| import gradio as gr
|
| from transformers import CLIPProcessor, CLIPModel
|
| from PIL import Image
|
| import torch
|
|
|
| print("Loading Classification Model...")
|
| model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
|
| processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
|
| model.eval()
|
| print("Model Loaded successfully!")
|
|
|
|
|
| LABELS = [
|
| "an official academic certificate or diploma",
|
| "a government ID card, passport, or driving license",
|
| "a random photograph of a person, nature, or objects",
|
| "a screenshot of a website or meme"
|
| ]
|
|
|
| def verify_document_class(image: Image.Image):
|
| """
|
| Returns:
|
| - is_valid (bool)
|
| - message (str)
|
| - best_label (str)
|
| - confidence (%) (float)
|
| - probabilities table (list)
|
| """
|
| if image is None:
|
| return False, "No image provided", "", 0.0, []
|
|
|
| image = image.convert("RGB")
|
|
|
| inputs = processor(text=LABELS, images=image, return_tensors="pt", padding=True)
|
|
|
| with torch.no_grad():
|
| outputs = model(**inputs)
|
| probs = outputs.logits_per_image.softmax(dim=1)[0].cpu().numpy()
|
|
|
| best_idx = int(probs.argmax())
|
| best_label = LABELS[best_idx]
|
| confidence = float(probs[best_idx] * 100.0)
|
|
|
|
|
| is_valid = best_idx in (0, 1)
|
| message = "Valid Document Class" if is_valid else "Invalid image type. Please upload a certificate or ID."
|
|
|
|
|
| table = [{"label": LABELS[i], "probability_%": float(probs[i] * 100.0)} for i in range(len(LABELS))]
|
|
|
| return is_valid, message, best_label, confidence, table
|
|
|
|
|
| demo = gr.Interface(
|
| fn=verify_document_class,
|
| inputs=gr.Image(type="pil", label="Upload Image"),
|
| outputs=[
|
| gr.Checkbox(label="Is Valid Document?"),
|
| gr.Textbox(label="Message"),
|
| gr.Textbox(label="Best Match Label"),
|
| gr.Number(label="Confidence (%)"),
|
| gr.JSON(label="All Probabilities"),
|
| ],
|
| title="Document Class Verifier (CLIP Gatekeeper)",
|
| description="Uploads an image and checks whether it looks like a certificate/diploma or ID vs random photo/screenshot."
|
| )
|
|
|
| demo.launch(server_name="0.0.0.0", server_port=7860) |
