Upload 3 files

app.py

@@ -0,0 +1,35 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from tensorflow.keras.preprocessing import image
+from PIL import Image
+
+# Load your trained model
+model = tf.keras.models.load_model("emotion_model.h5")  # Ensure this model is in the repo
+
+# Define emotion labels
+emotion_labels = ['Anger', 'Disgust', 'Fear', 'Happiness', 'Neutral', 'Sadness', 'Surprise', 'Contempt']
+
+# Function for inference
+def predict_emotion(img):
+    img = img.convert("RGB").resize((48, 48))  # Ensure correct size
+    img_array = image.img_to_array(img)
+    img_array = np.expand_dims(img_array, axis=0) / 255.0  # Normalize
+
+    predictions = model.predict(img_array)
+    predicted_class = np.argmax(predictions)
+    confidence = np.max(predictions)
+
+    return f"Emotion: {emotion_labels[predicted_class]} (Confidence: {confidence:.2f})"
+
+# Gradio UI
+iface = gr.Interface(
+    fn=predict_emotion,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="Emotion Detection",
+    description="Upload an image, and the AI will predict the emotion.",
+)
+
+# Run app
+iface.launch()

emotion_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39922632d095a301b9c0122dcf1846eba928c028865cabfe5f2386c36c2ccfb3
+size 289692192

requirements.txt

@@ -0,0 +1,4 @@
+tensorflow
+gradio
+numpy
+pillow