Open dgai91 opened 6 years ago
I have, but thinking how to send to you because 20gb in size.
This huge weight should be the CDE model. I just need single model which only contains optical and data_dim=4096, channel_flag=0
the structure of temporal_model is:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_1 (LSTM) (None, 3000) 1678800
_________________________________________________________________
dense_1 (Dense) (None, 128) 12928
_________________________________________________________________
dense_2 (Dense) (None, 5) 645
=================================================================
Because each different fold has its own weight (cross validation), so in total there are 26 spatial and 26 temporal weights.
oh, sorry I have forgotten this. could you send me the first sub weights?
weights for dige.rar https://drive.google.com/file/d/1Bf60k5EHfVbfPpUY7b0VrvFCz0MBzraL/view?usp=drive_web
-- Journey of thousand miles begins with a single step.
On Fri, 24 Aug 2018 at 15:01, Dige Ai notifications@github.com wrote:
oh, sorry I have forgotten this. could you send me the first sub weights?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/IcedDoggie/Micro-Expression-with-Deep-Learning/issues/14#issuecomment-415670737, or mute the thread https://github.com/notifications/unsubscribe-auth/AD-WkE58eu7-wup-KrZGNdUUxLjJ6ALXks5uT6TkgaJpZM4WIxyi .
thank you very much
Hi, due to the poor PC and GPU I can't train a full model using this param:
could you send me these weights which contains temporal_model, and VGG_model