Update app.py

app.py

@@ -1,74 +1,28 @@
-import tkinter as tk
-from tkinter import filedialog
 import cv2
-from PIL import Image, ImageTk
 import numpy as np
 from tensorflow.keras.models import load_model
 
-class ShelfClassifierApp:
-    def __init__(self, master):
-        self.master = master
-        self.master.title("Shelf Classifier")
-
-        self.model = load_model('your_model.h5')  # Load your model
-
-        self.canvas = tk.Canvas(master, width=300, height=300)
-        self.canvas.pack()
-
-        self.load_button = tk.Button(master, text="Load Image", command=self.load_image)
-        self.load_button.pack()
-
-        self.classify_button = tk.Button(master, text="Classify", command=self.classify_image)
-        self.classify_button.pack()
-
-        self.result_label = tk.Label(master, text="")
-        self.result_label.pack()
-
-        self.image = None
-
-    def load_image(self):
-        file_path = filedialog.askopenfilename()
-        if file_path:
-            self.image = cv2.imread(file_path)
-            self.image = cv2.cvtColor(self.image, cv2.COLOR_BGR2RGB)
-            self.display_image(self.image)
-
-    def display_image(self, image):
-        image = Image.fromarray(image)
-        image = ImageTk.PhotoImage(image)
-        self.canvas.create_image(0, 0, anchor=tk.NW, image=image)
-        self.canvas.image = image
-
-    def classify_image(self):
-        if self.image is not None:
-            # Preprocess the image
-            resized_image = cv2.resize(self.image, (224, 224))
-            resized_image = resized_image.astype('float32') / 255
-            resized_image = np.expand_dims(resized_image, axis=0)
-
-            # Make prediction
-            prediction = self.model.predict(resized_image)
-
-            # Postprocess the prediction
-            class_index = np.argmax(prediction)
-            class_label = "Disorganized or Empty" if class_index == 1 else "Organized"
-
-            # Draw bounding box if shelf is disorganized or empty
-            if class_index == 1:
-                # Draw red rectangle
-                image_with_box = cv2.rectangle(self.image, (0, 0), (self.image.shape[1], self.image.shape[0]), (255, 0, 0), 2)
-                self.display_image(image_with_box)
-            else:
-                self.display_image(self.image)
-
-            self.result_label.config(text=class_label)
-        else:
-            self.result_label.config(text="Please load an image first")
+class ShelfClassifier:
+    def __init__(self, model_path):
+        self.model = load_model(model_path)
+
+    def classify_image(self, image_path):
+        image = cv2.imread(image_path)
+        image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+        resized_image = cv2.resize(image_rgb, (224, 224))
+        resized_image = resized_image.astype('float32') / 255
+        resized_image = np.expand_dims(resized_image, axis=0)
+        prediction = self.model.predict(resized_image)
+        class_index = np.argmax(prediction)
+        class_label = "Disorganized or Empty" if class_index == 1 else "Organized"
+        return class_label
 
 def main():
-    root = tk.Tk()
-    app = ShelfClassifierApp(root)
-    root.mainloop()
+    model_path = 'your_model.h5'
+    classifier = ShelfClassifier(model_path)
+    image_path = 'your_image.jpg'  # Change to your image path
+    result = classifier.classify_image(image_path)
+    print("Classification Result:", result)
 
 if __name__ == "__main__":
     main()