我们都知道,深度学习需要大量的训练样本,目前处于搭建框架的初学阶段,且资源有限,自己用极其少量的图像做训练和测试的样本实验.以下为源码,自己做个记录,仅供参口,后续会增加样本数量,更改图像读取方式,进行模型源码补充.
from __future__ import print_function
import tensorflow as tf
#from tensorflow.examples.tutorials.mnist import input_data
import matplotlib.pyplot as plt
from pylab import *
from PIL import Image
import cv2.cv as cv
import numpy
def getImage(nth):
image_raw_data_jpg = tf.gfile.FastGFile(str(nth)+'.jpg', 'r').read()
with tf.Session() as sess:
img_data_jpg = tf.image.decode_jpeg(image_raw_data_jpg)
img_data_jpg = tf.image.convert_image_dtype(img_data_jpg, dtype=tf.uint8)#float32 uint8 tf.uint32 tf.uint8
resized_image = tf.image.resize_images(img_data_jpg,28,28, method=0)
grayed_image = tf.image.rgb_to_grayscale(resized_image)
grayed_image = grayed_image.eval()[:,:,0]
grayed_image = grayed_image.reshape((-1))
return grayed_image
def compute_accuracy(v_xs, v_ys):
global prediction
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, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
return result
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):
# 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')
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
ys = tf.placeholder(tf.float32, [None, 10])##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_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
# [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
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)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
## func2 layer ##
W_fc2 = weight_variable([1024, 10])##10
b_fc2 = bias_variable([10])##10
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + 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
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
sess = tf.Session()
# important step
sess.run(tf.initialize_all_variables())
p1=getImage(1)
p2=getImage(2)
p3=getImage(3)
p4=getImage(4)
p5=getImage(5)
p6=getImage(6)
p7=getImage(7)
p8=getImage(8)
p9=getImage(9)
p10=getImage(10)
p11=getImage(11)
pImages= [p1,p2,p3,p4,p5,p6,p7,p8,p9,p10,p11]#,p12]
pLable=[[1,0,0,0,0,0,0,0,0,0],[1,0,0,0,0,0,0,0,0,0],[1,0,0,0,0,0,0,0,0,0],[1,0,0,0,0,0,0,0,0,0],[1,0,0,0,0,0,0,0,0,0],[1,0,0,0,0,0,0,0,0,0],[0,1,0,0,0,0,0,0,0,0],[1,0,0,0,0,0,0,0,0,0],[0,1,0,0,0,0,0,0,0,0],[0,1,0,0,0,0,0,0,0,0],[0,1,0,0,0,0,0,0,0,0]]
for i in range(0,11):
batch_xs = pImages[:][0:i]
batch_xs.extend(pImages[:][i+1:11])
batch_ys = pLable[0:i][:]
batch_ys.extend(pLable[i+1:11][:])
sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
batch_ys[3:4][0]=0
print(compute_accuracy(pImages[:][i:11],pLable[i:11][:]))
print(compute_accuracy(pImages,pLable))