diff options
author | Sergey Karayev <sergeykarayev@gmail.com> | 2014-07-11 19:23:47 -0700 |
---|---|---|
committer | Sergey Karayev <sergeykarayev@gmail.com> | 2014-07-11 23:41:12 -0700 |
commit | dd546171bae1c3608ce70111c8ffb46c766ea9df (patch) | |
tree | ad5f50b1c15158657b3deca2293a6e066f9d68e0 /docs | |
parent | e8e8292c36f12e7b60b63adeac68e86337da7de5 (diff) | |
download | caffeonacl-dd546171bae1c3608ce70111c8ffb46c766ea9df.tar.gz caffeonacl-dd546171bae1c3608ce70111c8ffb46c766ea9df.tar.bz2 caffeonacl-dd546171bae1c3608ce70111c8ffb46c766ea9df.zip |
[example] image classification web demo
Diffstat (limited to 'docs')
-rw-r--r-- | docs/getting_pretrained_models.md | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/docs/getting_pretrained_models.md b/docs/getting_pretrained_models.md index bbac5ac4..14e6ee91 100644 --- a/docs/getting_pretrained_models.md +++ b/docs/getting_pretrained_models.md @@ -8,7 +8,8 @@ layout: default Note that unlike Caffe itself, these models are licensed for **academic research / non-commercial use only**. If you have any questions, please get in touch with us. -This page will be updated as more models become available. +*UPDATE* July 2014: we are actively working on a service for hosting user-uploaded model definition and trained weight files. +Soon, the community will be able to easily contribute different architectures! ### ImageNet @@ -26,4 +27,6 @@ This page will be updated as more models become available. validation accuracy 57.258% and loss 1.83948. - This model obtains a top-1 accuracy 57.1% and a top-5 accuracy 80.2% 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) +### Auxiliary Data + Additionally, you will probably eventually need some auxiliary data (mean image, synset list, etc.): run `data/ilsvrc12/get_ilsvrc_aux.sh` from the root directory to obtain it. |