Create app.py

app.py

@@ -0,0 +1,42 @@
+
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForPreTraining
+import streamlit as st
+from PIL import Image
+import cv2
+import requests
+from dotenv import load_dotenv
+import google.generativeai as genai
+from langchain_google_genai import ChatGoogleGenerativeAI
+import os
+import pandas as pd
+from huggingface_hub import login
+
+
+processor = AutoProcessor.from_pretrained("google/paligemma-3b-pt-224")
+model = AutoModelForPreTraining.from_pretrained("google/paligemma-3b-pt-224")
+
+st.title("Image segmentation and object analysis")
+uploaded_file = st.file_uploader("Choose an image")
+
+if uploaded_file is not None:
+    image_data = uploaded_file.read()
+    st.image(image_data)
+    st.write("file uploaded")
+    image = Image.open(uploaded_file)
+    # Specify the file path to save the image
+    filepath = "./uploaded_image.jpg" 
+    # Save the image
+    image.save(filepath)
+    st.success(f"Image saved successfully at {filepath}")
+    prompt = "Describe the image content in detail."
+
+    # Preprocess the image and prompt using the processor
+    inputs = processor( text=prompt, images=image, return_tensors="pt")
+
+    # Pass the inputs to the model
+    outputs = model(**inputs)
+    # Assuming you have the output stored in a variable called `outputs`
+    generated_text = processor.decode(outputs.logits.argmax(dim=-1)[0], skip_special_tokens=True)
+    print(generated_text)
+    st.write(generated_text)