import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# 讀取資料
mnist = input_data.read_data_sets("mnist_data/",one_hot=true)
# x為訓練影象的佔位符,y_為訓練影象標籤的佔位符
x = tf.placeholder(tf.float32, [none, 784])
y_ = tf.placeholder(tf.float32, [none, 10])
# 將單張從784維向量重新還原為28*28的矩陣
x_image = tf.reshape(x, [-1, 28, 28, 1])
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape = shape)
return tf.variable(initial)
def conv2d(x, w):
return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding="same")
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding="same")
# 第一層卷積層
w_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
# 第二層卷積層
w_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
# 全連線層,輸出為1024維的向量
w_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)
# 使用droput,keep_prob 是乙個佔位符,訓練時為0.5,測試時為1
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# 把1024維的向量轉換成10維,對應10個類別
w_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2
# 不採用先softmax再計算交叉熵的方法
# 而是用tf.nn.softmax_cross_entropy_with_logits直接計算
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y_conv))
# 同樣定義train_step
train_step = tf.train.adadeltaoptimizer(1e-4).minimize(cross_entropy)
# 定義測試的準確率
correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 建立session,對變數初始化
sess = tf.interactivesession()
sess.run(tf.global_variables_initializer())
# 訓練20000步
for i in range(20000):
batch = mnist.train.next_batch(50)
# 每100步報告一次在驗證集上的準確率
if i % 100 ==0:
train_accuracy = accuracy.eval(feed_dict=)
print("step %d, training accuracy %g" % (i, train_accuracy))
train_step.run(feed_dict=)
# 訓練結束後報告在測試集上的準確率
# 訓練結束後報告在測試集上的準確率
print("test accuracy %g" % accuracy.eval(feed_dict=))
兩層卷積網路 MNIST練習
原理參考 啟用函式 coding utf 8 import os os.environ tf cpp min log level 2 import tensorflow as tf from tensorflow.examples.tutorials.mnist import input data ...
PyTorch搭建兩層網路
舉乙個很簡單的例子來熟悉使用pytorch構建和訓練神經網路的整個過程。import torch import torch.nn as nn n,d in,h,d out 64,1000 100,10 隨機建立一些訓練資料 x torch.randn n,d in y torch.randn n,d...
兩層網路 三層網路的理解
對於搞it的同行而言,大部分人都不會直接和網路打交道,因此除非從事網路開發,否則對網路內部機制也不會太關心,但是明白網路資料是怎麼走的,這對每個it工程師應該是很重要的基礎知識。網路資料報如何在網路上遊蕩,長久以來也困擾了我很長時間,現在把這部分內容總結分享一下。說起網路,大家不約而同會想起大學課本...