12 Коммитов

Автор	SHA1	Сообщение	Дата
Achal Dave	bd762101db	Explicitly point out -weights flag in tutorial ... The -weights flag is somewhat easy to miss as it's only in one command, but is the crucial thing that anyone searching for 'how to finetune' is looking for. Hopefully this more clearly points out the '-weights' flag, which might otherwise be overlooked in this tutorial.	2016-04-20 17:34:29 -04:00
Viveka Kulharia	4f4d020949	minor mistakes removed	2016-03-02 10:37:56 +05:30
Muneyuki Noguchi	f19896ccca	Replace blobs_lr with lr_mult in readme.md. ... models/finetune_flickr_style/deploy.prototxt uses lr_mult now.	2015-12-20 19:12:09 +09:00
Sergey Karayev	f2f0a7a73d	Fixing finetune_flickr_style model reported accuracy.	2014-10-17 11:44:57 -07:00
Evan Shelhamer	4302304ddc	[examples] fix reference model name for flickr fine-tuning	2014-10-14 10:18:20 -07:00
Evan Shelhamer	57d14637d6	[example] fix data script paths for flickr fine-tuning	2014-10-08 19:56:21 -07:00
Evan Shelhamer	a857001775	fix fine-tuning example: paths, test acc., and total fine-tuning time	2014-09-04 12:46:57 -07:00
Evan Shelhamer	f7baf2b486	fix model download advice and prototxt name for fine-tuning	2014-09-04 02:33:19 -07:00
Sergey Karayev	c6827bf3fc	flickr style fine-tuning model (separated from example read me)	2014-09-04 03:59:14 +01:00
Sergey Karayev	da715ea07a	removed mention of getting_pretrained_models page and old paths	2014-09-04 03:59:14 +01:00
Sergey Karayev	59fafb1f0d	[docs] default setting for layout	2014-09-04 01:45:07 +01:00
Evan Shelhamer	23a5026084	[example] edit fine-tuning and train on ~2000 images, 1557 / 382 split ... - further detail merits of fine-tuning: less starving for itme and data - set random seed for reproducing the tutorial - 1557 train / 382 test split is more indicative of training quality than splits of 200 images	2014-08-28 22:37:25 -07:00