Skip connections

[TopTea1]

Hi, I try to figured out how skip connections works because in the paper we can see, that If a layer receive skip connections from multiple layers before it, then these layers’ outputs are concatenated in their depth dimension, and then a convolution of filter size 1x1, but when you read the code general_child.py#366, it's just an element wise addition. Do these operations give the same results? Thanks for your help