Update app.py

app.py

@@ -3,40 +3,42 @@ import tensorflow as tf
 import numpy as np
 from PIL import Image
 
-# Pfad zum gespeicherten Modell
+#!pip install tensorflow tensorflow-datasets gradio pillow matplotlib
+
 model_path = "pokemon-model_transferlearning.keras"
 model = tf.keras.models.load_model(model_path)
 
-# Definieren der Klassennamen
-labels = ['Articuno', 'Bulbasaur', 'Charmander']
+from PIL import Image
+import numpy as np
+import tensorflow as tf
 
-# Funktion zur Klassifizierung
-def classify_pokemon(image):
-    if image is None:
-        return {"Error": "No image uploaded"}
+# Define the core prediction function
+def predict_pokemon(image):
+    # Preprocess image
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((150, 150)) # Resize the image to 150x150
+    image = np.array(image)
+    image = np.expand_dims(image, axis=0) # Add batch dimension
     
-    # Bildvorverarbeitung
-    image = Image.fromarray(image).resize((150, 150))
-    image = np.array(image) / 255.0
-    image = np.expand_dims(image, axis=0)
-    
-    # Vorhersage
+    # Predict
     prediction = model.predict(image)
-    predicted_class = np.argmax(prediction[0])
-    confidence = np.max(prediction[0])
     
-    # Konfidenzwerte
-    confidences = {labels[i]: np.round(float(prediction[0][i]), 2) for i in range(len(labels))}
+    # Apply softmax to get probabilities for each class
+    probabilities = tf.nn.softmax(prediction)
+    
+    # Map probabilities to Pokemon classes
+    pokemon_classes = ['Articuno', 'Bulbasaur', 'Charmander']  
+    probabilities_dict = {pokemon_class: round(float(probability), 2) for pokemon_class, probability in zip(pokemon_classes, probabilities[0])}
     
-    return confidences, f"Predicted: {labels[predicted_class]}, Confidence: {confidence:.2f}"
+    return probabilities_dict
 
-# Erstellen einer Gradio-Schnittstelle
+# Create the Gradio interface
+input_image = gr.Image()
 iface = gr.Interface(
-    fn=classify_pokemon,
-    inputs=gr.Image(),
-    outputs=["label", "text"],
-    live=True
-)
-
-# Starten der Schnittstelle
-iface.launch()
+    fn=predict_pokemon,
+    inputs=input_image, 
+    outputs=gr.Label(),
+    live=True,
+    examples=["images/01.jpg", "images/02.png", "images/03.png", "images/04.jpg", "images/06.png", "images/06.png"],   
+    description="A simple mlp classification model for image classification using the mnist dataset.")
+iface.launch()