#%%
import tensorflow as tf
import numpy as np
#%%from tensorflow import placeholder
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("f:\python\data\mnist_data/", one_hot=true)
#%%#mnist 中每張共有28*28=784個畫素點
x = tf.placeholder(tf.float32, [none, 784], name="x")
#0-9 一共10個數字=>10個類別
y = tf.placeholder(tf.float32, [none, 10], name="y")
#%%#定義變數
w = tf.variable(tf.random_normal([784, 10]), name="w")
b = tf.variable(tf.zeros([10]), name="b")
#%%forword=tf.matmul(x, w) + b #前向計算
#%%train_epochs = 50 #訓練輪數
batch_size = 100 #單詞訓練樣本數(批次大小)
total_batch = int(mnist.train.num_examples/batch_size) #一輪訓練有多少批次
display_step = 1 #顯示粒度
learning_rate = 0.05 #學習率
#%%#結果分類
pred = tf.nn.softmax(forword) # softmax分類
#%%loss_function = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred),
reduction_indices=1)) #交叉熵
#%%optimizer = tf.train.gradientdescentoptimizer(learning_rate).minimize(loss_function) #梯度下降
#%%correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
#%%accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#%%arr1 = np.array([1,3,2,5,7,0])
arr2 = np.array([[1,2,3],[3,2,1],[4,7,2],[8,3,2]])
print("arr1=",arr1)
print("arr2=\n",arr2)
#%%sess = tf.session()
init = tf.global_variables_initializer()
sess.run(init)
#%%for epoch in range(train_epochs):
for batch in range(total_batch):
xs, ys = mnist.train.next_batch(batch_size)
sess.run(optimizer,feed_dict=)
loss,acc = sess.run([loss_function, accuracy],
feed_dict=)
if (epoch+1) % display_step == 0:
print("train epoch:",'%02d' % (epoch+1), "loss=","".format(loss),\
"accuracy=","".format(acc))
print("train finished")
#%%accu_test = sess.run(accuracy,
feed_dict=)
print("test accuracy:",accu_test)
#%%accu_validation = sess.run(accuracy,
feed_dict=)
print("test accuracy:",accu_validation)
#%%accu_train = sess.run(accuracy,
feed_dict=)
print("test accuracy:",accu_train)
#%%#進行**
prediction_result = sess.run(tf.argmax(pred,1),
feed_dict=)
#檢視**結果中的前10項
prediction_result[0:10]
#%%#定義視覺化函式
import matplotlib.pyplot as plt
def plot_images_labels_prediction(images,
labels,
prediction,
index,
num=10):
fig = plt.gcf() #獲取當前圖示,get current figure
fig.set_size_inches(10, 12) #1英吋等於2.54cm
if num > 25:
num = 25 #最多顯示25個子圖
for i in range(0, num):
ax = plt.subplot(5,5, i+1)
ax.imshow(np.reshape(images[index],(28,28)),
cmap='binary')
title = "label=" + str(np.argmax(labels[index]))
if len(prediction)>0:
title = "label=" +str(np.argmax(labels[index]))
ax.set_title(title,fontsize=10)
ax.set_xticks()
ax.set_yticks()
index += 1
plt.show()
#%%plot_images_labels_prediction(mnist.test.images,
mnist.test.labels,
prediction_result,10,10)
#%%plot_images_labels_prediction(mnist.test.images,
mnist.test.labels,
prediction_result,10,25)
#%%
mnist手寫數字識別
import tensorflow as tf import numpy as np from tensorflow.contrib.learn.python.learn.datasets.mnist import read data sets mnist read data sets f pyth...
MNIST手寫數字識別 tensorflow
神經網路一半包含三層，輸入層 隱含層 輸出層。如下圖所示 現以手寫數字識別為例 輸入為784個變數，輸出為10個節點，10個節點再通過softmax啟用函式轉化為 值。如下，準確率可達0.9226 import tensorflow as tf from tensorflow.examples.tu...
DNN識別mnist手寫數字
提取碼 sg3f 導庫import numpy as np import matplotlib.pyplot as plt import tensorflow as tf from tensorflow import keras from tensorflow.keras import layers...