Update utils.py

utils.py

@@ -1,23 +1,18 @@
+from transformers import ViTImageProcessor
 import torch
-from torchvision import transforms
 from PIL import Image
 import numpy as np
 
-def load_image(image_path):
-    transform = transforms.Compose([
-        transforms.Resize((224, 224)),
-        transforms.ToTensor(),
-        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
-    ])
-    
-    image = Image.open(image_path).convert('RGB')
-    return transform(image).unsqueeze(0)
+def load_image_vit(image_file, processor):
+    image = Image.open(image_file).convert('RGB')
+    inputs = processor(images=image, return_tensors="pt")
+    return inputs["pixel_values"]  # Shape: [1, 3, 224, 224]
 
-def predict_toxicity(model, image_tensor, device):
+def predict_toxicity_vit(model, inputs, device):
     model.eval()
     with torch.no_grad():
-        image_tensor = image_tensor.to(device)
-        outputs = model(image_tensor)
+        inputs = inputs.to(device)
+        outputs = model(inputs).logits
         probabilities = torch.nn.functional.softmax(outputs, dim=1)
         prediction = torch.argmax(probabilities, dim=1)
     return prediction.item(), probabilities[0].cpu().numpy()