same setting for nuclei data, but bad results?

[xinrzhsh24]

Hi, Valen~
I can get the pretty segmentation results using your trained model ( '2016-07-12_nuclei_all_61x61_bn_feature_net_61x61_'). But the model trained by using your code of 'training_template', the result is too bad. I also used your data (nulei_all_6161) and the model bn_feature_net_61*61. I noticed your trained model is 1.9M, while mine is 3.8M. What is the problems?

[vanvalen]

Greetings, From what I can tell, Keras changed how networks are saved, so we've been having some issues getting everything compatible with the new format. We're working on it now, and it should be fixed in the next couple of days. Dave David Van Valen MD, PhD Postdoctoral Scholar, Covert Lab Stanford University

…

On Tue, Jun 6, 2017 at 1:48 PM, xinrzhsh24 ***@***.***> wrote: Hi, Valen~ I can get the pretty segmentation results using your trained model ( '2016-07-12_nuclei_all_61x61_bn_feature_net_61x61_*'). But the model trained by using your code of 'training_template', the result is too bad. I also used your data (nulei_all_61*61) and the model bn_feature_net_61*61. I noticed your trained model is 1.9M, while mine is 3.8M. What is the problems? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#7>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AKYa9hzBmVdC3p4YjnGAz699iIefdCfjks5sBbswgaJpZM4Nx5Rc> .