model v1

main.py

@@ -1,17 +1,59 @@
-"""
-This is a starter file to get you going. You may also include other files if you feel it's necessary.
+import tensorflow as tf
+from sklearn.metrics import confusion_matrix, classification_report
+from tensorflow.keras import datasets, layers, models
+import matplotlib.pyplot as plt
+import numpy as np
 
-Make sure to follow the code convention described here:
-https://github.com/UWARG/computer-vision-python/blob/main/README.md#naming-and-typing-conventions
+def plot_sample(X, y, index):
+    plt.figure(figsize = (15, 2))
+    plt.imshow(X[index])
+    plt.xlabel(classes[y[index]])
+    plt.show()
 
-Hints:
-* The internet is your friend! Don't be afraid to search for tutorials/intros/etc.
-* We suggest using a convolutional neural network.
-* TensorFlow Keras has the CIFAR-10 dataset as a module, so you don't need to manually download and unpack it.
-"""
+(X_train, y_train), (X_test, y_test) = datasets.cifar10.load_data()
 
-# Import whatever libraries/modules you need
+classes = ["airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse", "ship", "truck"]
 
-import numpy as np
+y_train = y_train.reshape(-1,)
+
+X_train = X_train/255
+X_test = X_test/255
+
+cnn = models.Sequential([
+    layers.Conv2D(filters=32, kernel_size=(3, 3), activation='relu', input_shape=(32, 32, 3)),
+    layers.MaxPooling2D((2, 2)),
+
+    layers.Conv2D(filters=64, kernel_size=(3, 3), activation='relu'),
+    layers.MaxPooling2D((2, 2)),
+
+    layers.Flatten(),
+    layers.Dense(64, activation='relu'),
+    layers.Dense(10, activation='softmax')
+])
+
+cnn.compile(optimizer='adam',
+            loss='sparse_categorical_crossentropy',
+            metrics=['accuracy'])
+model_history = cnn.fit(X_train, y_train, epochs=10)
+cnn.evaluate(X_test, y_test)
+y_pred = cnn.predict(X_test)
+y_class = [np.argmax(element) for element in y_pred]
+
+def plot_loss():
+    plt.plot(model_history.history['loss'], label='loss')
+    plt.xlabel('Epoch')
+    plt.ylabel('Loss')
+    plt.legend(['Training', 'Test'])
+    plt.savefig('loss_mazin.png')
+    plt.close()
+
+def plot_accuracy():
+    plt.plot(model_history.history['accuracy'], label='accuracy')
+    plt.xlabel('Epoch')
+    plt.ylabel('Accuracy')
+    plt.legend(['Training', 'Test'])
+    plt.savefig('accuracy_mazin.png')
+    plt.close()
 
-# Your working code here
+plot_accuracy()
+plot_loss()