训练部分
import numpy as np
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
# number 1 to 10 data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
def compute_accuracy(v_xs, v_ys):
global prediction
global accuracy
y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
result = sess.run(accuracy)
# correct_prediction = np.mean(np.argmax(y_pre, axis = 1) == np.argmax(v_ys, axis = 1))
# result = correct_prediction
return result
def weight_variable(shape, name='weight'):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial, name)
def bias_variable(shape, name='b'):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial, name)
def conv2d(x, W):
# stride [1, x_movement, y_movement, 1]
# Must have strides[0] = strides[3] = 1
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
# stride [1, x_movement, y_movement, 1]
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# three optimistic method
#1.R 衰减 2.Regulation 3.滑动平均 窗口
LEARNING_RATE_BASE= 0.0008 #基础 学习 率
LEARNING_RATE_DECAY = 0.99 #衰减率
REGULARIZATION_RATE = 0.0001 #Regulation
MOVING_AVERAGE_DECAY = 0.99 # 滑动平均 衰减率
global_step = tf.Variable(0, trainable=False)
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])
# print(x_image.shape) # [n_samples, 28,28,1]
## conv1 layer ##
W_conv1 = weight_variable([5, 5, 1, 32]) # patch 5x5, in size 1, out size 32
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
h_pool1 = max_pool_2x2(h_conv1) # output size 14x14x32
## conv2 layer ##
W_conv2 = weight_variable([5, 5, 32, 64]) # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
h_pool2 = max_pool_2x2(h_conv2) # output size 7x7x64
## func1 layer ##
W_fc0 = weight_variable([7 * 7 * 64, 128])
b_fc0 = bias_variable([128])
W_fc1 = weight_variable([128, 2])
b_fc1 = bias_variable([2])
W_fc2 = weight_variable([2, 10], name='Weight')
b_fc2 = bias_variable([10], name='Bias')
#滑动 平均
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
#variables_averages_op = variable_averages.apply(tf.trainable_variables()) #在 没 有 指定 trainable = False 的 变量 生效
variables_averages_op = variable_averages.apply([W_fc1,b_fc1, W_fc2, b_fc2])
# [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc0 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc0) +b_fc0)
h_fc0_drop = tf.nn.dropout(h_fc0, keep_prob)
h_fc1 = tf.nn.relu(tf.matmul(h_fc0_drop, W_fc1) +b_fc1)
## func2 layer ##
tf.summary.histogram('Weight', W_fc2)
tf.summary.histogram('Bias', b_fc2)
y_conv = tf.matmul(h_fc1, W_fc2) + b_fc2
#prediction = tf.nn.softmax(y_conv) 需要 滑动平均 窗口 进行 预测
prediction = tf.nn.softmax(tf.matmul(h_fc1, variable_averages.average(W_fc2)) + variable_averages.average(b_fc2))
# the error between prediction and real data
# cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices=[1])) # loss
# cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, ys))
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_conv, labels=ys))
#reguraztion
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
regularization = regularizer(W_fc1) + regularizer(W_fc2)
loss = cross_entropy + regularization
#R 衰减 率
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples, LEARNING_RATE_DECAY)
train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss, global_step=global_step)
# train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy)
##每次 更新 W b 的 值 后 更新 滑动 平均 值
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name = 'train')
tf.summary.scalar('loss', loss)
merged = tf.summary.merge_all()
# summary writer goes in here
sess = tf.Session()
init = tf.global_variables_initializer()
train_writer = tf.summary.FileWriter("path/to/logs", sess.graph)
# test_writer = tf.summary.FileWriter("logs/test", sess.graph)
saver = tf.train.Saver()
# important step
sess.run(init)
print("begin train")
for i in range(5000):
global_step = + 1
batch_xs, batch_ys = mnist.train.next_batch(100)
batch_tx, batch_ty = mnist.test.next_batch(100)
#可以 使用 下面 注释 两行 替代
sess.run(train_op, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
#每次 更新 W b 的 值 后 更新 滑动 平均 值
#sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
#sess.run(variables_averages_op)
if i % 10 == 0:
# print(i)
# prediction = sess.run(prediction, feed_dict={xs : batch_tx, keep_prob: 0.5})
# print(prediction.shape)
# break
train_result = sess.run(merged, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 1})
test_result = sess.run(merged, feed_dict={xs: batch_tx, ys: batch_ty, keep_prob: 1})
train_writer.add_summary(train_result, i)
# test_writer.add_summary(test_result, i)
print(compute_accuracy(
batch_tx, batch_ty))
saver.save(sess, "save_path/mnist_2d.module")
测试部分
import numpy as np
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
import matplotlib.pyplot as plt
import numpy as np
# number 1 to 10 data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels
def compute_accuracy(v_xs, v_ys):
global prediction
global accuracy
y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
result = sess.run(accuracy)
# correct_prediction = np.mean(np.argmax(y_pre, axis = 1) == np.argmax(v_ys, axis = 1))
# result = correct_prediction
return result
def weight_variable(shape, name='weight'):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial, name)
def bias_variable(shape, name='b'):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial, name)
def conv2d(x, W):
# stride [1, x_movement, y_movement, 1]
# Must have strides[0] = strides[3] = 1
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
# stride [1, x_movement, y_movement, 1]
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# three optimistic method
#1.R 衰减 2.Regulation 3.滑动平均 窗口
LEARNING_RATE_BASE= 0.0008 #基础 学习 率
LEARNING_RATE_DECAY = 0.99 #衰减率
REGULARIZATION_RATE = 0.0001 #Regulation
MOVING_AVERAGE_DECAY = 0.99 # 滑动平均 衰减率
global_step = tf.Variable(0, trainable=False)
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])
# print(x_image.shape) # [n_samples, 28,28,1]
## conv1 layer ##
W_conv1 = weight_variable([5, 5, 1, 32]) # patch 5x5, in size 1, out size 32
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
h_pool1 = max_pool_2x2(h_conv1) # output size 14x14x32
## conv2 layer ##
W_conv2 = weight_variable([5, 5, 32, 64]) # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
h_pool2 = max_pool_2x2(h_conv2) # output size 7x7x64
## func1 layer ##
W_fc0 = weight_variable([7 * 7 * 64, 128])
b_fc0 = bias_variable([128])
W_fc1 = weight_variable([128, 2])
b_fc1 = bias_variable([2])
W_fc2 = weight_variable([2, 10], name='Weight')
b_fc2 = bias_variable([10], name='Bias')
#滑动 平均
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
#variables_averages_op = variable_averages.apply(tf.trainable_variables()) #在 没 有 指定 trainable = False 的 变量 生效
variables_averages_op = variable_averages.apply([W_fc1,b_fc1, W_fc2, b_fc2])
# [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc0 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc0) +b_fc0)
h_fc0_drop = tf.nn.dropout(h_fc0, keep_prob)
h_fc1_ = tf.matmul(h_fc0_drop, W_fc1) +b_fc1
h_fc1 = tf.nn.relu(h_fc1_)
## func2 layer ##
tf.summary.histogram('Weight', W_fc2)
tf.summary.histogram('Bias', b_fc2)
y_conv = tf.matmul(h_fc1, W_fc2) + b_fc2
#prediction = tf.nn.softmax(y_conv) 需要 滑动平均 窗口 进行 预测
prediction = tf.nn.softmax(tf.matmul(h_fc1, variable_averages.average(W_fc2)) + variable_averages.average(b_fc2))
# the error between prediction and real data
# cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices=[1])) # loss
# cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, ys))
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_conv, labels=ys))
#reguraztion
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
regularization = regularizer(W_fc1) + regularizer(W_fc2)
loss = cross_entropy + regularization
#R 衰减 率
learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples, LEARNING_RATE_DECAY)
train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss, global_step=global_step)
# train_step = tf.train.GradientDescentOptimizer(1e-3).minimize(cross_entropy)
##每次 更新 W b 的 值 后 更新 滑动 平均 值
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name = 'train')
tf.summary.scalar('loss', loss)
merged = tf.summary.merge_all()
# summary writer goes in here
sess = tf.Session()
init = tf.global_variables_initializer()
train_writer = tf.summary.FileWriter("path/to/logs", sess.graph)
# test_writer = tf.summary.FileWriter("logs/test", sess.graph)
sess = tf.Session()
init = tf.global_variables_initializer()
# important step
sess.run(init)
saver = tf.train.Saver()
saver.restore(sess, "save_path/mnist_2d.module")
global test_result
global batch_ty
sample = 20000
batch_tx, batch_ty = mnist.test.next_batch(sample)
test_result = sess.run(h_fc1_, feed_dict={xs: batch_tx, ys: batch_ty, keep_prob: 1})
print(compute_accuracy(batch_tx, batch_ty))
#print(test_result)
batch_ty = np.argmax(batch_ty, axis=1)
print(batch_ty[0:10])
fig = plt.figure()
ax1 = fig.add_subplot(111)
# 设置标题
ax1.set_title('Scatter Plot')
# 设置X轴标签
plt.xlabel('X')
# 设置Y轴标签
plt.ylabel('Y')
# 画散点图
cValue = ['pink','orange','g','cyan','r','y','gray','purple','black', 'b']
# 0 粉红 1 橙色 2 绿色 3 青色 4 红色 5 黄色 6 灰色 7 紫色 8 黑色 9蓝色
for i in range(0, 10):
# print(test_result[:, 0])
x = []
y = []
for j in range(0, sample):
if i == batch_ty[j]:
x.append(test_result[j, 0])
y.append(test_result[j, 1])
# if (test_result[j, 0] + test_result[j, 1]) < 10:
# im = np.array(batch_tx[0])
# im = im.reshape(28, 28)
# plt.imshow(im, cmap='gray')
# plt.show()
ax1.scatter(x, y, c=cValue[i], marker='.')
# 设置图标
plt.legend('x1')
# 显示所画的图
plt.show()
结果图
