SqueezeNet benchmark about squeezenet HOT 10 CLOSED

Very cool!

from squeezenet.

Added SqueezeNet + ELU instead of ReLU

from squeezenet.

Hi, I'd like to test this model. How may I get/generate deploy.prototxt file for the same?

from squeezenet.

@gaush123 There's a PR for a deploy.prototxt here: #2
(link)

We still need to do our own sanity-check on this deploy.prototxt, but it looks right to me.

from squeezenet.

@forresti One more question that I do have is, why there is no kernel size mention in the "pool 10" layer, the layers which is directly connected to the softmax layer at the top most.

from squeezenet.

@gaush123
In pool10, we use globalpool: True. In Caffe, globalpool means to set the kernel size equal to the size of the input data. So, if conv10 outputs 13x13xChannels, then pool10 has a 13x13 kernel.

This is a nice bit of flexibility -- it allows you to input various sizes of input images, and the CNN will still produce a 1x1x1000 classification vector.

from squeezenet.

Thanks @forresti
One more, when I download this model it shows its type as 'pcx' image, while other standard models are in binary txt format. Is it possible to do any kind of conversions here?

from squeezenet.

see #5.

from squeezenet.

@forresti now we have released the tech report http://arxiv.org/abs/1606.02228 so you can cite linear lr_policy ;) Also, hope than you can adopt some other stuff from to the squeezenet.

from squeezenet.

@ducha-aiki Great! We have an other upcoming publication and we will cite this!

from squeezenet.