caffe

История

Luke Yeager 2f5889cb84 Use input_shape instead of input_dim in examples		2015-08-20 14:29:02 -07:00
..
deploy.prototxt	Use input_shape instead of input_dim in examples	2015-08-20 14:29:02 -07:00
readme.md	BVLC models are for unrestricted use (follow-up to #1650 )	2015-01-07 23:00:27 -05:00
solver.prototxt	Renaming CaffeNet model prototxts and unignoring models/*	2014-09-04 03:59:14 +01:00
train_val.prototxt	Upgrade existing nets using upgrade_net_proto_text tool	2015-02-05 15:17:24 -08:00

readme.md

name	caffemodel	caffemodel_url	license	sha1	caffe_commit
BVLC AlexNet Model	bvlc_alexnet.caffemodel	http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel	unrestricted	9116a64c0fbe4459d18f4bb6b56d647b63920377	`709dc15af4`

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.