To use transformers instead

app.py

@@ -1,32 +1,36 @@
-import torch
-import clip
-from PIL import Image
-import gradio as gr
-
-# Load model
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model, preprocess = clip.load("ViT-B/32", device=device)
-
-# Load normal class image embeddings
-# For real use, you should create multiple embeddings and average them
-normal_image = preprocess(Image.open("normal_sample.jpg")).unsqueeze(0).to(device)
-with torch.no_grad():
-    normal_embedding = model.encode_image(normal_image)
-    normal_embedding /= normal_embedding.norm()
-
-def detect_anomaly(img):
-    img = preprocess(img).unsqueeze(0).to(device)
-    with torch.no_grad():
-        test_embedding = model.encode_image(img)
-        test_embedding /= test_embedding.norm()
-        similarity = (test_embedding @ normal_embedding.T).item()
-    
-    if similarity < 0.8:  # example threshold
-        result = "Anomaly Detected"
-    else:
-        result = "Normal"
-    return f"Similarity: {similarity:.2f} | {result}"
-
-gr.Interface(fn=detect_anomaly,
-             inputs=gr.Image(),
-             outputs="text").launch()
+import torch
+from transformers import CLIPProcessor, CLIPModel
+from PIL import Image
+import gradio as gr
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load the model
+model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32").to(device)
+processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+# Load normal image for reference
+normal_image = Image.open("normal_sample.jpg")
+
+with torch.no_grad():
+    inputs = processor(images=normal_image, return_tensors="pt").to(device)
+    normal_features = model.get_image_features(**inputs)
+    normal_features = normal_features / normal_features.norm(p=2, dim=-1, keepdim=True)
+
+def detect_anomaly(img):
+    with torch.no_grad():
+        inputs = processor(images=img, return_tensors="pt").to(device)
+        test_features = model.get_image_features(**inputs)
+        test_features = test_features / test_features.norm(p=2, dim=-1, keepdim=True)
+        
+        similarity = (test_features @ normal_features.T).item()
+        
+    if similarity < 0.8:  # threshold example
+        result = "Anomaly Detected"
+    else:
+        result = "Normal"
+    return f"Similarity: {similarity:.2f} | {result}"
+
+gr.Interface(fn=detect_anomaly,
+             inputs=gr.Image(),
+             outputs="text").launch()