Tensorflow CNN with custom images with RGB values - python-3.x

Question

I have followed tutorials on creating a CNN with the MNIST dataset, and understands most of it. Then I tried to convert it into my own custom images with RGB values. But have trouble in certain parts of the code, as I do not fully understands what happens and how to proceed next. I know I have to change the channels to 3, but does not know if the rest of the helper functions are correct? I also do not understand when I have initialized everything how to train it. Because of the batch_x, batch_y = iterator.get_next()
I am not able to use the feed_dict, and do not how to train this? On the MNIST data it was possible to set the dropout, but how can i specify this now? And as far as a I understand, I do not train it on the real data know?
How can I also calculate the result in the same way as with the MNIST data, when I create and test the validation data?
The code looks like this:
import tensorflow as tf
import process_images as image_util
from tensorflow.contrib.data import Dataset, Iterator
# With MNIST
#from tensorflow.examples.tutorials.mnist import input_data
#mnist = input_data.read_data_sets("MNISt_data/", one_hot=True)
filenames_dummy, labels_dummy = image_util.run_it()
#The filenames_dummy and labels_dummy are two lists looking like this, respectively:
#["data/image_1.png", "data/image_2.png", ..., "data/image_n.png"]
# The values of the labels are 0-3, since I have 4 classes.
#[0, 1, ..., 3]
filenames = tf.constant(filenames_dummy)
labels = tf.constant(labels_dummy)
def _parse_function(filename, label):
image_string = tf.read_file(filename)
image_decoded = tf.image.decode_png(image_string, channels=3)
# The image size is 425x425.
image_resized = tf.image.resize_images(image_decoded, [425,425])
return image_resized, label
dataset = tf.contrib.data.Dataset.from_tensor_slices((filenames, labels))
dataset = dataset.map(_parse_function)
dataset = dataset.batch(30)
dataset = dataset.repeat()
iterator = dataset.make_one_shot_iterator()
# Helper functions
# INIT weights
def init_weights(shape):
init_random_dist = tf.truncated_normal(shape, stddev=0.1)
return(tf.Variable(init_random_dist))
# INIT Bias
def init_bias(shape):
init_bias_vals = tf.constant(0.1, shape=shape)
return tf.Variable(init_bias_vals)
# CONV2D
def conv2d(x, W):
# x --> input tensor [batch, H, W, Channels]
# W --> [filter H, filter W, Channels IN, Channels OUT]
return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')
# Pooling
def max_pooling_2by2(x):
# x --> [batch, h, w, c]
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
#Convolutional layer
def convolutional_layer(input_x, shape):
W =init_weights(shape)
b = init_bias([shape[3]])
return tf.nn.relu(conv2d(input_x, W)+b)
# Normal (FULLY CONNTCTED)
def normal_full_layer(input_layer, size):
input_size = int(input_layer.get_shape()[1])
W = init_weights([input_size, size])
b = init_bias([size])
return tf.matmul(input_layer, W) + b
# PLACEHOLDERS
x = tf.placeholder(tf.float32, shape=[None, 180625])
y_true = tf.placeholder(tf.float32, shape=[None, 4])
# With MNIST
#x = tf.placeholder(tf.float32, shape=[None, 784])
#y_true = tf.placeholder(tf.float32, shape=[None, 10])
# Layers
x_image = tf.reshape(x, [-1, 425,425, 1])
# With MNIST
#x_image = tf.reshape(x, [-1, 28,28, 1])
convo_1 = convolutional_layer(x_image, shape=[5,5,1,32])
convo_1_pooling = max_pooling_2by2(convo_1)
convo_2 = convolutional_layer(convo_1_pooling, shape=[5,5,32, 64])
convo_2_pooling = max_pooling_2by2(convo_2)
convo_2_flat = tf.reshape(convo_2_pooling, [-1, 7*7*64])
full_layer_one = tf.nn.relu(normal_full_layer(convo_2_flat, 1024))
# Dropout
hold_prob = tf.placeholder(tf.float32)
full_one_dropout = tf.nn.dropout(full_layer_one, keep_prob=hold_prob)
y_pred = normal_full_layer(full_one_dropout, 4)
# With MNIST
#y_pred = normal_full_layer(full_one_dropout, 10)
# LOSS function
cross_entropy =
tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_true, logits=y_pred))
# Optimizer
optimizer = tf.train.AdamOptimizer(learning_rate=0.001)
train = optimizer.minimize(cross_entropy)
init = tf.global_variables_initializer()
steps = 5000
with tf.Session() as sess:
sess.run(init)
for i in range(steps):
batch_x, batch_y = iterator.get_next()
test1, test2 = sess.run([batch_x, batch_y])
# With MNIST
#sess.run(train, feed_dict={x:batch_x, y_true:batch_y, hold_prob:0.5})
if i%100 == 0:
print("ON STEP {}".format(i))
print("Accuracy: ")
matches = tf.equal(tf.argmax(y_pred, 1), tf.argmax(y_true, 1))
accuracy = tf.reduce_mean(tf.cast(matches, tf.float32))
# With MNIST
#print(sess.run(accuracy, feed_dict={x:mnist.test.images, y_true:mnist.test.labels, hold_prob:1.0}))