Update app.py

app.py

@@ -5,6 +5,40 @@ import re
 import random
 import whisper
 from pydub import AudioSegment
+import torch
+import torchvision.transforms as transforms
+import torchvision.models as models
+from PIL import Image
+
+
+# Load ResNet18 model
+model = models.resnet18(weights=models.ResNet18_Weights.IMAGENET1K_V1)
+model.fc = torch.nn.Linear(model.fc.in_features, 2)  # Adjust for two classes
+model.eval()
+
+# Define image transformation
+transform = transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor()
+])
+
+# Function to classify posture images
+def classify_image(image):
+    if image is None:
+        return "No image provided! Please upload or capture an image."
+    
+    image = transform(image).unsqueeze(0)
+    output = model(image)
+    _, predicted = torch.max(output, 1)
+    return (
+        "Good Posture! Sit exactly like that for your Interview!" 
+        if predicted.item() == 0 
+        else "Bad Posture, you should think of sitting a little straighter or more in frame for your real interview."
+    )
+
+# Set up Gradio interface
+iface = gr.Interface(fn=classify_image, inputs=gr.Image(type="pil"), outputs="text")
+iface.launch()
 
 # uploading and cleaning the knowledge txt file
 def load_questions(file_path):