caffe

История

Brian Chu ca4c6fb4e2 Set CaffeNet train_val test mirroring to false		2015-10-13 13:24:42 -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	Set CaffeNet train_val test mirroring to false	2015-10-13 13:24:42 -07:00

readme.md

name	caffemodel	caffemodel_url	license	sha1	caffe_commit
BVLC CaffeNet Model	bvlc_reference_caffenet.caffemodel	http://dl.caffe.berkeleyvision.org/bvlc_reference_caffenet.caffemodel	unrestricted	4c8d77deb20ea792f84eb5e6d0a11ca0a8660a46	`709dc15af4`

This model is the result of following the Caffe ImageNet model training instructions. It is a replication of the model described in the AlexNet publication with some differences:

not training with the relighting data-augmentation;
the order of pooling and normalization layers is switched (in CaffeNet, pooling is done before normalization).

This model is snapshot of iteration 310,000. The best validation performance during training was iteration 313,000 with validation accuracy 57.412% and loss 1.82328. 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

This model is released for unrestricted use.