search

WeiTang114 / MVCNN-TensorFlow

An Multi-View CNN (MVCNN) implementation with TensorFlow.
MIT License
120 stars 67 forks source link

why do we use group =2 in the model? #11

Closed yix081 closed 7 years ago

yix081 commented 7 years ago

for conv2, conv4, conv5, they all have parameter "group" sets to 2, which I feel is not necessary. What's the reason using it?

WeiTang114 commented 7 years ago

It is for the historical reason that original AlexNet [1] used group in their structure, and as I am using Caffe's AlexNet pretrained model, I need to build the graph exactly the same as that.

[1] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012.