def main():
# image shape: N x H x W, pixel [0, 255]
# label shape: N x 10
with np.load(r'mnist.npz', allow_pickle=True) as f:
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
plt.imshow(x_train[59999], cmap='gray')
plt.show()
print(x_train.shape, x_train[0].max(), x_train[0].min()) #(60000, 28, 28) 255 0 5
print(x_test.shape, x_test[0].max(), x_test[0].min()) #(10000, 28, 28) 255 0 7
x_train = normalize_image(x_train)
x_test = normalize_image(x_test)
y_train = one_hot_labels(y_train)
y_test = one_hot_labels(y_test)
net = LeNet()
averagetime, _ = net.fit(x_train, y_train, x_test, y_test, epoches=10, batch_size=16, lr=1e-3)
accuracy = net.evaluate(x_test, labels=y_test)
print("final accuracy {}".format(accuracy))
print(averagetime,'s')
model = load_model(filename)
initial_epoch = int(filename.split('weights.')[-1].split('-')[0])
print('restore from ckpt, initial_echo = {0}'.format(initial_epoch))
print(model.summary())
tensorboard = TensorBoard(log_dir='./logs_lenet')
# weights.{epoch:02d}-{val_loss:.2f}.hdf5 : a kind of code rule
checkpointer = ModelCheckpoint(
filepath='./ckpt_lenet/weights.{epoch:02d}-{val_loss:.2f}.h5',
monitor='val_loss')
history = model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
callbacks=[tensorboard, checkpointer],
validation_data=(x_test, y_test),
initial_epoch=initial_epoch)
model.save('model/mnist_lenet.h5')
del model
model = load_model('model/mnist_lenet.h5')
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
