Update utils.py

utils.py

@@ -1,64 +1,26 @@
-import tensorflow as tf
-from tensorflow.keras.models import Sequential
-from tensorflow.keras.layers import Conv2D, Flatten, MaxPooling2D, Dense, Dropout, SpatialDropout2D
-from tensorflow.keras.losses import sparse_categorical_crossentropy, binary_crossentropy
-from tensorflow.keras.optimizers import Adam
-from tensorflow.keras.preprocessing.image import ImageDataGenerator
-import numpy as np
 from PIL import Image
+import numpy as np
+from Downloading_model import model_download
 
-def gen_labels():
-    train = 'Dataset'
-    train_generator = ImageDataGenerator(rescale=1/255)
-
-    train_generator = train_generator.flow_from_directory(train,
-                                                          target_size=(256, 256),
-                                                          batch_size=32,
-                                                          class_mode='sparse')
-    labels = train_generator.class_indices
-    labels = dict((v, k) for k, v in labels.items())
-
-    return labels
-
-data_augmentation = tf.keras.Sequential([
-    tf.keras.layers.experimental.preprocessing.Rescaling(1./127.5, offset= -1),
-    tf.keras.layers.experimental.preprocessing.RandomFlip("horizontal_and_vertical"),
-    tf.keras.layers.experimental.preprocessing.RandomRotation(0.2),
-    tf.keras.layers.experimental.preprocessing.RandomZoom(0.2)
-], name='data_augmentation')
-
-#Instantiating the base model
-input_shape = (256,256,3)
-base_model = tf.keras.applications.ResNet50V2(include_top=False, input_shape=input_shape)
-
-#Making the layers of the model trainable
-base_model.trainable = True
+labels = ['cardboard', 'glass', 'metal', 'paper', 'plastic', 'trash']
 
-def preprocess(img_path_or_img):
-    if isinstance(img_path_or_img, str):  # Check if input is a path
-        img = Image.open(img_path_or_img)
-    elif isinstance(img_path_or_img, Image.Image):  # Check if input is already an Image object
-        img = img_path_or_img
-    else:
-        raise ValueError("Input must be a string path or a PIL Image object.")
-    
+def preprocess_image(img_path):
+    img = Image.open(img_path)
     img = img.resize((256, 256))
     img_array = np.array(img)
+    img_array = np.expand_dims(img_array, axis=0)
     return img_array
 
-def model_arc():
-    model = tf.keras.Sequential([
-        data_augmentation,
-        base_model,
-        tf.keras.layers.GlobalAveragePooling2D(),
-        tf.keras.layers.Dense(6, activation='softmax')
-    ])
+# Function to classify the garbage
+def classify_garbage(img_path, model):
+    processed_img = preprocess_image(img_path)
+    prediction = model.predict(processed_img)
+
+    class_labels = ["cardboard", "glass", "metal", "paper", "plastic", "trash"]
+    predicted_class = np.argmax(prediction, axis=1)[0]
+    classification_result = class_labels[predicted_class]
 
-    learning_rate = 0.00001
-    model.compile(
-        loss='sparse_categorical_crossentropy',
-        optimizer=tf.keras.optimizers.Adam(learning_rate),
-        metrics=['accuracy']
-    )
+    # Get the confidence (probability) of the predicted class
+    confidence = prediction[0][predicted_class] * 100  # Convert probability to percentage
 
-    return model
+    return classification_result, confidence