Upload 5 files

app.py

@@ -0,0 +1,225 @@
+import json
+import streamlit as st
+from streamlit import session_state
+import os
+import numpy as np
+
+import tensorflow as tf 
+from tensorflow import keras
+from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau
+from tensorflow.keras.layers import Activation, Input, Conv2D, MaxPooling2D, BatchNormalization, Conv2DTranspose, concatenate
+from tensorflow.keras.models import Model, load_model
+from sklearn.model_selection import train_test_split
+from tensorflow.keras.models import Model, load_model
+import matplotlib.pyplot as plt
+import mpld3
+import streamlit.components.v1 as components
+import matplotlib.pyplot as plt
+import warnings
+from temp import model
+warnings.filterwarnings('ignore')
+
+
+session_state = st.session_state
+if "user_index" not in st.session_state:
+    st.session_state["user_index"] = 0
+
+
+def signup(json_file_path="data.json"):
+    st.title("Signup Page")
+    with st.form("signup_form"):
+        st.write("Fill in the details below to create an account:")
+        name = st.text_input("Name:")
+        email = st.text_input("Email:")
+        age = st.number_input("Age:", min_value=0, max_value=120)
+        sex = st.radio("Sex:", ("Male", "Female", "Other"))
+        password = st.text_input("Password:", type="password")
+        confirm_password = st.text_input("Confirm Password:", type="password")
+
+        if st.form_submit_button("Signup"):
+            if password == confirm_password:
+                user = create_account(name, email, age, sex, password, json_file_path)
+                session_state["logged_in"] = True
+                session_state["user_info"] = user
+            else:
+                st.error("Passwords do not match. Please try again.")
+def display_image(image, title='Image'):
+    plt.figure(figsize=(6, 6))
+    plt.title(title)
+    
+    # Check if the image is a TensorFlow tensor
+    if isinstance(image, tf.Tensor):
+        # Convert to NumPy array
+        image = image.numpy()
+        
+    # Squeeze the image to remove single-dimensional entries from the shape
+    image = np.squeeze(image)
+    
+    # Display the image
+    plt.imshow(image, cmap='gray' if image.ndim == 2 else None)
+    plt.axis('off')
+    plt.show()
+def check_login(username, password, json_file_path="data.json"):
+    try:
+        with open(json_file_path, "r") as json_file:
+            data = json.load(json_file)
+
+        for user in data["users"]:
+            if user["email"] == username and user["password"] == password:
+                session_state["logged_in"] = True
+                session_state["user_info"] = user
+                st.success("Login successful!")
+                return user
+
+        st.error("Invalid credentials. Please try again.")
+        return None
+    except Exception as e:
+        st.error(f"Error checking login: {e}")
+        return None
+
+
+def predict(uploaded_file):
+    model = load_model('model.h5')
+    bytes_data = uploaded_file.read()
+    image = tf.io.decode_image(bytes_data, channels=3)
+    image = tf.image.resize(image, (256, 256))
+    image = tf.cast(image, tf.float32) / 255.0
+    
+    # Expand dimensions to simulate batch size of 1
+    image = tf.expand_dims(image, axis=0)
+    
+    # Perform prediction
+    pred_mask = model.predict(image)
+    pred_mask = tf.argmax(pred_mask, axis=-1)
+    pred_mask = tf.expand_dims(pred_mask, axis=-1)
+    return pred_mask
+
+
+def initialize_database(json_file_path="data.json"):
+    try:
+        # Check if JSON file exists
+        if not os.path.exists(json_file_path):
+            # Create an empty JSON structure
+            data = {"users": []}
+            with open(json_file_path, "w") as json_file:
+                json.dump(data, json_file)
+    except Exception as e:
+        print(f"Error initializing database: {e}")
+
+
+def login(json_file_path="data.json"):
+    st.title("Login Page")
+    username = st.text_input("Username:")
+    password = st.text_input("Password:", type="password")
+
+    login_button = st.button("Login")
+
+    if login_button:
+        user = check_login(username, password, json_file_path)
+        if user is not None:
+            session_state["logged_in"] = True
+            session_state["user_info"] = user
+        else:
+            st.error("Invalid credentials. Please try again.")
+
+def get_user_info(email, json_file_path="data.json"):
+    try:
+        with open(json_file_path, "r") as json_file:
+            data = json.load(json_file)
+            for user in data["users"]:
+                if user["email"] == email:
+                    return user
+        return None
+    except Exception as e:
+        st.error(f"Error getting user information: {e}")
+        return None
+
+
+def render_dashboard(user_info, json_file_path="data.json"):
+    try:
+        st.title(f"Welcome to the Dashboard, {user_info['name']}!")
+        st.subheader("User Information:")
+        st.write(f"Name: {user_info['name']}")
+        st.write(f"Sex: {user_info['sex']}")
+        st.write(f"Age: {user_info['age']}")
+    except Exception as e:
+        st.error(f"Error rendering dashboard: {e}")
+def create_account(name, email, age, sex, password, json_file_path="data.json"):
+    try:
+        # Check if the JSON file exists or is empty
+        if not os.path.exists(json_file_path) or os.stat(json_file_path).st_size == 0:
+            data = {"users": []}
+        else:
+            with open(json_file_path, "r") as json_file:
+                data = json.load(json_file)
+
+        # Append new user data to the JSON structure
+        user_info = {
+            "name": name,
+            "email": email,
+            "age": age,
+            "sex": sex,
+            "password": password,
+
+        }
+        data["users"].append(user_info)
+
+        # Save the updated data to JSON
+        with open(json_file_path, "w") as json_file:
+            json.dump(data, json_file, indent=4)
+
+        st.success("Account created successfully! You can now login.")
+        return user_info
+    except json.JSONDecodeError as e:
+        st.error(f"Error decoding JSON: {e}")
+        return None
+    except Exception as e:
+        st.error(f"Error creating account: {e}")
+        return None
+
+
+def main(json_file_path="data.json"):
+    st.sidebar.title("Real-time image segmentation for self-driving cars")
+    page = st.sidebar.radio(
+        "Go to",
+        ("Signup/Login", "Dashboard", "Upload Image"),
+        key="Real-time image segmentation for self-driving cars",
+    )
+
+    if page == "Signup/Login":
+        st.title("Signup/Login Page")
+        login_or_signup = st.radio(
+            "Select an option", ("Login", "Signup"), key="login_signup"
+        )
+        if login_or_signup == "Login":
+            login(json_file_path)
+        else:
+            signup(json_file_path)
+
+    elif page == "Dashboard":
+        if session_state.get("logged_in"):
+            render_dashboard(session_state["user_info"])
+        else:
+            st.warning("Please login/signup to view the dashboard.")
+
+    elif page == "Upload Image":
+        if session_state.get("logged_in"):
+            st.title("Upload Image")
+            uploaded_image = st.file_uploader(
+                "Choose a image (PNG)", type=["png"]
+            )
+            if st.button("Upload") and uploaded_image is not None:
+                st.image(uploaded_image, use_container_width =True)
+                st.success("Image uploaded successfully!")
+                image = predict(uploaded_image)[0]
+                img = tf.keras.preprocessing.image.array_to_img(image.numpy())
+                fig, ax = plt.subplots()
+                ax.imshow(img)
+                ax.axis('off')
+                ax.set_title('Predicted Image')
+                print(type(img))
+                st.pyplot(fig)
+                
+if __name__ == "__main__":
+    initialize_database()
+    main()

data.json

@@ -0,0 +1,39 @@
+{
+    "users": [
+        {
+            "name": "Shreyansh",
+            "email": "Shreyansh@mail.com",
+            "age": 22,
+            "sex": "Male",
+            "password": "123"
+        },
+        {
+            "name": "Shreyansh",
+            "email": "Shreyansh@gmail.com",
+            "age": 22,
+            "sex": "Male",
+            "password": "123"
+        },
+        {
+            "name": "Shreyansh",
+            "email": "Shreyanshjain@gmail.com",
+            "age": 20,
+            "sex": "Male",
+            "password": "123"
+        },
+        {
+            "name": "Shreyansh",
+            "email": "Shreyansh@jain",
+            "age": 22,
+            "sex": "Male",
+            "password": "123"
+        },
+        {
+            "name": "Gani",
+            "email": "gvenkat@gmail.com",
+            "age": 22,
+            "sex": "Male",
+            "password": "kumar9849"
+        }
+    ]
+}

model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61067fc71efcb09f1db8543d53abca00a2cbac7fc95d055a275e9dc0b33b4d9d
+size 104099616

requirements.txt

@@ -0,0 +1,6 @@
+numpy
+tensorflow
+scikit-learn
+matplotlib
+streamlit
+mpld3

temp.py

@@ -0,0 +1,100 @@
+import json
+import streamlit as st
+from streamlit import session_state
+import numpy as np
+import pandas as pd
+import imageio
+import random
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' 
+
+import tensorflow as tf 
+from tensorflow import keras
+from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau
+from tensorflow.keras.layers import Activation, Input, Conv2D, MaxPooling2D, BatchNormalization, Conv2DTranspose, concatenate
+from tensorflow.keras.models import Model, load_model
+from sklearn.model_selection import train_test_split
+from tensorflow.keras.models import Model, load_model
+
+import matplotlib.pyplot as plt
+import warnings
+warnings.filterwarnings('ignore')
+
+
+import tensorflow as tf 
+from tensorflow import keras
+from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau
+from tensorflow.keras.layers import Activation, Input, Conv2D, MaxPooling2D, BatchNormalization, Conv2DTranspose, concatenate
+from tensorflow.keras.models import Model, load_model
+from sklearn.model_selection import train_test_split
+from tensorflow.keras.models import Model, load_model
+
+import matplotlib.pyplot as plt
+import warnings
+warnings.filterwarnings('ignore')
+
+
+session_state = st.session_state
+if "user_index" not in st.session_state:
+    st.session_state["user_index"] = 0
+
+
+def signup(json_file_path="data.json"):
+    st.title("Signup Page")
+    with st.form("signup_form"):
+        st.write("Fill in the details below to create an account:")
+        name = st.text_input("Name:")
+        email = st.text_input("Email:")
+        age = st.number_input("Age:", min_value=0, max_value=120)
+        sex = st.radio("Sex:", ("Male", "Female", "Other"))
+        password = st.text_input("Password:", type="password")
+        confirm_password = st.text_input("Confirm Password:", type="password")
+
+        if st.form_submit_button("Signup"):
+            if password == confirm_password:
+                user = create_account(name, email, age, sex, password, json_file_path)
+                session_state["logged_in"] = True
+                session_state["user_info"] = user
+            else:
+                st.error("Passwords do not match. Please try again.")
+
+
+def check_login(username, password, json_file_path="data.json"):
+    try:
+        with open(json_file_path, "r") as json_file:
+            data = json.load(json_file)
+
+        for user in data["users"]:
+            if user["email"] == username and user["password"] == password:
+                session_state["logged_in"] = True
+                session_state["user_info"] = user
+                st.success("Login successful!")
+                return user
+
+        st.error("Invalid credentials. Please try again.")
+        return None
+    except Exception as e:
+        st.error(f"Error checking login: {e}")
+        return None
+
+
+def predict(model):
+    image_path = "image.png"
+    image_path = tf.Variable(image_path)
+    # Load and preprocess the image
+    image = tf.io.read_file(image_path)
+    image = tf.image.decode_image(image, channels=3)
+    image = tf.image.resize(image, (256, 256))
+    image = tf.cast(image, tf.float32) / 255.0
+    
+    # Expand dimensions to simulate batch size of 1
+    image = tf.expand_dims(image, axis=0)
+    
+    # Perform prediction
+    pred_mask = model.predict(image)
+    pred_mask = tf.argmax(pred_mask, axis=-1)
+    pred_mask = tf.expand_dims(pred_mask, axis=-1)
+    return pred_mask
+
+model = load_model('model.h5')
+predict(model)