search

tangyuhao / GOTURN-Tensorflow

A tensorflow implementation for GOTURN tracker
MIT License
130 stars 61 forks source link

Why do you need to transpose the concatenated tensor? #27

Open foromer4 opened 5 years ago

foromer4 commented 5 years ago

Could you pelase explain why you permutate the order to be n c w * h? in this line? concat = tf.transpose(concat, perm=[0, 3, 1, 2])

Why does it need to be the same order as caffe?

thanks, Omer

tangyuhao commented 5 years ago

I did not retrain the model , I used the model converter to convert caffe model to tf model but did not reorder at that time. To make the parameters work as before I need permutation

The code is for finetuning

On Tue, Jun 4, 2019 at 02:54 Omer Schleifer notifications@github.com wrote:

Could you pelase explain why you permutate the order to be n c w * h? in this line? concat = tf.transpose(concat, perm=[0, 3, 1, 2])

Why does it need to be the same order as caffe?

thanks, Omer

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/tangyuhao/GOTURN-Tensorflow/issues/27?email_source=notifications&email_token=ACTFLKP6BTMXONFBIOLVXLDPYY3WHA5CNFSM4HS2VS3KYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4GXPP3EA, or mute the thread https://github.com/notifications/unsubscribe-auth/ACTFLKO3HVJNTWYRGV5OHVLPYY3WHANCNFSM4HS2VS3A .