Delete app.py

app.py

@@ -1,73 +0,0 @@
-
-import os  # Import the os module
-import torch
-from facenet_pytorch import InceptionResnetV1, MTCNN
-from PIL import Image
-from torchvision import transforms
-from sklearn.metrics.pairwise import cosine_similarity
-import gradio as gr
-
-# Load pre-trained FaceNet model
-facenet_model = InceptionResnetV1(pretrained='vggface2').eval()
-
-# Load MTCNN for face detection and alignment
-mtcnn = MTCNN(keep_all=True, device='cuda' if torch.cuda.is_available() else 'cpu')
-
-# Preprocessing function for FaceNet with face alignment
-def preprocess_image_facenet(img):
-    img = Image.fromarray(img).convert('RGB')
-    img_cropped = mtcnn(img)
-    if img_cropped is not None:
-        img_cropped = img_cropped[0]  # Take the first face detected
-        transform = transforms.Compose([
-            transforms.Resize((160, 160)),
-            transforms.ToTensor(),
-            transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-        ])
-        img_tensor = transform(img_cropped).unsqueeze(0)
-        return img_tensor
-    else:
-        return None
-
-# Register employee images for FaceNet
-def register_images_facenet(model, image_dir):
-    embeddings = {}
-    for filename in os.listdir(image_dir):
-        if filename.endswith('.jpg') or filename.endswith('.png'):
-            img_path = os.path.join(image_dir, filename)
-            img_tensor = preprocess_image_facenet(img_path)
-            if img_tensor is not None:
-                with torch.no_grad():
-                    embedding = model(img_tensor).numpy()
-                embeddings[filename.split('.')[0]] = embedding
-    return embeddings
-
-# Load employee images and register them
-employee_images_dir = 'employees_images'  # Ensure this directory is in the same directory as app.py
-facenet_embeddings = register_images_facenet(facenet_model, employee_images_dir)
-
-# Identify image function
-def identify_image_facenet(model, embeddings, img, threshold=0.5):
-    img_tensor = preprocess_image_facenet(img)
-    if img_tensor is not None:
-        with torch.no_grad():
-            embedding = model(img_tensor).numpy()
-        max_similarity = 0
-        identified_person = None
-        for name, registered_embedding in embeddings.items():
-            similarity = cosine_similarity(embedding, registered_embedding)
-            if similarity > max_similarity:
-                max_similarity = similarity
-                identified_person = name
-        if max_similarity >= threshold:
-            return f"Identified as {identified_person} with similarity {max_similarity[0][0]:.2f}"
-        else:
-            return "No match found"
-    else:
-        return "No face detected"
-
-# Gradio interface
-facenet_interface = gr.Interface(fn=identify_image_facenet, inputs="image", outputs="text", title="FaceNet Verification with Threshold 0.5")
-
-if _name_ == "_main_":
-    facenet_interface.launch()