这是我改写的代码，可以运行，但是过拟合现象严重，不知道怎么修改比较好
# -*- coding: utf-8 -*-
"""
Created on Wed Dec 20 14:45:35 2017
@author: Administrator
"""
#coding:utf-8
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
import tensorflow as tf
import numpy as np
data_name = 'YaleB_32x32.mat'
sele_num = 10
import matlab.engine
eng = matlab.engine.start_matlab()
t = eng.data_imread_MSE(data_name,sele_num)
eng.quit()
#t = np.array(t)
Train_Ma = np.array(t[0]).astype(np.float32)
Train_Lab = np.array(t[1]).astype(np.int8)
Test_Ma = np.array(t[2]).astype(np.float32)
Test_Lab = np.array(t[3]).astype(np.int8)
Num_fea = Train_Ma.shape[1]
Num_Class = Train_Lab.shape[1]
image_row = 32
image_column = 32
def conv_op(input_op, name, kh, kw, n_out, dh, dw, p):
n_in = input_op.get_shape()[-1].value
with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope+"w",
shape=[kh, kw, n_in, n_out],
dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer_conv2d())
conv = tf.nn.conv2d(input_op, kernel, (1, dh, dw, 1), padding='SAME')
bias_init_val = tf.constant(0.0, shape=[n_out], dtype=tf.float32)
biases = tf.Variable(bias_init_val, trainable=True, name='b')
z = tf.nn.bias_add(conv, biases)
activation = tf.nn.relu(z, name=scope)
p += [kernel, biases]
return activation
# 全连接层函数
def fc_op(input_op, name, n_out, p):
n_in = input_op.get_shape()[-1].value
with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope+"w",
shape=[n_in, n_out],
dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer())
biases = tf.Variable(tf.constant(0.1, shape=[n_out], dtype=tf.float32), name='b')
activation = tf.nn.relu_layer(input_op, kernel, biases, name=scope)
p += [kernel, biases]
return activation
def mpool_op(input_op, name, kh, kw, dh, dw):
return tf.nn.max_pool(input_op,
ksize=[1, kh, kw, 1],
strides=[1, dh, dw, 1],
padding='SAME',
name=name)
# assume input_op shape is 224x224x3
sess = tf.InteractiveSession()
# ---------- 定义 输入和输出 --------------- #
x = tf.placeholder(tf.float32, [None, Num_fea])
y_ = tf.placeholder(tf.float32, [None, Num_Class])
x_image = tf.reshape(x, [-1,image_row,image_column,1])
keep_prob = tf.placeholder(tf.float32)
# block 1 -- outputs 112x112x64
p = []
conv1_1 = conv_op(x_image, name="conv1_1", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
conv1_2 = conv_op(conv1_1, name="conv1_2", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
pool1 = mpool_op(conv1_2, name="pool1", kh=2, kw=2, dw=2, dh=2)
# block 2 -- outputs 56x56x128
conv2_1 = conv_op(pool1, name="conv2_1", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
conv2_2 = conv_op(conv2_1, name="conv2_2", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
pool2 = mpool_op(conv2_2, name="pool2", kh=2, kw=2, dh=2, dw=2)
# # block 3 -- outputs 28x28x256
conv3_1 = conv_op(pool2, name="conv3_1", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_2 = conv_op(conv3_1, name="conv3_2", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_3 = conv_op(conv3_2, name="conv3_3", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
pool3 = mpool_op(conv3_3, name="pool3", kh=2, kw=2, dh=2, dw=2)
# block 4 -- outputs 14x14x512
conv4_1 = conv_op(pool3, name="conv4_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_2 = conv_op(conv4_1, name="conv4_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_3 = conv_op(conv4_2, name="conv4_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool4 = mpool_op(conv4_3, name="pool4", kh=2, kw=2, dh=2, dw=2)
# block 5 -- outputs 7x7x512
conv5_1 = conv_op(pool4, name="conv5_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_2 = conv_op(conv5_1, name="conv5_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_3 = conv_op(conv5_2, name="conv5_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool5 = mpool_op(conv5_3, name="pool5", kh=2, kw=2, dw=2, dh=2)
# flatten
shp = pool5.get_shape()
flattened_shape = shp[1].value * shp[2].value * shp[3].value
resh1 = tf.reshape(pool5, [-1, flattened_shape], name="resh1")
# fully connected
fc6 = fc_op(resh1, name="fc6", n_out=4096, p=p)
fc6_drop = tf.nn.dropout(fc6, keep_prob, name="fc6_drop")
fc7 = fc_op(fc6_drop, name="fc7", n_out=4096, p=p)
fc7_drop = tf.nn.dropout(fc7, keep_prob, name="fc7_drop")
fc8 = fc_op(fc7_drop, name="fc8", n_out=Num_Class, p=p)
predictions = tf.nn.softmax(fc8)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(predictions), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(predictions,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.global_variables_initializer().run()
for i in range(1000):
train_accuracy = accuracy.eval(feed_dict={
x:Train_Ma, y_: Train_Lab, keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: Train_Ma, y_: Train_Lab, keep_prob: 0.8})
print("test accuracy %g"%accuracy.eval(feed_dict={
x: Test_Ma, y_: Test_Lab, keep_prob: 1.0}))
另外一种更简便的改写
# -*- coding: utf-8 -*-
"""
Created on Wed Dec 20 15:40:44 2017
@author: Administrator
"""
# -*- coding: utf-8 -*-
"""
Created on Wed Dec 20 14:45:35 2017
@author: Administrator
"""
#coding:utf-8
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
import tensorflow as tf
import numpy as np
data_name = 'YaleB_32x32.mat'
sele_num = 10
import matlab.engine
eng = matlab.engine.start_matlab()
t = eng.data_imread_MSE(data_name,sele_num)
eng.quit()
#t = np.array(t)
Train_Ma = np.array(t[0]).astype(np.float32)
Train_Lab = np.array(t[1]).astype(np.int8)
Test_Ma = np.array(t[2]).astype(np.float32)
Test_Lab = np.array(t[3]).astype(np.int8)
Num_fea = Train_Ma.shape[1]
Num_Class = Train_Lab.shape[1]
image_row = 32
image_column = 32
def conv_op(input_op, name, kh, kw, n_out, dh, dw, p):
n_in = input_op.get_shape()[-1].value
with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope+"w",
shape=[kh, kw, n_in, n_out],
dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer_conv2d())
conv = tf.nn.conv2d(input_op, kernel, (1, dh, dw, 1), padding='SAME')
bias_init_val = tf.constant(0.0, shape=[n_out], dtype=tf.float32)
biases = tf.Variable(bias_init_val, trainable=True, name='b')
z = tf.nn.bias_add(conv, biases)
activation = tf.nn.relu(z, name=scope)
p += [kernel, biases]
return activation
# 全连接层函数
def fc_op(input_op, name, n_out, p):
n_in = input_op.get_shape()[-1].value
with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope+"w",
shape=[n_in, n_out],
dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer())
biases = tf.Variable(tf.constant(0.1, shape=[n_out], dtype=tf.float32), name='b')
activation = tf.nn.relu_layer(input_op, kernel, biases, name=scope)
p += [kernel, biases]
return activation
def mpool_op(input_op, name, kh, kw, dh, dw):
return tf.nn.max_pool(input_op,
ksize=[1, kh, kw, 1],
strides=[1, dh, dw, 1],
padding='SAME',
name=name)
# assume input_op shape is 224x224x3
# block 1 -- outputs 112x112x64
def inference_op(input_op, keep_prob):
p = []
# assume input_op shape is 224x224x3
# block 1 -- outputs 112x112x64
conv1_1 = conv_op(input_op, name="conv1_1", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
conv1_2 = conv_op(conv1_1, name="conv1_2", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
pool1 = mpool_op(conv1_2, name="pool1", kh=2, kw=2, dw=2, dh=2)
# block 2 -- outputs 56x56x128
conv2_1 = conv_op(pool1, name="conv2_1", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
conv2_2 = conv_op(conv2_1, name="conv2_2", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
pool2 = mpool_op(conv2_2, name="pool2", kh=2, kw=2, dh=2, dw=2)
# # block 3 -- outputs 28x28x256
conv3_1 = conv_op(pool2, name="conv3_1", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_2 = conv_op(conv3_1, name="conv3_2", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_3 = conv_op(conv3_2, name="conv3_3", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
pool3 = mpool_op(conv3_3, name="pool3", kh=2, kw=2, dh=2, dw=2)
# block 4 -- outputs 14x14x512
conv4_1 = conv_op(pool3, name="conv4_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_2 = conv_op(conv4_1, name="conv4_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_3 = conv_op(conv4_2, name="conv4_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool4 = mpool_op(conv4_3, name="pool4", kh=2, kw=2, dh=2, dw=2)
# block 5 -- outputs 7x7x512
conv5_1 = conv_op(pool4, name="conv5_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_2 = conv_op(conv5_1, name="conv5_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_3 = conv_op(conv5_2, name="conv5_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool5 = mpool_op(conv5_3, name="pool5", kh=2, kw=2, dw=2, dh=2)
# flatten
shp = pool5.get_shape()
flattened_shape = shp[1].value * shp[2].value * shp[3].value
resh1 = tf.reshape(pool5, [-1, flattened_shape], name="resh1")
# fully connected
fc6 = fc_op(resh1, name="fc6", n_out=4096, p=p)
fc6_drop = tf.nn.dropout(fc6, keep_prob, name="fc6_drop")
fc7 = fc_op(fc6_drop, name="fc7", n_out=4096, p=p)
fc7_drop = tf.nn.dropout(fc7, keep_prob, name="fc7_drop")
fc8 = fc_op(fc7_drop, name="fc8", n_out=Num_Class, p=p)
predictions = tf.nn.softmax(fc8)
return predictions, fc8, p
# ---------- 定义 输入和输出 --------------- #
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32, [None, Num_fea])
y_ = tf.placeholder(tf.float32, [None, Num_Class])
x_image = tf.reshape(x, [-1,image_row,image_column,1])
keep_prob = tf.placeholder(tf.float32)
predictions, fc8, p = inference_op(x_image, keep_prob)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(predictions), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(predictions,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.global_variables_initializer().run()
for i in range(100):
train_accuracy = accuracy.eval(feed_dict={
x:Train_Ma, y_: Train_Lab, keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict={x: Train_Ma, y_: Train_Lab, keep_prob: 0.8})
print("test accuracy %g"%accuracy.eval(feed_dict={
x: Test_Ma, y_: Test_Lab, keep_prob: 1.0}))