Tensorflow Summary Scalar is not being displayed - tensorflow

Question

I am using the following code to produce scalar graphs for my accuracy and cost, but the scalar summaries are not being displayed at the tensorboard. It gives me an error saying No scalar data was found. Can someone have a look please? code for the model:
def train_neural_network(x):
prediction = convolutional_neural_network(x)
merged_summary_op = tf.summary.merge_all()
with tf.name_scope("cost"):
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=1e-3).minimize(cost)
tf.summary.scalar("cost", cost)
hm_epochs = 10
with tf.Session() as sess:
writer = tf.summary.FileWriter('C:/Thesis/Conv3d/69', sess.graph)
sess.run(tf.initialize_all_variables())
successful_runs = 0
total_runs = 0
for epoch in range(hm_epochs):
epoch_loss = 0
for data in train_data:
total_runs += 1
try:
X = data[0]
Y = data[1]
_, c = sess.run([optimizer, cost], feed_dict={x: X, y: Y})
writer.add_summary(summary, global_step=epoch)
epoch_loss += c
successful_runs += 1
except Exception as e:
pass
print('Epoch', epoch + 1, 'completed out of', hm_epochs, 'loss:', epoch_loss)
with tf.name_scope("accuracy"):
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
tf.summary.scalar("accuracy", accuracy)
print('Accuracy:', accuracy.eval({x: [i[0] for i in validation_data], y: [i[1] for i in validation_data]}))
print('Done. Finishing accuracy:')
print('Accuracy:', accuracy.eval({x: [i[0] for i in validation_data], y: [i[1] for i in validation_data]}))
print('fitment percent:', successful_runs / total_runs)

Answer 1

You need to call merge_all after defining the summary ops. What happens right now is that the op simply doesn't have anything to summarize (since it's called first) and unfortunately isn't "smart" enough to add summary ops that are defined later.
Note that I also "fixed" the code in that you generally shouldn't run TF ops in a loop; I moved all the accuracy stuff before the training loop.
def train_neural_network(x):
prediction = convolutional_neural_network(x)
with tf.name_scope("cost"):
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=1e-3).minimize(cost)
tf.summary.scalar("cost", cost)
with tf.name_scope("accuracy"):
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
tf.summary.scalar("accuracy", accuracy)
merged_summary_op = tf.summary.merge_all()
hm_epochs = 10
with tf.Session() as sess:
writer = tf.summary.FileWriter('C:/Thesis/Conv3d/69', sess.graph)
sess.run(tf.initialize_all_variables())
successful_runs = 0
total_runs = 0
for epoch in range(hm_epochs):
epoch_loss = 0
for data in train_data:
total_runs += 1
try:
X = data[0]
Y = data[1]
_, c = sess.run([optimizer, cost], feed_dict={x: X, y: Y})
writer.add_summary(summary, global_step=epoch)
epoch_loss += c
successful_runs += 1
except Exception as e:
pass
print('Epoch', epoch + 1, 'completed out of', hm_epochs, 'loss:', epoch_loss)
print('Accuracy:', accuracy.eval({x: [i[0] for i in validation_data], y: [i[1] for i in validation_data]}))
print('Done. Finishing accuracy:')
print('Accuracy:', accuracy.eval({x: [i[0] for i in validation_data], y: [i[1] for i in validation_data]}))
print('fitment percent:', successful_runs / total_runs)