ShuffleNet

ShuffleNet copied to clipboard

Accuracy about shufflenet_v2 _1x

1

I trained imagenet using your shufflenet_v2_1x.prototxt but I got only 48% top1 accuracy. So I want to know your performance using it and some training details you know ? Thank...

wang5566

License info

1

Could you please provide LICENSE for the project? Thanks.

moljacq

pre-train model

70

Have you successfully trained the model? can you sent me a pre-train model, i want to train a shufflenet-ssd with a pre-train model. thanks!

linchaozhang

Message type "caffe.LayerParameter" has no field named "shuffle_channel_param"

15

I have added the shuffle layer into caffe, and run 'make all' successfully. And I have trained the model with shuffle layer successfully. But when I run the test code...

XingyuXie

Not getting a good accuracy

21

Hi @farmingyard , I ran your deploy prototxt on imagenet this weekend yet still got a bad accuracy output. (exactly the same prototxt I'd be appreciated if you could share...

leochli

Hi, Thank you for sharing the code. 1. The function of shuffle_channel_layer is only to exchange the locations of channels, right? 2. Can I set the the 'group' in '...

DanChen001

about the train.prototxt and deploy.prototxt

1

When I use your delpoy.prototxt, do i need to add a fc layer after the last conv layer? or i just need a softmax layer

abcdvzz

ShuffleNet-2x

1

ShuffleNet 2x means all channels multiply by 2?

mynameischaos

I didn't find pointwise group conv in your deploy.prototxt

1

There only exist channel shuffle setting and depthwise conv setting for 3*3 convolution, why didn't have group convolution for 1*1 kernel ?

wujiyang

what's the type of "ConvolutionDepthwise"

2

it occurs an error of no the layer type ConvolutionDepthwise

andeyeluguo