Why v1.1 does not have deploy.prototxt

[changyun79]

Hello,
I am wondering why v1.1 does not have deploy.prototxt. Missed commit? Thank you.

[forresti]

We can add that. Thanks to @terrychenism for creating this on SqueezeNet v1.0.

Nobody on our team uses the deploy.prototxt interface very often... we mostly load custom training/testing sets into LMDBs to avoid being bottlenecked by I/O.

[changyun79]

Thanks for the quick response. I appreciate if it can be added in.

[besirkurtulmus]

I'd also appreciate if you could add deploy.txt too.

[austingg]

@besirkurtulmus it's quite easy to make deploy.prototxt with reference train_val.prototxt. You can just modified the input and output layers and there are some reference in Caffe/models directory.

[psyhtest]

@forresti

I thought one needs deploy.prototxt to measure the execution time using caffe time? I appreciate your research is mostly about achieving the same accuracy but what about performance?

[forresti]

I often run caffe time on train_val.prototxt files... it works great. :)

[psyhtest]

@forresti

Thanks! Do you know which batch size gets picked up for benchmarking - from the TRAIN or TEST specification?

[forresti]

I think train. But, caffe time will print the dimensions of all layers
including the batch size.
On Jul 8, 2016 1:19 AM, "Anton Lokhmotov" notifications@github.com wrote:

forresti
Thanks! Do you know which batch size gets picked up for benchmarking -
from the TRAIN or TEST specification? Is it deterministic?

—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
#12 (comment),
or mute the thread
https://github.com/notifications/unsubscribe/AB7Sqg2wwWGzjM1NGSTmsTVpXGrHcx3jks5qTggrgaJpZM4I2qdc
.

[AliaMYH]

What exactly is the difference between the train_val and the deploy prototxt ? What are their different purposes?

[amroamroamro]

@forresti
there's now three PRs to add deploy.txt for v1.1: #20, #21, #43