Densely Connected Convolutional Networks: CVPR 2017 Best Paper Award Winner
1–4 of 4 posts
Re: Densely Connected Convolutional Networks: CVPR 2017 Best Paper Award Winner
#2Am I understanding this correctly? The layers do not combine their inputs.
Equation (2)
x_l = H_l([x_0, x_1, . . . , x_l−1])
Could be re-written: x_l = [H_l(x_0), H_l(x_1), . . . , H_l(x_l−1)]
Re: Densely Connected Convolutional Networks: CVPR 2017 Best Paper Award Winner
#3Am I understanding this correctly? The layers do not combine their inputs. Equation (2) x_l = H_l([x_0, x_1, . . . , x_l−1]) Could be re-written: x_l = [H_l(x_0), H_l(x_1), . . . , H_l(x_l−1)]
No, inputs to each layer are concatenated before being passed through H.
Re: Densely Connected Convolutional Networks: CVPR 2017 Best Paper Award Winner
#4Seems promising and easy to use in practice.