Meaning of evaluation metrics in tensorflow

Question

I am pretty much a beginner in tensorflow and simply following a tutorial. There is no problem with my code but I have a question regarding the output

accuracy: 0.95614034
accuracy_baseline: 0.6666666
auc: 0.97714674
auc_precision_recall: 0.97176754
average_loss: 0.23083039
global_step: 760
label/mean: 0.33333334
loss: 6.578666
prediction/mean: 0.3428335

I would like to know what prediction/mean and label/mean represents?

Thank you in advance

Answer 1

The predictionis the output of the network. When you feed in many inputs after each other you get many outputs (predictions). The prediction/mean is just the sum of all these outputs divided by the number of outputs. The lablel is the value which the network should output/predict for a given input. Again you can sum them up and divide them by the number of elements in order to get the label/mean of the labels. When you compare the prediction/mean with the label/mean you can find out how efficient your net was.