Update app.py

app.py

@@ -1,35 +1,51 @@
 import gradio as gr
-import tensorflow as tf
 from PIL import Image
-import numpy as np
 
+# Load your custom regression model
+model_path = "transferlearning_pokemon.keras"
 
-# Modell laden
-model = tf.keras.models.load_model('pokemon_classifier.keras')
+#model.load_weights(model_path)
+model = tf.keras.models.load_model(model_path)
 
-def classify_image(image):
-    # Bild vorverarbeiten
-    image = Image.fromarray(image.astype('uint8')).convert('RGB')
-    image = image.resize((150, 150))  # Anpassung der Größe an das Modell
-    image = np.array(image) / 255.0  # Normalisieren
-    image = np.expand_dims(image, axis=0)  # Hinzufügen der Batch-Dimension
+labels = ['Abra', 'Ditto', 'Gengar']
 
-    # Vorhersage machen
-    prediction = model.predict(image).flatten()
-    classes = ['Abra', 'Ditto', 'Gengar']  # Namen der Klassen
+def predict_pokemons(image):
+    # Preprocess the image
+    print(type(image))
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((150, 150))  # Resize the image as per the model's input requirement
+    image = np.array(image)
+    image = np.expand_dims(image, axis=0)  # Add batch dimension
+    
+    # Predict
+    predictions = model.predict(image)
+    
+    # Convert the logits to probabilities using softmax
+    probabilities = tf.nn.softmax(predictions[0]).numpy()
+    
+    # Create a dictionary to hold the probabilities for each class
+    results = {class_names[i]: float(np.round(probabilities[i], 2)) for i in range(len(class_names))}
+    return results
 
-    # Wahrscheinlichkeiten mit Klassen verbinden und formatieren
-    return {classes[i]: float(prediction[i]) for i in range(len(classes))}
+# Define regression function
+def predict_regression(image):
+    # Preprocess image
+    image = Image.fromarray(image.astype('uint8'))  # Convert numpy array to PIL image
+    image = image.resize((150, 150))
+    image = np.array(image)
+    print(image.shape)
+    # Predict
+    prediction = model.predict(image[None, ...])  # Assuming single regression value
+    print(prediction)
+    confidences = str(prediction)
+    return confidences
 
-# Gradio-Interface erstellen
+# Create Gradio interface
 input_image = gr.Image()
-iface = gr.Interface(
-    fn=classify_image,
-    inputs=input_image,
-    outputs=gr.Label(num_top_classes=3),
-    examples=["pokemon/Abra/00000000.png", "pokemon/Ditto/00000000.jpg", "pokemon/Gengar/00000000.png"],  # Beispiele hinzufügen
-    description="Upload an image of a Pokémon to classify it as Pikachu, Charmander, or Bulbasaur."
-)
-
-# Interface starten
-iface.launch()
+output_text = gr.Textbox(label="Predicted Value")
+interface = gr.Interface(fn=predict_pokemons, 
+                         inputs=input_image, 
+                         outputs=gr.Label(),
+                         examples=["images/images_0.png", "images/images_1.png", "images/images_2.png", "images/images_3.png"],   
+                         description="A simple pokemon classification model based on Xception and Pokemon Images (https://www.kaggle.com/datasets/mikoajkolman/pokemon-images-first-generation17000-files).")
+interface.launch()