diff options
author | Sergio <sguada@gmail.com> | 2014-12-20 23:24:32 -0800 |
---|---|---|
committer | Sergio <sguada@gmail.com> | 2014-12-21 17:02:54 -0800 |
commit | b99e6cdcaf10196b901cfa870d9ca5f7d9d886bf (patch) | |
tree | a8daa9dfd48153f203e34b5f4ab57aa5daf3d3f2 /models/bvlc_reference_caffenet | |
parent | 4ba6efc7ac939be59e5ff121c0289885a9a4263d (diff) | |
download | caffeonacl-b99e6cdcaf10196b901cfa870d9ca5f7d9d886bf.tar.gz caffeonacl-b99e6cdcaf10196b901cfa870d9ca5f7d9d886bf.tar.bz2 caffeonacl-b99e6cdcaf10196b901cfa870d9ca5f7d9d886bf.zip |
Added credits for training bvlc models
Diffstat (limited to 'models/bvlc_reference_caffenet')
-rw-r--r-- | models/bvlc_reference_caffenet/readme.md | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/models/bvlc_reference_caffenet/readme.md b/models/bvlc_reference_caffenet/readme.md index d1c6269a..b867e738 100644 --- a/models/bvlc_reference_caffenet/readme.md +++ b/models/bvlc_reference_caffenet/readme.md @@ -18,6 +18,8 @@ The best validation performance during training was iteration 313,000 with valid This model obtains a top-1 accuracy 57.4% and a top-5 accuracy 80.4% on the validation set, using just the center crop. (Using the average of 10 crops, (4 + 1 center) * 2 mirror, should obtain a bit higher accuracy still.) +This model was trained by Jeff Donahue @jeffdonahue + ## License The data used to train this model comes from the ImageNet project, which distributes its database to researchers who agree to a following term of access: |