import keras
from keras.datasets import cifar10
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
 
import matplotlib.pyplot as plt
%matplotlib inline

# The data, shuffled and split between train and test sets:
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

x_train shape: (50000, 32, 32, 3)
50000 train samples
10000 test samples

## Each image is a 32 x 32 x 3 numpy array
x_train[444].shape

(32, 32, 3)

## Let's look at one of the images
 
print(y_train[444])
plt.imshow(x_train[444]);

[9]

num_classes = 10
 
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

# now instead of classes described by an integer between 0-9 we have a vector with a 1 in the (Pythonic) 9th position
y_train[444]

array([0., 0., 0., 0., 0., 0., 0., 0., 0., 1.])

# As before, let's make everything float and scale
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

keras.layers.convolutional.Conv2D(filters, kernel_size, strides=(1, 1), padding='valid', data_format=None, dilation_rate=(1, 1), activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None, **kwargs)

# Let's build a CNN using Keras' Sequential capabilities
 
model_1 = Sequential()
 
 
## 5x5 convolution with 2x2 stride and 32 filters
model_1.add(Conv2D(32, kernel_size = (5, 5), strides = (2,2), padding='same',
                 input_shape=x_train.shape[1:]))
model_1.add(Activation('relu'))
 
## Another 5x5 convolution with 2x2 stride and 32 filters
model_1.add(Conv2D(32, (5, 5), strides = (2,2), activation="relu")) # another way to define activation
 
 
## 2x2 max pooling reduces to 3 x 3 x 32
model_1.add(MaxPooling2D(pool_size=(2, 2)))
model_1.add(Dropout(0.25))
 
## Flatten turns 3x3x32 into 288x1
model_1.add(Flatten())
model_1.add(Dense(512))
model_1.add(Activation('relu'))
model_1.add(Dropout(0.5))
model_1.add(Dense(num_classes))
model_1.add(Activation('softmax'))
 
model_1.summary()

/usr/local/lib/python3.11/dist-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.
  super().__init__(activity_regularizer=activity_regularizer, **kwargs)
Model: "sequential"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ conv2d (Conv2D)                 │ (None, 16, 16, 32)     │         2,432 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ activation (Activation)         │ (None, 16, 16, 32)     │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ conv2d_1 (Conv2D)               │ (None, 6, 6, 32)       │        25,632 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ max_pooling2d (MaxPooling2D)    │ (None, 3, 3, 32)       │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout (Dropout)               │ (None, 3, 3, 32)       │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ flatten (Flatten)               │ (None, 288)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense (Dense)                   │ (None, 512)            │       147,968 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ activation_1 (Activation)       │ (None, 512)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dropout_1 (Dropout)             │ (None, 512)            │             0 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ dense_1 (Dense)                 │ (None, 10)             │         5,130 │
├─────────────────────────────────┼────────────────────────┼───────────────┤
│ activation_2 (Activation)       │ (None, 10)             │             0 │
└─────────────────────────────────┴────────────────────────┴───────────────┘
 Total params: 181,162 (707.66 KB)
 Trainable params: 181,162 (707.66 KB)
 Non-trainable params: 0 (0.00 B)

batch_size = 32
 
# initiate RMSprop optimizer
opt = keras.optimizers.RMSprop(learning_rate=0.0005)
 
# Let's train the model using RMSprop
model_1.compile(loss='categorical_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])
 
model_1.fit(x_train, y_train,
              batch_size=batch_size,
              epochs=15,
              validation_data=(x_test, y_test),
              shuffle=True)

Epoch 1/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 13s 6ms/step - accuracy: 0.3136 - loss: 1.8675 - val_accuracy: 0.4506 - val_loss: 1.5152
Epoch 2/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 6s 4ms/step - accuracy: 0.4739 - loss: 1.4538 - val_accuracy: 0.5385 - val_loss: 1.2852
Epoch 3/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 5s 3ms/step - accuracy: 0.5191 - loss: 1.3548 - val_accuracy: 0.5606 - val_loss: 1.2484
Epoch 4/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 6s 4ms/step - accuracy: 0.5435 - loss: 1.3027 - val_accuracy: 0.5620 - val_loss: 1.2574
Epoch 5/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 6s 4ms/step - accuracy: 0.5592 - loss: 1.2648 - val_accuracy: 0.5616 - val_loss: 1.2314
Epoch 6/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 6s 4ms/step - accuracy: 0.5674 - loss: 1.2424 - val_accuracy: 0.5452 - val_loss: 1.3458
Epoch 7/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 10s 4ms/step - accuracy: 0.5718 - loss: 1.2406 - val_accuracy: 0.5917 - val_loss: 1.1967
Epoch 8/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 5s 4ms/step - accuracy: 0.5748 - loss: 1.2402 - val_accuracy: 0.6114 - val_loss: 1.1200
Epoch 9/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 6s 4ms/step - accuracy: 0.5711 - loss: 1.2464 - val_accuracy: 0.5790 - val_loss: 1.2071
Epoch 10/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 10s 4ms/step - accuracy: 0.5820 - loss: 1.2403 - val_accuracy: 0.4886 - val_loss: 1.5045
Epoch 11/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 6s 4ms/step - accuracy: 0.5753 - loss: 1.2391 - val_accuracy: 0.6053 - val_loss: 1.1649
Epoch 12/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 10s 4ms/step - accuracy: 0.5779 - loss: 1.2530 - val_accuracy: 0.5396 - val_loss: 1.3305
Epoch 13/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 6s 4ms/step - accuracy: 0.5763 - loss: 1.2622 - val_accuracy: 0.5561 - val_loss: 1.2769
Epoch 14/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 6s 4ms/step - accuracy: 0.5788 - loss: 1.2512 - val_accuracy: 0.5679 - val_loss: 1.2698
Epoch 15/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 6s 4ms/step - accuracy: 0.5731 - loss: 1.2575 - val_accuracy: 0.5863 - val_loss: 1.2251
<keras.src.callbacks.history.History at 0x7b0b01452b50>

# Please provide your solution here
# Create model_2 as mentioned in the exercise

from tensorflow.keras.preprocessing.image import ImageDataGenerator
 
datagen = ImageDataGenerator(
    rotation_range=20,  # randomly rotate images in the range (degrees, 0 to 180)
    width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
    height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
    horizontal_flip=False,  # randomly flip images
    shear_range=0.1,   # Shear intensity (shear angle in counter-clockwise direction)
    zoom_range=0.1,    # Zoom in/out on images
    fill_mode='nearest'   # Strategy to fill in new pixels
    )

# Let's build a CNN using Keras' Sequential capabilities
model_1 = Sequential()
 
## 5x5 convolution with 2x2 stride and 32 filters
model_1.add(Conv2D(32, kernel_size = (5, 5), strides = (2,2), padding='same',
                 input_shape=x_train.shape[1:]))
model_1.add(Activation('relu'))
 
## Another 5x5 convolution with 2x2 stride and 32 filters
model_1.add(Conv2D(32, (5, 5), strides = (2,2), activation="relu")) # another way to define activation
 
 
## 2x2 max pooling reduces to 3 x 3 x 32
model_1.add(MaxPooling2D(pool_size=(2, 2)))
#model_1.add(Dropout(0.25))
 
## Flatten turns 3x3x32 into 288x1
model_1.add(Flatten())
model_1.add(Dense(512))
model_1.add(Activation('relu'))
#model_1.add(Dropout(0.5))
model_1.add(Dense(num_classes))
model_1.add(Activation('softmax'))
 
batch_size = 32
 
# Let's train the model using RMSprop
model_1.compile(loss='categorical_crossentropy',
                optimizer='rmsprop',
                metrics=['accuracy'])
 
# Fit the model on the batches generated by datagen.flow().
model_1.fit(
    datagen.flow(x_train, y_train, batch_size=batch_size),
    epochs=15,
    validation_data=(x_test, y_test)
)

Epoch 1/15
/usr/local/lib/python3.11/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.
  self._warn_if_super_not_called()
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 33s 20ms/step - accuracy: 0.3195 - loss: 1.8580 - val_accuracy: 0.5205 - val_loss: 1.3476
Epoch 2/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 30s 19ms/step - accuracy: 0.4840 - loss: 1.4376 - val_accuracy: 0.5217 - val_loss: 1.3634
Epoch 3/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 30s 19ms/step - accuracy: 0.5274 - loss: 1.3324 - val_accuracy: 0.5750 - val_loss: 1.1765
Epoch 4/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 41s 19ms/step - accuracy: 0.5594 - loss: 1.2471 - val_accuracy: 0.6083 - val_loss: 1.1206
Epoch 5/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 30s 19ms/step - accuracy: 0.5745 - loss: 1.2118 - val_accuracy: 0.6015 - val_loss: 1.1356
Epoch 6/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 29s 19ms/step - accuracy: 0.5858 - loss: 1.1726 - val_accuracy: 0.6154 - val_loss: 1.1121
Epoch 7/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 42s 19ms/step - accuracy: 0.6007 - loss: 1.1575 - val_accuracy: 0.6197 - val_loss: 1.0995
Epoch 8/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 33s 21ms/step - accuracy: 0.6035 - loss: 1.1363 - val_accuracy: 0.6273 - val_loss: 1.0985
Epoch 9/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 38s 19ms/step - accuracy: 0.6074 - loss: 1.1399 - val_accuracy: 0.6604 - val_loss: 0.9989
Epoch 10/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 31s 20ms/step - accuracy: 0.6181 - loss: 1.1066 - val_accuracy: 0.6279 - val_loss: 1.1005
Epoch 11/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 30s 19ms/step - accuracy: 0.6132 - loss: 1.1133 - val_accuracy: 0.6527 - val_loss: 1.0322
Epoch 12/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 31s 20ms/step - accuracy: 0.6201 - loss: 1.1032 - val_accuracy: 0.6485 - val_loss: 1.0506
Epoch 13/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 30s 19ms/step - accuracy: 0.6232 - loss: 1.1023 - val_accuracy: 0.6452 - val_loss: 1.0841
Epoch 14/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 31s 20ms/step - accuracy: 0.6258 - loss: 1.0899 - val_accuracy: 0.6548 - val_loss: 1.0765
Epoch 15/15
1563/1563 ━━━━━━━━━━━━━━━━━━━━ 29s 19ms/step - accuracy: 0.6221 - loss: 1.1078 - val_accuracy: 0.6285 - val_loss: 1.0848
<keras.src.callbacks.history.History at 0x7b0b01450390>