Attempting to use uninitialized value - even if I did initialization - tensorflow

Question

Error of initialization occurs even after global initialization
The error about initialization is this:
FailedPreconditionError: Attempting to use uninitialized value biases
[[Node: biases/read = IdentityT=DT_FLOAT, _class=["loc:#Adagrad/update_biases/ApplyAdagrad"], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]
import functools
def lazy_property(function):
attribute = '_cache_' + function.__name__
#property
#functools.wraps(function)
def decorator(self):
if not hasattr(self, attribute):
setattr(self, attribute, function(self))
return getattr(self, attribute)
return decorator
class Model:
def __init__(self, data, target):
self.data = data
self.target = target
self._logits = None
self._prediction = None
self._optimize = None
self._error = None
#lazy_property
def logits(self):
w = tf.Variable(tf.truncated_normal([784, 1]), name='weights')
b = tf.Variable(tf.zeros([1]), name='biases')
self._logits = tf.matmul(self.data, w) + b
return self._logits
#lazy_property
def prediction(self):
self._prediction = tf.nn.softmax(self.logits)
return self._prediction
#lazy_property
def optimize(self):
labels = tf.to_int64(self.target)
logits = self.prediction
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=labels, name='xentropy')
loss = tf.reduce_mean(cross_entropy, name='xentropy_mean')
self._optimize = tf.train.AdagradOptimizer(0.05).minimize(loss)
return self._optimize
#lazy_property
def error(self):
mistakes = tf.not_equal(tf.argmax(self.target, 1), tf.argmax(self.prediction, 1))
return tf.reduce_mean(tf.cast(mistakes, tf.float32))
batch_size = 100
num_steps = 1000
tf.reset_default_graph()
data = MNIST(data_dir="data/MNIST/")
X = tf.placeholder(tf.float32, [batch_size, 784], name='Placeholder_Input')
Y = tf.placeholder(tf.int64, [batch_size], name='Placeholder_Output')
model = Model(X, Y)
with tf.Session() as session:
session.run(tf.global_variables_initializer())
for step in range(num_steps):
model = Model(X,Y)
for _ in range(100):
x_batch, y_true_batch, _ = data.random_batch(batch_size=batch_size)
y_true_batch = np.argmax(y_true_batch, axis=1)
error,_ = session.run(model.optimize, feed_dict={X: x_batch, Y: y_true_batch})
if (step % 100 == 0):
print("Error rate # iter %d : %f" % (step, error))

Answer 1

You should run session.run(tf.global_variables_initializer()) once the model is fully defined. Note that you are defining a new model at each step, and the variables are only being instantiated when you call model.optimize. Here is my recommendation:
model = Model(X,Y)
optimize = model.optimize
with tf.Session() as session:
session.run(tf.global_variables_initializer())
for step in range(num_steps):
for _ in range(100):
x_batch, y_true_batch, _ = data.random_batch(batch_size=batch_size)
y_true_batch = np.argmax(y_true_batch, axis=1)
error,_ = session.run(optimize, feed_dict={X: x_batch, Y: y_true_batch})
if (step % 100 == 0):
print("Error rate # iter %d : %f" % (step, error))