Create app.py

app.py

@@ -0,0 +1,102 @@
+import numpy as np
+import streamlit as st
+from PIL import Image
+import io
+
+# Load the saved model
+from tensorflow.keras.models import load_model
+
+# Load the model architecture and weights
+model = load_model('/content/drive/MyDrive/ICT Project/Emotion_detection.h5')
+
+# Define the emotion labels
+emotion_labels = ['happy', 'sad', 'neutral']
+
+# Function to preprocess the image for the model
+def preprocess_image(image):
+    # Resize the image to match the input size of the model
+    image = image.resize((48, 48))
+    # Convert the image to grayscale
+    image = image.convert('L')
+    # Convert the image to a numpy array
+    image = np.array(image)
+    # Normalize the image
+    image = image / 255.0
+    # Expand the dimensions to match the input shape of the model
+    image = np.expand_dims(image, axis=-1)
+    # Expand the dimensions to create a batch of size 1
+    image = np.expand_dims(image, axis=0)
+    return image
+
+# Custom CSS for styling
+st.markdown("""
+    <style>
+    .title {
+        font-size: 3em;
+        color: #4CAF50; /* Green */
+        text-align: center;
+    }
+    .description {
+        font-size: 1.2em;
+        color: #777777; /* Gray */
+        text-align: center;
+    }
+    .header {
+        font-size: 1.5em;
+        color: #ff6f61; /* Red */
+    }
+    .predicted-emotion {
+        font-size: 1.5em;
+        color: #1e90ff; /* Blue */
+    }
+    .spinner-text {
+        font-size: 1.2em;
+        color: #ffa500; /* Orange */
+    }
+    </style>
+""", unsafe_allow_html=True)
+
+# Title and description
+st.markdown('<div class="title">Emotion Detection</div>', unsafe_allow_html=True)
+st.markdown('<div class="description">Upload an image to detect emotions</div>', unsafe_allow_html=True)
+
+# File uploader for images
+st.markdown('<div class="header">Upload Image</div>', unsafe_allow_html=True)
+image_file = st.file_uploader("Choose an image", type=["png", 'jpg'])
+
+# Sidebar to show previous predictions
+if 'predictions' not in st.session_state:
+    st.session_state.predictions = []
+
+st.sidebar.header("Previous Predictions")
+for pred in st.session_state.predictions:
+    st.sidebar.image(pred['image'], caption=pred['emotion'], use_column_width=True)
+
+# Display the uploaded image and predict emotions
+if image_file is not None:
+    image = Image.open(image_file)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    with st.spinner('Processing...'):
+        st.markdown('<div class="spinner-text">Processing...</div>', unsafe_allow_html=True)
+
+        # Preprocess the image
+        preprocessed_image = preprocess_image(image)
+
+        # Make predictions
+        predictions = model.predict(preprocessed_image)
+        predicted_label = emotion_labels[np.argmax(predictions)]
+
+        # Display the predicted emotion
+        st.markdown(f'<div class="predicted-emotion">Predicted Emotion: {predicted_label}</div>', unsafe_allow_html=True)
+
+        # Save the prediction and image to session state
+        image_bytes = io.BytesIO()
+        image.save(image_bytes, format='PNG')
+        st.session_state.predictions.append({
+            'image': image_bytes.getvalue(),
+            'emotion': predicted_label
+        })
+
+        # Update the sidebar with the new prediction
+        st.sidebar.image(image_bytes.getvalue(), caption=predicted_label, use_column_width=True)