Update app.py

app.py

@@ -4,38 +4,43 @@ from tensorflow.keras.preprocessing import image
 from huggingface_hub import hf_hub_download
 import numpy as np
 import os
+from PIL import Image  
 
 MODEL_REPO = "zotthytt12/vegetable-classifier"
 MODEL_FILENAME = "model/veg_model.h5"
 
 # pobierz model z Hugging Face Hub
+print("Pobieranie modelu...")
 model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILENAME)
+print("Model pobrany, ładowanie...")
 model = tf.keras.models.load_model(model_path)
+print("Model załadowany.")
+
 
 CLASS_NAMES = ['Bean', 'Bitter_Gourd', 'Bottle_Gourd', 'Brinjal', 'Broccoli',
                'Cabbage', 'Capsicum', 'Carrot', 'Cauliflower', 'Cucumber',
                'Papaya', 'Potato', 'Pumpkin', 'Radish', 'Tomato']
-
 IMG_SIZE = (128, 128)
 
 def predict(img_path):
-    # img_path to ścieżka do pliku, który Gradio stworzył
-    from PIL import Image
+
     img = Image.open(img_path)
     img = img.resize(IMG_SIZE)
     x = image.img_to_array(img)
     x = np.expand_dims(x, axis=0) / 255.0
+    
     preds = model.predict(x)
     probs = preds[0]
+    
+
     return {CLASS_NAMES[i]: float(probs[i]) for i in range(len(CLASS_NAMES))}
 
 iface = gr.Interface(
     fn=predict,
-    inputs=gr.Image(type="filepath"),   # zmienione z "pil" na "filepath"
+    inputs=gr.Image(type="filepath"),
     outputs=gr.Label(num_top_classes=3),
     title="Vegetable Classifier",
-    description="Wgraj zdjęcie warzywa, a model powie co to jest."
-)
+    description="Wgraj zdjęcie warzywa, a model powie co to jest.")
 
 if __name__ == "__main__":
     iface.launch(show_error=True)