Accuracy equals 0.903883 when iteration is 0. Why?

[lismqi]

Issue summary

I began to train my model on my data. I found the accuracy was so high. I don't know what happened.The result maybe not persuasive.Here was the information....

I0510 10:44:10.164682 32107 solver.cpp:337] Iteration 0, Testing net (#0)
I0510 10:44:17.416599 32107 solver.cpp:404] Test net output #0: accuracy = 0.903883
I0510 10:44:17.416632 32107 solver.cpp:404] Test net output #1: loss = 0.590191 (* 1 = 0.590191 loss)

Your system configuration

Operating system:14.04.1-Ubuntu
Python or MATLAB version (for pycaffe and matcaffe respectively):python2.7

[shaibagon]

Please use the caffe-users list for usage, installation, or modeling questions, or other requests for help.
You may also post questions on stackoverflow, make sure you tag them with caffe tag.
There is also caffe.help documenting the different layers of caffe.
Do not post such requests to Issues. Doing so interferes with the development of Caffe.

Please read the guidelines for contributing before submitting this issue.