Update app.py

app.py

@@ -3,25 +3,30 @@ import tensorflow as tf
 from PIL import Image
 import numpy as np
 
-# Load the model
-model = tf.keras.models.load_model('pokemon_classifier_model.keras')
+# Load your custom regression model
+model_path = "pokemon_model_tl.keras"
+model = tf.keras.models.load_model(model_path)
 
-def predict(image):
-    img = tf.keras.preprocessing.image.img_to_array(image)
-    img = tf.keras.preprocessing.image.smart_resize(img, (224, 224))
-    img = tf.expand_dims(img, 0)  # Make batch of one
-    
-    pred = model.predict(img)
-    pred_label = tf.argmax(pred, axis=1).numpy()[0]  # get the index of the max logit
-    pred_class = class_names[pred_label]  # use the index to get the corresponding class name
-    confidence = tf.nn.softmax(pred)[0][pred_label]  # softmax to get the confidence
-    
-    print(f"Predicted: {pred_class}, Confidence: {confidence:.4f}")
-    return pred_class
+labels = ['Wartortle', 'Weedle', 'Weepinbell', 'Weezing']
 
+# 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)).convert('RGB') #resize the image to 28x28 and converts it to gray scale
+    image = np.array(image)
+    print(image.shape)
+    # Predict
+    prediction = model.predict(image[None, ...])  # Assuming single regression value
+    confidences = {labels[i]: np.round(float(prediction[0][i]), 2) for i in range(len(labels))}
+    return confidences
 
-# Setup Gradio interface
-iface = gr.Interface(fn=predict, inputs=gr.Image(), outputs="text", title="Pokémon Classifier")
-
-# Run the interface
-iface.launch()
+# Create Gradio interface
+input_image = gr.Image()
+output_text = gr.Textbox(label="Predicted Value")
+interface = gr.Interface(fn=predict_regression, 
+                         inputs=input_image, 
+                         outputs=gr.Label(),
+                         examples=["wartortle.jpg", "weedle.jpg", "weepinbell.jpg", "weezing.jpg"],   
+                         description="A simple mlp classification model for image classification using the pokemon dataset.")
+interface.launch()