Closed ducha-aiki closed 7 years ago
Very cool!
Added SqueezeNet + ELU instead of ReLU
Hi, I'd like to test this model. How may I get/generate deploy.prototxt file for the same?
@gaush123 There's a PR for a deploy.prototxt here: https://github.com/DeepScale/SqueezeNet/pull/2 (link)
We still need to do our own sanity-check on this deploy.prototxt, but it looks right to me.
@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.
@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.
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?
see #5.
@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.
@ducha-aiki Great! We have an other upcoming publication and we will cite this!
Hi,
SqueezeNet is really cool architecture! I have added it to my caffenet-variants benchmark and it looks even better than caffenet. https://github.com/ducha-aiki/caffenet-benchmark/blob/master/Architectures.md
Note, that because of speed reasons, I use image size = 128 px, so performances of all nets are degraded compared to classical 227px.
I`d like to suggest a bit different solver setup for SqueezeNet. According to my tests on caffenet128, linear lr_policy works better, than squared, as in your solver: https://github.com/ducha-aiki/caffenet-benchmark/blob/master/Lr_policy.md
Best regards, Dmytro.