with graph.as_default():
training = tf.placeholder(dtype=tf.bool, name="is_training")
is_testing = tf.placeholder(dtype=bool, shape=(), name="is_testing")
# create global step for decaying learning rate
global_step = tf.Variable(0, trainable=False)
learning_rate = tf.train.exponential_decay(starting_rate,
global_step,
steps_per_epoch * epochs_per_decay,
decay_factor,
staircase=staircase)
with tf.name_scope('inputs') as scope:
image, label = read_and_decode_single_example(train_files, label_type="label_normal", normalize=False)
X_def, y_def = tf.train.shuffle_batch([image, label], batch_size=batch_size, capacity=2000,
min_after_dequeue=1000)
# Placeholders
X = tf.placeholder_with_default(X_def, shape=[None, 299, 299, 1])
y = tf.placeholder_with_default(y_def, shape=[None])
X = tf.cast(X, dtype=tf.float32)
# Convolutional layer 1
with tf.name_scope('conv1') as scope:
conv1 = tf.layers.conv2d(
X, # Input data
filters=32, # 32 filters
training = tf.placeholder(dtype=tf.bool, name="is_training")
is_testing = tf.placeholder(dtype=bool, shape=(), name="is_testing")
# create global step for decaying learning rate
global_step = tf.Variable(0, trainable=False)
learning_rate = tf.train.exponential_decay(starting_rate,
global_step,
steps_per_epoch *
epochs_per_decay,
decay_factor,
staircase=staircase)
with tf.name_scope('inputs') as scope:
image, label = read_and_decode_single_example(train_files,
label_type=how,
normalize=False,
distort=False)
X_def, y_def = tf.train.shuffle_batch([image, label],
batch_size=batch_size,
capacity=2000,
seed=None,
min_after_dequeue=1000)
# Placeholders
X = tf.placeholder_with_default(X_def, shape=[None, 288, 288, 1])
y = tf.placeholder_with_default(y_def, shape=[None, 288, 288, 1])
# cast to float and scale input data
X_adj = tf.cast(X, dtype=tf.float32)
X_adj = _scale_input_data(X_adj,
