Returns farm insect type given an image with about 91% accuracy.
See https://www.kaggle.com/code/dima806/farm-insects-image-detection-vit for more details.
Classification report:
precision recall f1-score support
Fall Armyworms 0.7895 0.3191 0.4545 47
Western Corn Rootworms 0.9787 0.9787 0.9787 47
Colorado Potato Beetles 1.0000 0.9792 0.9895 48
Thrips 0.9762 0.8723 0.9213 47
Corn Earworms 0.9070 0.8125 0.8571 48
Cabbage Loopers 0.9388 0.9583 0.9485 48
Armyworms 0.6143 0.9149 0.7350 47
Brown Marmorated Stink Bugs 1.0000 1.0000 1.0000 48
Tomato Hornworms 0.9792 1.0000 0.9895 47
Citrus Canker 0.9038 1.0000 0.9495 47
Aphids 0.9020 0.9583 0.9293 48
Corn Borers 0.8148 0.9167 0.8627 48
Fruit Flies 1.0000 1.0000 1.0000 48
Africanized Honey Bees (Killer Bees) 1.0000 1.0000 1.0000 48
Spider Mites 0.9167 0.9167 0.9167 48
accuracy 0.9090 714
macro avg 0.9147 0.9085 0.9022 714
weighted avg 0.9151 0.9090 0.9027 714
- Downloads last month
- 55
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for dima806/farm_insects_image_detection
Base model
google/vit-base-patch16-224-in21k