Padding in conv-10 layer

forresti / SqueezeNet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

BSD 2-Clause "Simplified" License

2.17k stars 723 forks source link

Closed AlexandreBriot closed 7 years ago

AlexandreBriot commented 7 years ago

Hello I wonder why we need to use pad=1 in conv-10 layer. What is the goal to use padding with a 1x1 kernel ? Thanks in advance for your help. Alex

layer { name: "conv10" type: "Convolution" bottom: "fire9/concat" top: "conv10" convolution_param { num_output: 1000 pad: 1 kernel_size: 1 } }

chibai commented 7 years ago

@AlexandreBriot check the closed issue 14 you can close the issue i guess