized framework for agricultural machine learning. AgML provides access to public agricultural datasets for common agricultural deep learning tasks, with standard benchmarks and pretrained models, as well the ability to generate synthetic data and annotations.

Apache License 2.0

167 stars 28 forks source link

DeepWeeds has 9 classes only #54

Closed Akshatha-Mohan closed 2 months ago

Akshatha-Mohan commented 2 months ago

In the rangeland_weeds_australia in the AgML repo, the class names are [no_weeds, chinee_apple, lantana, parkinsonia, parthenium, prickly_acacia, rubber_vine, siam_weed, snake_weed, negative]. However the actual dataset does not have the class "no_weeds". The actual total number of classes is 9 and not 10.

masonearles commented 2 months ago

@amogh7joshi Thoughts on correcting this?

amogh7joshi commented 2 months ago

This has been fixed in AgML v0.6.1 (releasing in like 20 minutes), update to the latest version to use the fixed dataset @Akshatha-Mohan.