SENet

SENet copied to clipboard

Train custom data

1

How to train my custom data with SENet

Muhammad333

Does SENet need to expand the number of channels on the input?

1

Hello, thank you for your contribution. I don't quite understand a few points. Input. shape = (1,10242,6) 1. Do I need to extend the input to 4 dimensions? (1,10242,6)----->(1,1,10242,6) 2....

tanjia123456

Could you please provide the training detail of the SE-WRN for cifar? Thanks a lot!

rederyang

How to preprocess the image on pretrained model

2

Hi we can't get good result with preprocessing info on the pretrained model. BGR mean values [103.94,116.78,123.68] are subtracted scale: 0.017 is used as std values for image preprocessing can...

mancomao

Did anyone use SENet on Optical Flow features?

2

Did anyone use SENet on Optical Flow features? Dose it work on Optical Flow features?

tingweiwang

ghost

Hello @hujie-frank First of all, **thanks for sharing your amazing work**. I am trying to reproduce your results using VGG-16 but on cifar10 & cifar100, but unfortunately, I couldn't increase...

eslambakr

SE-VGG-16

2

hi, I want to do some work under your work. I would like to use the pretrained model of SE-VGG-16 network, because our resources are limited, we can't train the...

SWHL

Hello, thank you very much for your work. Your work is great, and you have contributed a lot to this field. I see that the top-1 result of the Inception-ResNet-v2...

xueweili

I am curious about the values ofSE_Stage_5 top err, GFLOPs and Params. I know the basiline ResNet-50 and see the description of "

jerryqiang