AI人工智慧Keras實作神經網路模型之mnist手寫數字辨識

iPython code請進

print('神經網路模型')

import keras
keras.__version__

!nvcc --version

from keras.datasets import mnist

? mnist

import matplotlib.pyplot as plt
import numpy as np

(X_train, y_train), (X_test, y_test)=mnist.load_data()

X_train.shape

y_train.shape

np.set_printoptions(linewidth=np.inf)
X_train[7]

y_train[0:10]

plt.figure(figsize=(5, 5))
for i in range(9):
    plt.subplot(3, 3, i+1)
    plt.imshow(X_train[i])
plt.savefig("nums.jpg")
plt.show()

X_train=X_train.reshape(60000, 784).astype('float32')
X_test=X_test.reshape(10000, 784).astype('float32')

#normalizing
X_train/=255
X_test/=255
X_train[0]

from keras.models import Sequential

from tensorflow.keras.layers import Dense
from tensorflow.keras import optimizers
from tensorflow.keras.utils import *

n_class=10
y_train=to_categorical(y_train, n_class) #one-hot coding
y_test=to_categorical(y_test, n_class)

print('處理好了後面就是關鍵，剩下5個指令就好了')

model=Sequential()
model.add(Dense(64, activation='tanh', input_shape=(784, )))  #sigmoid, tanh, relu
model.add(Dense(10, activation='softmax'))

model.compile(
    loss='mean_squared_error',
    optimizer=optimizers.SGD(learning_rate=0.01), #隨機梯度下降法(Stochastic gradient descent, SGD)
    metrics=['accuracy']
)

model.fit(
    X_train, y_train, batch_size=128, epochs=200,
    verbose=1,
    validation_data=(X_test, y_test)
)