from keras.datasets import mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

train_images[0].shape, train_labels[0]

import jovian

jovian.log_dataset({
    'from': '2019-01-01',
    'to': '2019-02-01',
    'features': ['created_at']
})

%matplotlib inline
import matplotlib.pyplot as plt

grid_size = 6
f, axarr = plt.subplots(grid_size, grid_size)
for i in range(grid_size):
    for j in range(grid_size):
        ax = axarr[i, j]
        ax.get_xaxis().set_visible(False)
        ax.get_yaxis().set_visible(False)
        ax.imshow(train_images[i * grid_size + j], cmap='gray')

train_images = train_images.reshape((60000, 28, 28, 1))
train_images = train_images.astype('float32') / 255
test_images = test_images.reshape((10000, 28, 28, 1))
test_images = test_images.astype('float32') / 255

from keras.utils import to_categorical

partial_train_images = train_images[:45000]
partial_train_labels = train_labels[:45000]

validation_images = train_images[45000:]
validation_labels = train_labels[45000:]

partial_train_labels = to_categorical(partial_train_labels)
validation_labels = to_categorical(validation_labels)
test_labels = to_categorical(test_labels)

input_shape = (28,28,1)
num_classes = 10

from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28,28,1)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(num_classes, activation='softmax'))

model.summary()

from jovian.callbacks.keras import JovianKerasCallback

model.compile(
    optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'], 
              )

log_hyperparams

history = model.fit(
    partial_train_images, 
 
    partial_train_labels, 
    epochs=1, 
    batch_size=128, 
       callbacks=[JovianKerasCallback()],
    validation_data=(validation_images, validation_labels))

import matplotlib.pyplot as plt

acc = history.history['acc']
loss = history.history['loss']
val_acc = history.history['val_acc']
val_loss = history.history['val_loss']

epochs = range(1, len(acc) + 1)

plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.margins(0.05)

plt.figure()

plt.plot(epochs, loss, 'bo', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.margins(0.05)

plt.show()

test_loss, test_acc = model.evaluate(test_images, test_labels)

print('Test loss:', test_loss)
print('Test acc:', test_acc)

model.save('mnist-cnn.h5')

!pip install jovian --upgrade

import jovian

jovian.commit()