Closed lryta closed 7 years ago
@lryta The travis is done now. But I guess the failure is caused by perform test, as the extra CNN layer might impact the network performance. What's the accuracy you would get after using extra another CNN layer?
@HrWangChengdu It's due to a weird pip
error: pip
cannot install minpy
. I restarted the job on Travis. Regarding my modification on testcase, I just added a dumb layer which won't change the output result (it's not sent to the final result anyway). I just want to address symbols can be reused in the testcases.
Could you test the performance loss due to this change?
I roughly tested in cnn_sym.py
and I saw no performance difference. My scant modification should not change performance logically. (No computational change in fact)
Could you please use trash as the output and test the network gain? I just want to make sure the gradient could work.
Fix symbol cannot be reused. @HrWangChengdu @jermainewang