Skip to content
master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
caffe/models/bvlc_alexnet/
Go to file
caffe/models/bvlc_alexnet/

Latest commit

@shelhamer
shelhamer BVLC -> BAIR
44da39f Apr 14, 2017
BVLC -> BAIR 
Berkeley AI Research (BAIR) is the the successor to
the Berkeley Vision and Learning Center (BVLC).
44da39f

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
. .
deploy.prototxt
[examples] switch examples + models to Input layers
February 25, 2016 17:29
readme.md
BVLC -> BAIR
April 14, 2017 13:11
solver.prototxt
Renaming CaffeNet model prototxts and unignoring models/*
September 4, 2014 03:59
train_val.prototxt
Upgrade existing nets using upgrade_net_proto_text tool
February 5, 2015 15:17

readme.md

name caffemodel caffemodel_url license sha1 caffe_commit
BAIR/BVLC AlexNet Model
bvlc_alexnet.caffemodel
unrestricted
9116a64c0fbe4459d18f4bb6b56d647b63920377
709dc15af4a06bebda027c1eb2b3f3e3375d5077

This model is a replication of the model described in the AlexNet publication.

Differences:

  • not training with the relighting data-augmentation;
  • initializing non-zero biases to 0.1 instead of 1 (found necessary for training, as initialization to 1 gave flat loss).

The bundled model is the iteration 360,000 snapshot. The best validation performance during training was iteration 358,000 with 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.)

This model was trained by Evan Shelhamer @shelhamer

License

This model is released for unrestricted use.