i'm stuck working on a Tensorflow Convolutional Neural Network for a university project and i hope somebody can help me.
it's supposed to output a picture for a picture input. left is input, right is output. both are in .jpeg format.
The weights look like this. left image shows the weights before learning, right is after a few epochs and it does not change at all with further training.
The net does not seem to learn anything useful and i have a feeling i forgot something basic. the accuracy peeks around 5% when learning
here is what it looks when i save the input image x
i dont know if i make a mistake loading or saving the image
And this is what the output y of the net looks like
i based the code on the tensorflow mnist tutorial. here is my code that i have shortened to make it more readable:
import tensorflow as tf
from PIL import Image
import numpy as np
def weight_variable(dim,stddev=0.35):
init = tf.random_normal(dim, stddev=stddev)
return tf.Variable(init)
def bias_variable(dim,val=0.1):
init = tf.constant(val, shape=dim)
return tf.Variable(init)
def conv2d(x,W):
return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding = 'SAME')
def max_pool2x2(x):
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding = 'SAME')
def output_pics(pic): # for weights
#1 color (dimension) array cast to uint8 and output as jpeg to file
def output_pics_color(pic):
#3 colors (dimensions) array cast to uint8 and output as jpeg to file
def show_pic(pic):
#3 colors (dimensions) array cast to uint8 and shown in window
filesX = [...] # filenames of inputs for training
filesY = [...] # filenames of outputsfor training
test_filesX = [...]# filenames of inputs for testing
test_filesY = [...]# filenames of outputs for testing
px_size = 128 # size of images 128x128 (resized)
filename_queueX = tf.train.string_input_producer(filesX)
filename_queueY = tf.train.string_input_producer(filesY)
filename_testX = tf.train.string_input_producer(test_filesY)
filename_testY = tf.train.string_input_producer(test_filesY)
image_reader = tf.WholeFileReader()
img_name, img_dataX = image_reader.read(filename_queueX)
imageX = tf.image.decode_jpeg(img_dataX)
imageX = tf.image.resize_images(imageX, [px_size,px_size])
imageX.set_shape((px_size,px_size,3))
imageX=tf.cast(imageX, tf.float32)
...
same for imageY, test_imageX, test_imageY
trainX = []
trainY = []
testX = []
testY = []
j=1
with tf.name_scope('model'):
x=tf.placeholder(tf.float32, [None, px_size,px_size,3])
prob = tf.placeholder(tf.float32)
init_op = tf.global_variables_initializer()
# load images into lists
with tf.Session() as sess:
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
for i in range(1,65):
trainX.append(imageX.eval())
trainY.append(imageY.eval())
for i in range(1, 10):
testX.append(test_imageX.eval())
testY.append(test_imageY.eval())
coord.request_stop()
coord.join(threads)
# layer 1
x_img = tf.reshape(x,[-1,px_size,px_size, 3])
W1 = weight_variable([20,20,3,3])
b1 = bias_variable([3])
y1 = tf.nn.softmax(conv2d(x_img,W1)+b1)
# layer 2
W2 = weight_variable([30,30,3,3])
b2 = bias_variable([3])
y2=tf.nn.softmax(conv2d(y1, W2)+b2)
# layer 3
W3 = weight_variable([40,40,3,3])
b3 = bias_variable([3])
y3=tf.nn.softmax(conv2d(y2, W3)+b3)
y = y3
with tf.name_scope('train'):
y_ =tf.placeholder(tf.float32, [None, px_size,px_size,3])
cross_entropy = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y_, logits=y))
opt = tf.train.MomentumOptimizer(learning_rate=0.5, momentum=0.1).minimize(cross_entropy)
with tf.name_scope('eval'):
correct = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))
nEpochs = 1000
batchSize = 10
res = 0
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
trAccs = []
for i in range(nEpochs):
if i%100 == 0 :
train_accuracy = sess.run(accuracy, feed_dict={x:trainX, y_:trainY, prob: 1.0})
print(train_accuracy)
output_pics(W1)#output weights of layer 1 to file
output_pics_color(x)#save input image
output_pics_color(y)#save net output
sess.run(opt, feed_dict={x:trainX, y_:trainY, prob: 0.5})
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.