Part 1 done. Made a complete.py file to make a complete.keras model

reaches 95+

Also made a bonus model that achieves 98%+

Part 1/MNIST-Complete.py

+import tensorflow as tf
+from tensorflow import keras
+
+tf.random.set_seed(1234)
+
+print("--Get data--")
+mnist = tf.keras.datasets.mnist
+(x_train, y_train), (x_test, y_test) = mnist.load_data()
+
+print("--Process data--")
+x_train, x_test = x_train / 255.0, x_test / 255.0
+
+print("--Make model--")
+model = tf.keras.models.Sequential([
+    tf.keras.layers.Flatten(input_shape=(28, 28, 1)),
+    tf.keras.layers.Dense(30, activation='relu'),
+    tf.keras.layers.Dropout(0.2),
+    tf.keras.layers.Dense(20, activation='relu'),
+    tf.keras.layers.Dropout(0.2),
+    tf.keras.layers.Dense(10, activation='softmax')
+])
+model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+
+print("--Fit model--")
+model.fit(x_train, y_train, epochs=10, verbose=2)
+
+print("--Evaluate model--")
+model_loss1, model_acc1 = model.evaluate(x_train,  y_train, verbose=2)
+model_loss2, model_acc2 = model.evaluate(x_test,  y_test, verbose=2)
+print(f"Train / Test Accuracy: {model_acc1*100:.1f}% / {model_acc2*100:.1f}%")
+
+#save - complete
+model.save("MNIST-Complete.keras")
+
+
+#load complete
+# loaded_model = tf.keras.models.load_model("MNIST-Complete.keras")
\ No newline at end of file

Part 1/MNIST-Complete98+.py

+import tensorflow as tf
+from tensorflow import keras # whats wrong?
+
+tf.random.set_seed(1234)
+
+print("--Get data--")
+mnist = tf.keras.datasets.mnist
+(x_train, y_train), (x_test, y_test) = mnist.load_data()
+
+print("--Process data--")
+x_train, x_test = x_train / 255.0, x_test / 255.0
+
+print("--Make model--")
+model = tf.keras.models.Sequential([
+    tf.keras.layers.Conv2D(16, (3, 3), activation='relu', input_shape=(28, 28, 1), padding='same', strides=(2, 2)),
+    tf.keras.layers.BatchNormalization(),
+    tf.keras.layers.MaxPooling2D((2, 2)),
+
+    # added kernel_regularizer to help
+    tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same', strides=(2, 2)),
+    tf.keras.layers.BatchNormalization(),
+    tf.keras.layers.MaxPooling2D((2, 2)),
+
+    tf.keras.layers.Conv2D(64, (3, 3), activation='relu', padding='same'),
+    tf.keras.layers.BatchNormalization(),
+    tf.keras.layers.MaxPooling2D((2, 2)),
+
+    tf.keras.layers.Flatten(input_shape=(28, 28, 1)),
+    tf.keras.layers.Dense(64, activation='relu'),
+    tf.keras.layers.Dropout(0.3),
+    tf.keras.layers.Dense(32, activation='relu'),
+    tf.keras.layers.Dropout(0.2),
+    tf.keras.layers.Dense(10, activation='softmax')
+])
+model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+
+print("--Fit model--")
+model.fit(x_train, y_train, epochs=20, verbose=2)
+
+print("--Evaluate model--")
+model_loss1, model_acc1 = model.evaluate(x_train,  y_train, verbose=2)
+model_loss2, model_acc2 = model.evaluate(x_test,  y_test, verbose=2)
+print(f"Train / Test Accuracy: {model_acc1*100:.1f}% / {model_acc2*100:.1f}%")
+
+#save - complete
+model.save("MNIST-Complete98+.keras")
+
+
+#load complete
+# loaded_model = tf.keras.models.load_model("MNIST-Complete.keras")
\ No newline at end of file

Part 1/MNIST-starter.py

+#Original Author: Jonathan Hudson
+#CPSC 501 W25
+
+import tensorflow as tf
+
+tf.random.set_seed(1234)
+
+print("--Get data--")
+mnist = tf.keras.datasets.mnist
+(x_train, y_train), (x_test, y_test) = mnist.load_data()
+
+print("--Process data--")
+x_train, x_test = x_train / 255.0, x_test / 255.0
+
+print("--Make model--")
+model = tf.keras.models.Sequential([
+  tf.keras.layers.Flatten(input_shape=(28, 28)),
+  tf.keras.layers.Dense(10, activation='softmax')
+])
+model.compile(optimizer='sgd', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+
+print("--Fit model--")
+model.fit(x_train, y_train, epochs=1, verbose=2)
+
+print("--Evaluate model--")
+model_loss1, model_acc1 = model.evaluate(x_train,  y_train, verbose=2)
+model_loss2, model_acc2 = model.evaluate(x_test,  y_test, verbose=2)
+print(f"Train / Test Accuracy: {model_acc1*100:.1f}% / {model_acc2*100:.1f}%")
\ No newline at end of file