Views
No views yet
| Metric | Value |
|---|---|
| Accuracy | 83.38% |
| Precision | 71.50% |
| Recall (Sensitivity) | 72.25% |
| Specificity | 88.02% |
| F1 Score | 0.7187 |
| MCC | 0.6009 |
1from transformers import AutoImageProcessor, AutoModelForImageClassification
2from PIL import Image
3import torch
4
5# Load model and processor
6model = AutoModelForImageClassification.from_pretrained("Shivamnegi92/cancer-classification-vit")
7processor = AutoImageProcessor.from_pretrained("Shivamnegi92/cancer-classification-vit")
8
9# Load and preprocess image
10image = Image.open("path/to/your/image.jpg")
11inputs = processor(images=image, return_tensors="pt")
12
13# Make prediction
14with torch.no_grad():
15 outputs = model(**inputs)
16 predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
17 predicted_class = torch.argmax(predictions, dim=-1)
18
19# Interpret results
20class_names = ["Normal", "Malignant"]
21confidence = predictions[0][predicted_class].item()
22result = class_names[predicted_class.item()]
23
24print(f"Prediction: {result}")
25print(f"Confidence: {confidence:.4f}")1@misc{cancer-classification-vit-2024,
2 title={Cancer Image Classification using Vision Transformer},
3 author={Shivam Negi},
4 year={2024},
5 howpublished={\url{https://huggingface.co/Shivamnegi92/cancer-classification-vit}}
6}