Upload 6 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+EfficientNet_ModelWeights.keras filter=lfs diff=lfs merge=lfs -text

EfficientNet_ModelWeights.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0751c1be6cda630868a74d1c0409694fc2e638fd3af2d519de7f6220469f2b12
+size 18180480

README.md

@@ -1,12 +1,2 @@
----
-title: Face Expresion15
-emoji: 👁
-colorFrom: pink
-colorTo: pink
-sdk: streamlit
-sdk_version: 1.32.2
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Expresso
+I have built a model which tries to predict the facial expression of the image provided. This model is using the EfficientNet as its base model. The current idea works only for a limited number of expressions.

app.py

@@ -0,0 +1,110 @@
+# from flask import Flask, request, jsonify, render_template
+# from tensorflow.keras.models import load_model
+# from tensorflow.keras.preprocessing import image
+# from efficientnet.tfkeras import preprocess_input
+# import numpy as np
+
+# app = Flask(__name__)
+
+# model = load_model('EfficientNet_ModelWeights.keras')
+
+# def preprocess_and_predict(model, img_path, target_size=(224, 224)):
+#     # Load and preprocess the image
+#     img = image.load_img(img_path, target_size=target_size)
+#     img_array = image.img_to_array(img)
+#     img_array = np.expand_dims(img_array, axis=0)
+#     img_array = preprocess_input(img_array)
+
+#     # Make prediction
+#     prediction = model.predict(img_array)
+#     predicted_class = np.argmax(prediction) 
+
+#     # Return the predicted class
+#     return predicted_class
+
+# @app.route('/')
+# def home():
+#     return render_template('index.html')
+
+# @app.route('/predict', methods=['POST'])
+# def predict():
+#     if 'file' not in request.files:
+#         return jsonify({'error': 'No file part'})
+
+#     file = request.files['file']
+
+#     # Save the uploaded file temporarily
+#     file_path = 'temp_image.jpg'
+#     file.save(file_path)
+
+#     # Make prediction
+#     predicted_class = preprocess_and_predict(model, file_path)
+
+#     # Return the predicted class as a response
+#     return render_template('index.html', prediction=predicted_class)
+
+# if __name__ == '__main__':
+#     app.run(debug=True)
+
+import streamlit as st
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+from efficientnet.tfkeras import preprocess_input
+import numpy as np
+
+# Load your machine learning model
+@st.cache(allow_output_mutation=True)
+def load_model():
+    return load_model('EfficientNet_ModelWeights.keras')
+
+# Prediction function
+def preprocess_and_predict(model, img_path, target_size=(224, 224)):
+    # Load and preprocess the image
+    img = image.load_img(img_path, target_size=target_size)
+    if img is None:
+        print("Error: Image not loaded.")
+        return None
+    
+    # Converting image to array and preprocessing using EfficientNet's preprocessing
+    img_array = image.img_to_array(img)
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array = preprocess_input(img_array)
+
+    # Predicting the class label
+    preds = model.predict(img_array)
+    predicted_label = np.argmax(preds[0])
+
+    reverse_expression_labels = {v: k for k, v in expression_labels.items()}
+
+    # Converting the predicted label index to its corresponding expression label
+    predicted_expression_label = reverse_expression_labels[predicted_label]
+    
+    return predicted_expression_label
+def main():
+    st.title('Expresso - Image Prediction')
+
+    # Display the custom HTML content
+    with open("index.html", "r", encoding="utf-8") as file:
+        html_code = file.read()
+        st.components.v1.html(html_code, width=700, height=800)
+
+    # Load the model
+    model = load_model()
+
+    # Check if the file uploader is used
+    if st.file_uploader is not None:
+        uploaded_file = st.file_uploader("Upload your image", type=['jpg', 'png'])
+        if uploaded_file is not None:
+            # Make prediction when the "Predict" button is clicked
+            if st.button('Predict'):
+                # Save the uploaded file temporarily
+                with open("temp_image.jpg", "wb") as f:
+                    f.write(uploaded_file.read())
+                # Make prediction
+                predicted_class = preprocess_and_predict(model, "temp_image.jpg")
+                # Display prediction result
+                st.write(f'Predicted Class: {predicted_class}')
+
+if __name__ == '__main__':
+    main()
+

index.html

@@ -0,0 +1,21 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>Expresso - Image Prediction</title>
+<link rel="stylesheet" href="styles.css"> 
+</head>
+<body>
+
+<div class="container">
+    <h1>Expresso - Image Prediction</h1>
+    <form id="uploadForm" enctype="multipart/form-data" action="/predict" method="post">
+        <label for="imageUpload" style="display: block; text-align: center; margin-bottom: 20px;">Upload your image</label>
+        <input type="file" id="imageUpload" name="file" style="display: block; margin: 0 auto 20px;" accept="image/*">
+        <button type="submit" class="upload-btn">Predict</button>
+    </form>
+</div>
+
+</body>
+</html>

requirements.txt

@@ -0,0 +1,9 @@
+pandas==1.3.0
+numpy==1.19.5
+scikit-learn==1.0.1
+matplotlib==3.5.0
+matplotlib-inline==0.1.3
+seaborn==0.11.1
+tensorflow==2.6.0
+tensorboard==2.6.0
+streamlit==1.2.0

styles.css

@@ -0,0 +1,40 @@
+body {
+    font-family: Arial, sans-serif;
+    margin: 0;
+    padding: 20px;
+    background-image: url('https://img.freepik.com/free-vector/emoticons-with-empty-space-background_79603-1023.jpg'); 
+    background-size: cover;
+    background-position: center;
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    height: 100vh;
+}
+
+.container {
+    max-width: 600px;
+    background-color: rgba(255, 255, 255, 0.8); 
+    padding: 20px;
+    border-radius: 10px;
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+}
+
+h1 {
+    text-align: center;
+}
+
+.upload-btn {
+    display: block;
+    margin: 20px auto;
+    padding: 10px 20px;
+    background-color: #007bff; /* Blue button */
+    color: #fff; /* White text */
+    border: none;
+    border-radius: 5px;
+    cursor: pointer;
+    transition: background-color 0.3s;
+}
+
+.upload-btn:hover {
+    background-color: #0056b3; /* Darker blue on hover */
+}