Update burrito.py

burrito.py

@@ -10,8 +10,8 @@ IMG_SIZE = 224
 BATCH_SIZE = 32
 
 # Define train and validation directories
-train_dir = 'path/to/train/folder'
-val_dir = 'path/to/validation/folder'
+train_dir = 'm2rncvif2arzs1w3q44gfn\images.cv_m2rncvif2arzs1w3q44gfn\data\train\burrito'
+val_dir = 'm2rncvif2arzs1w3q44gfn\images.cv_m2rncvif2arzs1w3q44gfn\data\val\burrito'
 
 # Use ImageDataGenerator for data augmentation
 train_datagen = ImageDataGenerator(
@@ -39,46 +39,60 @@ val_generator = val_datagen.flow_from_directory(
     batch_size=BATCH_SIZE,
     class_mode='categorical')
 
-# Define the model
+# Define the model architecture
 model = Sequential()
 
-# Add convolutional layers
 model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(IMG_SIZE, IMG_SIZE, 3)))
 model.add(MaxPooling2D((2, 2)))
+
 model.add(Conv2D(64, (3, 3), activation='relu'))
 model.add(MaxPooling2D((2, 2)))
+
 model.add(Conv2D(128, (3, 3), activation='relu'))
 model.add(MaxPooling2D((2, 2)))
 
-# Flatten and add dense layers
+model.add(Conv2D(256, (3, 3), activation='relu'))
+model.add(MaxPooling2D((2, 2)))
+
 model.add(Flatten())
 model.add(Dense(512, activation='relu'))
 model.add(Dropout(0.5))
-model.add(Dense(3, activation='softmax'))
+model.add(Dense(2, activation='softmax'))
+
+# Compile the model with categorical crossentropy loss and Adam optimizer
+model.compile(loss='categorical_crossentropy',
+              optimizer='adam',
+              metrics=['accuracy'])
 
-# Compile the model
-model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
+# Define the number of training and validation steps per epoch
+train_steps_per_epoch = train_generator.samples // BATCH_SIZE
+val_steps_per_epoch = val_generator.samples // BATCH_SIZE
 
-# Train the model
-history = model.fit(
+# Train the model with fit_generator
+history = model.fit_generator(
     train_generator,
-    steps_per_epoch=train_generator.samples // BATCH_SIZE,
-    epochs=50,
+    steps_per_epoch=train_steps_per_epoch,
+    epochs=10,
     validation_data=val_generator,
-    validation_steps=val_generator.samples // BATCH_SIZE)
-
-# Load an image
-img_path = 'path/to/image.jpg'
-img = image.load_img(img_path, target_size=(IMG_SIZE, IMG_SIZE))
-
-# Convert the image to a numpy array and normalize it
-img_array = image.img_to_array(img) / 255.
-
-# Expand the dimensions of the array to match the model input shape
-img_array = np.expand_dims(img_array, axis=0)
-
-# Use the model to predict the class probabilities
-probs = model.predict(img_array)[0]
-
-# Print the predicted class probabilities
-print(probs)
+    validation_steps=val_steps_per_epoch)
+
+# Path to directory with burrito images
+dir_path = 'm2rncvif2arzs1w3q44gfn\images.cv_m2rncvif2arzs1w3q44gfn\data\test\burrito'
+
+# Loop through all images in the directory
+for img_file in os.listdir(dir_path):
+    # Load and preprocess the image
+    img_path = os.path.join(dir_path, img_file)
+    img = image.load_img(img_path, target_size=(IMG_SIZE, IMG_SIZE))
+    img_array = image.img_to_array(img)
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array /= 255.0
+
+    # Make a prediction
+    prediction = model.predict(img_array)
+
+    # Print the prediction result
+    if prediction[0][0] > prediction[0][1]:
+        print('{}: Not a burrito'.format(img_file))
+    else:
+        print('{}: Burrito!'.format(img_file))