How to save and load Keras models
Ref：https://machinelearningmastery.com/save-load-keras-deep-learning-models/
'''
from future import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
import tensorflow as tf
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
tf.keras.backend.set_session(tf.Session(config=config))
batch_size = 128
num_classes = 10
epochs = 9
input image dimensions
img_rows, img_cols = 28, 28
the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
model.save('mnist.h5')
print('Saved model to disk')
'''
CNN visualization
Ref: https://www.kaggle.com/amarjeet007/visualize-cnn-with-keras
'''
load and evaluate a saved model
import tensorflow as tf
import numpy as np
from keras.datasets import mnist
from keras.models import load_model
import matplotlib.pyplot as plt
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
tf.keras.backend.set_session(tf.Session(config=config))
How to save and load keras model?
ref: https://machinelearningmastery.com/save-load-keras-deep-learning-models/
load model
model = load_model('mnist.h5')
summarize model
model.summary()
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train/=255
x_test/=255
x_train.shape
plt.imshow(np.squeeze(x_train[65]), cmap='gray')
plt.show()
x_train[65] with shape (1, 28, 28)
conv2d_1_input should have 4 dimensions
img = np.expand_dims(x_train[65], axis=0)
predict = model.predict(img)
print(predict)
print('predict shape', predict.shape)
from keras.models import Model
layer_outputs = [layer.output for layer in model.layers]
activation_model = Model(inputs=model.input, outputs=layer_outputs)
activations = activation_model.predict(img)
def display_activation(activations, col_size, row_size, act_index):
activation = activations[act_index]
print('activation:', activation.shape )
activation_index=0
fig, ax = plt.subplots(row_size, col_size, figsize=(row_size15,col_size9))
for row in range(0,row_size):
for col in range(0,col_size):
ax[row][col].imshow(activation[0, :, :, activation_index], cmap='gray')
activation_index += 1
display_activation(activations, 4, 8, 0)
plt.show()
display_activation(activations, 8, 8, 1)
plt.show()
'''
