In the paper ImageNet Classification with Deep Convolutional Neural Networks, the size of input image is 224x224. The following figure shows the input size. enter image description here

From caffe, deploy.prototxt file from the directory of the bvlc_alexnet says that the input size is 227x227. enter image description here

Why is the input size different?

  • 1
    $\begingroup$ I don't have reputation to comment so I am asking a small follow-up. does the 10 represent batch size and 3 represent the RGB channels? $\endgroup$ – Shreyas Pimpalgaonkar Jun 11 '18 at 11:21

I guess it has been a mistake. Take a look at here.

The other author's were Ilya Sutskever and Geoffrey Hinton. So, AlexNet input starts with 227 by 227 by 3 images. And if you read the paper, the paper refers to 224 by 224 by 3 images. But if you look at the numbers, I think that the numbers make sense only of actually 227 by 227.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.