titu1994
commented
7 years ago It's fine. This is more clear in what it is doing. By stating explicitly that the input is added to the list and not used in concatenate is in line with what the paper wrote, so for clarity I wrote it that way as well.
Makes no difference in performance.
Also, looking at several implementations and network diagrams, such as this:
It appears that in __denseblock needs to be modified a bit because the input is only connected to the output through conv blocks.
should be:
which should mean the relevant instances of
[1:]in the file can go away. I also think this also means concat_list does not need to be returned.the same should apply for keras-contrib