README.md

metadata

tags:
  - image-classification
  - pytorch
  - medical
  - colon
metrics:
  - f1

Vision Transformer fine-tuned on kvasir_v2 for colonoscopy classification

Download this image and drag/upload it to the widget!

Metrics

                        precision    recall  f1-score   support

    dyed-lifted-polyps       0.95      0.93      0.94        60
dyed-resection-margins       0.97      0.95      0.96        64
           esophagitis       0.93      0.79      0.85        67
          normal-cecum       1.00      0.98      0.99        54
        normal-pylorus       0.95      1.00      0.97        57
         normal-z-line       0.82      0.93      0.87        67
                polyps       0.92      0.92      0.92        52
    ulcerative-colitis       0.93      0.95      0.94        59

              accuracy                           0.93       480
             macro avg       0.93      0.93      0.93       480
          weighted avg       0.93      0.93      0.93       480

How to use

from transformers import ViTFeatureExtractor, ViTForImageClassification
from hugsvision.inference.VisionClassifierInference import VisionClassifierInference

path = "mrm8488/vit-base-patch16-224_finetuned-kvasirv2-colonoscopy"


classifier = VisionClassifierInference(
    feature_extractor = ViTFeatureExtractor.from_pretrained(path),
    model = ViTForImageClassification.from_pretrained(path),
)

img  = "Your image path"
label = classifier.predict(img_path=img)
print("Predicted class:", label)

Disclaimer: This model was trained for research only

Created by Manuel Romero/@mrm8488 | LinkedIn

Made with ♥ in Spain