This repository has been archived by the owner on May 24, 2018. It is now read-only.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I have added layer names in the example conf.
Please confirm the sizes with the Appendix of BN paper, with noting that
output size of inception
4c
and4d
should be14x14x608
(160+160+160+128, 96+192+192+128)output size of inception
4e
should be14x14x1056
(192+256+608)@winstywang and @antinucleon: I'm very sorry that due to the wrong padding for pooling layers in my previous BN.conf, I met inconsistent sizes error in
ch_concat
. the fix of pooling size PR #154 is wrong, please get it back to the original one. I thought the pooling output size is by takingfloor()
, but notceil()
and set the wrong paddings in BN.conf.