Query about weight filter size in AlexNet

Question

deepika s 2021-8-14

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/898152-query-about-weight-filter-size-in-alexnet

评论： deepika s 2021-8-18

I have analysed the pretrained alexnet model. I have attached the screen shot. In that conv2 row, weights are given as 5*5*48*256. what is 48 here?. As per my knowledge, 48 represents the previous layer (number of channels in previous layer). but number of previous layer is 96 after pool1. likewise, same doubt in conv4 and conv5.

Can anyone explain this question?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Harikrishnan Balachandran Nair 2021-8-17

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/898152-query-about-weight-filter-size-in-alexnet#answer_768472

The reason that the third dimension of weights in the mentioned layer is not the same as the number of channels in input is that the corresponding layer in AlexNet perform grouped Convolution. You can refer to the following Documentation to learn more about AlexNet : https://www.mathworks.com/help/deeplearning/ref/alexnet.html.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

deepika s 2021-8-18

Yes. but how the third dimesion (48) of weight in Conv2 is convolves with number of channels (nothing but dimension 96) in the pool1 output? Both dimensions are different.

请先登录，再进行评论。