Tensorflow reporting wrong AUC - tensorflow

Question

I have an issue while using AUC from tensorflow library. I train my model (convolutional neural network) per batch ( i do not use a validation set) and after each epoch I use an independent test set to obtain my evaluations. The problem lies within AUC evaluation.
In each batch I calculate AUC/Accuracy/Loss/Precision/Recall/F1_score for the training set and then I aggregate the mean of these scores. When I try to do the same for the test set I again calculate the same scores. I notice that all scores except AUC have different values. I think it is not correct test's loss function to increase and AUC to increase as well. And the problem is that test's AUC is almost identical to training's AUC (even though their accuracy, loss error are completely different).
with tf.name_scope("output"):
W = tf.Variable(tf.truncated_normal([num_filters_total, num_classes], stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b")
scores = tf.nn.xw_plus_b(h_drop, W, b, name="scores")
predictions = tf.argmax(scores, 1, name="predictions")
l2_loss += tf.nn.l2_loss(W, name="l2_loss")
l2_loss += tf.nn.l2_loss(b, name="l2_loss")
tf.summary.histogram("l2", l2_loss)
tf.summary.histogram("weigths", W)
tf.summary.histogram("biases", b)
with tf.name_scope("auc_score"):
# labelOut = tf.argmax(y_place_holder, 1)
probability = tf.nn.softmax(scores)
# auc_scoreTemp = streaming_auc(y_place_holder, probability, curve="PR")
auc_scoreTemp = tf.metrics.auc(y_place_holder, probability, curve="PR")
auc_score = tf.reduce_mean(tf.cast(auc_scoreTemp, tf.float32), name="auc_score")
tf.summary.scalar("auc_score", auc_score)
with tf.name_scope("accuracy"):
labelOut = tf.argmax(y_place_holder, 1)
correct_prediction = tf.equal(predictions, tf.argmax(y_place_holder, 1), name="correct_prediction")
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name="accuracy")
tf.summary.scalar("accuracy", accuracy)
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
for batch in batches:
x_batch, y_batch = list(zip(*batch))
_, accuracy_train, auc_training, loss_train, prec_batch, recall_batch, f1_batch \
= sess.run([train_step, accuracy, auc_score, cross_entropy, precision_mini_batch,
recall_mini_batch, f1_score_min_batch], feed_dict={x_place_holder: x_batch,
y_place_holder: y_batch,
emb_place_holder: vocab_inv_emb_dset,
dropout_keep_prob: dropout_rate})
...
for test_batch in test_batches:
auc_test = None
x_test_batch, y_test_batch = list(zip(*test_batch))
accuracy_test, loss_test, auc_test = sess.run([accuracy, cross_entropy, auc_score],
feed_dict={x_place_holder: x_test_batch,
y_place_holder: y_test_batch,
emb_place_holder: vocab_inv_emb_dset_val,
dropout_keep_prob: 1.0})
I also tried to use streaming_auc which returns always 1.
EDIT
In the end of every epoch I reset the local variables by running:
sess.run(tf.local_variables_initializer())
But the first batch outputs really bad results. After the first batch I get normal results from test set which are not close to the training results. I don't know if this is the correct way to do it but results seem more realistic this way.

Answer 1

All of the tf.metrics return a value and an updating op (see here). So as described here you want to use the updating op to accumulate values and then evaluate auc_score to retrieve the accumulated value, something like this:
...
auc_score, auc_op = tf.metrics.auc(y_place_holder, probability, curve="PR")
...
for batch in batches:
sess.run([train_step, accuracy, auc_op, cross_entropy,...)
...
py_auc = sess.run(auc)
EDIT -- toy example showing tf.metrics.auc and tf.contrib.metrics.streaming_auc
import tensorflow as tf
from tensorflow.contrib import metrics
batch_sz = 100
noise_mag = 0.5
nloop = 10
tf.set_random_seed(0)
batch_x = tf.random_uniform([batch_sz, 1], 0, 2, dtype=tf.int32)
noise = noise_mag * tf.random_normal([batch_sz, 1])
batch_y = tf.sigmoid(tf.to_float(batch_x) + noise)
auc_val, auc_accum = tf.metrics.auc(batch_x, batch_y)
#note: contrib.metrics.streaming_auc reverses labels, predictions
auc_val2, auc_accum2 = metrics.streaming_auc(batch_y, batch_x)
with tf.Session() as sess:
sess.run(tf.local_variables_initializer())
for i in range(nloop):
_ = sess.run([auc_accum, auc_accum2])
auc, auc2 = sess.run([auc_val, auc_val2])
print('Accumulated AUC = ', sess.run(auc_val)) #0.9238014
print('Accumulated AUC2 = ', sess.run(auc_val)) #0.9238014