1.原理图:
2.代码:
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets('data/', one_hot=True)
trainimg = mnist.train.images
trainlabel = mnist.train.labels
testimg = mnist.test.images
testlabel = mnist.test.labels
print ("MNIST ready")
n_input = 784
n_output = 10
weights = {
'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1)),
'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.1)),
'wd1': tf.Variable(tf.random_normal([7*7*128, 1024], stddev=0.1)),
'wd2': tf.Variable(tf.random_normal([1024, n_output], stddev=0.1))
}
biases = {
'bc1': tf.Variable(tf.random_normal([64], stddev=0.1)),
'bc2': tf.Variable(tf.random_normal([128], stddev=0.1)),
'bd1': tf.Variable(tf.random_normal([1024], stddev=0.1)),
'bd2': tf.Variable(tf.random_normal([n_output], stddev=0.1))
}
"""前向传播
卷积层1:3*3*1 -> 64
池化层1:2*2
卷积层2:3*3*64 ->128
池化层2:2*2
全连接层1:7*7*128 ->1024
全连接层2:1024 ->10
"""
def conv_basic(_input, _w, _b, _keepratio):
# INPUT
_input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
# CONV LAYER 1
_conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')
# _mean, _var = tf.nn.moments(_conv1, [0, 1, 2])
# _conv1 = tf.nn.batch_normalization(_conv1, _mean, _var, 0, 1, 0.0001)
_conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1']))
_pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
_pool_dr1 = tf.nn.dropout(_pool1, _keepratio)
# CONV LAYER 2
_conv2 = tf.nn.conv2d(_pool_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME')
# _mean, _var = tf.nn.moments(_conv2, [0, 1, 2])
# _conv2 = tf.nn.batch_normalization(_conv2, _mean, _var, 0, 1, 0.0001)
_conv2 = tf.nn.relu(tf.nn.bias_add(_conv2, _b['bc2']))
_pool2 = tf.nn.max_pool(_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
_pool_dr2 = tf.nn.dropout(_pool2, _keepratio)
# VECTORIZE
_dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])
# FULLY CONNECTED LAYER 1
_fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w['wd1']), _b['bd1']))
_fc_dr1 = tf.nn.dropout(_fc1, _keepratio)
# FULLY CONNECTED LAYER 2
_out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])
# RETURN
out = {'input_r': _input_r, 'conv1': _conv1, 'pool1': _pool1, 'pool1_dr1': _pool_dr1,
'conv2': _conv2, 'pool2': _pool2, 'pool_dr2': _pool_dr2, 'dense1': _dense1,
'fc1': _fc1, 'fc_dr1': _fc_dr1, 'out': _out
}
return out
print("CNN READY")
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
keepratio = tf.placeholder(tf.float32)
# FUNCTIONS
_pred = conv_basic(x, weights, biases, keepratio)['out']
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=_pred))
optm = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
_corr = tf.equal(tf.argmax(_pred, 1), tf.argmax(y, 1))
accr = tf.reduce_mean(tf.cast(_corr, tf.float32))
init = tf.global_variables_initializer()
# SAVER
save_step = 1
saver = tf.train.Saver(max_to_keep=3)
print("GRAPH READY")
do_train = 1
sess = tf.Session()
sess.run(init)
training_epochs = 15
batch_size = 16
display_step = 1
if do_train == 1:#训练
for epoch in range(training_epochs):
avg_cost = 0.
# total_batch = int(mnist.train.num_examples/batch_size)
total_batch = 10
# Loop over all batches
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
# Fit training using batch data
sess.run(optm, feed_dict={x: batch_xs, y: batch_ys, keepratio: 0.7})
# Compute average loss
avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio: 1.}) / total_batch
# Display logs per epoch step
if epoch % display_step == 0:
print("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, keepratio: 1.})
print(" Training accuracy: %.3f" % (train_acc))
# test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio:1.})
# print (" Test accuracy: %.3f" % (test_acc))
# Save Net
if epoch % save_step == 0:
saver.save(sess, "save/nets/cnn_mnist_basic.ckpt-" + str(epoch))
print("OPTIMIZATION FINISHED")
if do_train == 0:#测试
epoch = training_epochs - 1
saver.restore(sess, "save/nets/cnn_mnist_basic.ckpt-" + str(epoch))
test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio: 1.})
print(" TEST ACCURACY: %.3f" % (test_acc))
3.测试:
do_train=1
Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.
See `tf.nn.softmax_cross_entropy_with_logits_v2`.
GRAPH READY
2019-05-13 21:08:46.535000: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Epoch: 000/015 cost: 6.706351614
Training accuracy: 0.375
Epoch: 001/015 cost: 3.045194244
Training accuracy: 0.375
Epoch: 002/015 cost: 1.572650748
Training accuracy: 0.750
Epoch: 003/015 cost: 1.190892065
Training accuracy: 0.750
WARNING:tensorflow:From F:\python\shi_jue\venv\lib\site-packages\tensorflow\python\training\saver.py:966: remove_checkpoint (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to delete files with this prefix.
Epoch: 004/015 cost: 1.222349179
Training accuracy: 0.562
Epoch: 005/015 cost: 1.086833096
Training accuracy: 0.688
Epoch: 006/015 cost: 1.113742071
Training accuracy: 0.812
Epoch: 007/015 cost: 0.929461908
Training accuracy: 0.750
Epoch: 008/015 cost: 0.859379065
Training accuracy: 0.812
Epoch: 009/015 cost: 0.798095918
Training accuracy: 0.875
Epoch: 010/015 cost: 0.590675253
Training accuracy: 0.750
Epoch: 011/015 cost: 0.533954525
Training accuracy: 0.938
Epoch: 012/015 cost: 0.461822632
Training accuracy: 0.938
Epoch: 013/015 cost: 0.378245395
Training accuracy: 0.875
Epoch: 014/015 cost: 0.412136450
Training accuracy: 0.875
OPTIMIZATION FINISHED
do_train=0
