I made the code with tensorflow to train and test convolutional neural network. I use input with my own jpeg image. Image files are called as batch format by my own code, input_batch.py. After being called, convolution is proceeded with convpool.py. But now, my results in test data are returned with same values. Also in training, some batch data's convolution results are returned same.
I also looked at this issue, Tensorflow predicts always the same result but the solutions in this issue are failed to apply in my code.
My result always return like this :
step 0, training accuracy 0.2
result: [[ 5.76441448e-18 1.00000000e+00]
[ 5.76441448e-18 1.00000000e+00]
[ 5.76441448e-18 1.00000000e+00]
[ 5.76441448e-18 1.00000000e+00]
[ 5.76441448e-18 1.00000000e+00]
[ 5.76441448e-18 1.00000000e+00]
[ 5.76434913e-18 1.00000000e+00]
[ 5.85150709e-18 1.00000000e+00]
[ 2.83430459e-17 1.00000000e+00]
[ 0.00000000e+00 1.00000000e+00]]
test result:[[ 0. 1.]]actual result:[ 1. 0.]
test result:[[ 0. 1.]]actual result:[ 1. 0.]
test result:[[ 0. 1.]]actual result:[ 0. 1.]
test result:[[ 0. 1.]]actual result:[ 0. 1.]
test result:[[ 0. 1.]]actual result:[ 0. 1.]
test result:[[ 0. 1.]]actual result:[ 1. 0.]
test result:[[ 0. 1.]]actual result:[ 1. 0.]
test result:[[ 0. 1.]]actual result:[ 0. 1.]
test result:[[ 0. 1.]]actual result:[ 1. 0.]
test result:[[ 0. 1.]]actual result:[ 1. 0.]
and here is my code:
import tensorflow as tf
import input_batch
import input
import convpool
import matplotlib.pyplot as plt
import numpy as np
FLAGS = tf.app.flags.FLAGS
sess = tf.Session()
x_image = tf.placeholder("float", shape=[None,FLAGS.width,FLAGS.height,FLAGS.depth])
y_ = tf.placeholder("float", shape=[None,FLAGS.num_class])
# x_image=tf.reshape(x,[-1,FLAGS.width,FLAGS.height,FLAGS.depth])
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 spp_layer(x,n_bin,output_depth):
(a,b,c,d) = x.get_shape()
h = int(b+(n_bin-1))/n_bin
w = int(c+(n_bin-1))/n_bin
return tf.reshape(tf.nn.max_pool(x,ksize=[1, h, w, 1], strides=[1, h, w, 1], padding='SAME'),[-1, n_bin * n_bin , output_depth])
W_conv1 = weight_variable([11, 11, 3 , 96])
b_conv1 = bias_variable([96])
W_conv2 = weight_variable([5, 5, 96, 256])
b_conv2 = bias_variable([256])
W_fc1 = weight_variable([14*14* 256, 4096])
b_fc1 = bias_variable([4096])
W_fc2 = weight_variable([4096, 2])
b_fc2 = bias_variable([2])
keep_prob = tf.placeholder("float")
y_conv_train = convpool.train(x_image,W_conv1,b_conv1,W_conv2,b_conv2,W_fc1,b_fc1,W_fc2,b_fc2,keep_prob)
cross_entropy = -tf.reduce_mean(y_*tf.log(tf.clip_by_value(y_conv_train,1e-10,1.0)))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv_train,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,"float"))
sess = tf.Session()
sess.run(tf.initialize_all_variables())
for i in range(50):
batch = input_batch.get_data_jpeg(sess,'train',10)
if i%1==0:
train_accuracy = sess.run(accuracy,feed_dict={x_image:batch[0], y_:batch[1], keep_prob:1.0})
train_result = sess.run(y_conv_train, feed_dict={x_image: batch[0], y_: batch[1], keep_prob: 1.0})
# print('result : ', sess.run(W_fc2))
print("step %d, training accuracy %g" %(i,train_accuracy))
print('result:', train_result)
sess.run(train_step, feed_dict={x_image:batch[0], y_:batch[1], keep_prob:0.5})
# ############################test###################################
for i in range (10):
input.initialization()
testinput = input.get_data_jpeg(sess,'eval')
test_img = testinput.x_data
(i_x,i_y,i_z) = testinput.x_size
testimg = tf.reshape(test_img, [-1,i_x,i_y,i_z])
testresult=convpool.train(testimg,W_conv1,b_conv1,W_conv2,b_conv2,W_fc1,b_fc1,W_fc2,b_fc2,1.0)
result = sess.run(testresult)
print("test result:"+str(result)+ "actual result:"+ str(testinput.y_data))
#convpool.py
import tensorflow as tf
FLAGS = tf.app.flags.FLAGS
def train(input,W_conv1,b_conv1,W_conv2,b_conv2,W_fc1,b_fc1,W_fc2,b_fc2,keep_prob):
h_conv1 = tf.nn.relu(tf.nn.conv2d(input, W_conv1, strides=[1, 4, 4, 1], padding='SAME') + b_conv1)
h_pool1 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
h_conv2 = tf.nn.relu(tf.nn.conv2d(h_pool1, W_conv2, strides=[1, 1, 1, 1], padding='SAME') + b_conv2)
h_pool2 = tf.nn.max_pool(h_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# print(h_pool2)
h_pool2_flat = tf.reshape(h_pool2, [-1, 14*14 * 256])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
return y_conv
#input_batch.py
import os
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import random
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('data_dir', 'C://Users/sh/PycharmProjects/test2/data',
"""Directory where to write event logs """
"""and checkpoint.""")
FLAGS.width = 224
FLAGS.height = 224
FLAGS.depth = 3
FLAGS.num_class = 2
batch_index = 0
filenames = []
FLAGS.imsize = FLAGS.height * FLAGS.width * FLAGS.depth
def get_filenames(data_set):
global filenames
labels = [ ]
with open(FLAGS.data_dir + '/labels.txt') as f:
for line in f:
inner_list = [elt.strip() for elt in line.split(',')]
labels += inner_list
for i, label in enumerate(labels):
list = os.listdir(FLAGS.data_dir + '/' + data_set + '/' +label)
for filename in list:
filenames.append([label + '/' + filename, i])
random.shuffle(filenames)
def get_data_jpeg(sess, data_set, batch_size):
global batch_index, filenames
if len(filenames) == 0:
get_filenames(data_set)
max = len(filenames)
begin = batch_index
end = batch_index + batch_size
if end >= max:
end = max
batch_index = 0
x_data = np.array([])
y_data = np.zeros((batch_size, FLAGS.num_class))
index = 0
for i in range(begin, end) :
with tf.gfile.FastGFile(FLAGS.data_dir + '/' + data_set + '/' + filenames[i][0], 'rb') as f :
image_data = f.read()
decode_image = tf.image.decode_jpeg(image_data, channels=FLAGS.depth)
resized_image = tf.image.resize_images(decode_image, [FLAGS.height, FLAGS.width],method=1)
image = sess.run(resized_image)
x_data = np.append(x_data, np.asarray(image.data, dtype='float32'))/255
y_data[index][filenames[i][1]] = 1 batch_index += batch_size
try:
x_data = x_data.reshape(batch_size, FLAGS.height, FLAGS.width, FLAGS.depth)
except:
return None, None
return x_data, y_data
