12 Коммитов

Автор	SHA1	Сообщение	Дата
Tea	b72b0318e2	replace snprintf with a C++98 equivalent	2015-11-26 09:54:12 +08:00
Tea	f3a933a620	Separate IO dependencies ... OpenCV, LMDB, LevelDB and Snappy are made optional via switches (USE_OPENCV, USE_LMDB, USE_LEVELDB) available for Make and CMake builds. Since Snappy is a LevelDB dependency, its use is determined by USE_LEVELDB. HDF5 is left bundled because it is used for serializing weights and solverstates.	2015-09-17 15:08:29 +08:00
Darren Garvey	e8f96f58aa	Fix memory leak in convert_mnist_siamese_data. ... This fixes a memory leak by using delete[] rather than plain delete.	2015-09-02 00:14:43 +01:00
Luke Yeager	2f5889cb84	Use input_shape instead of input_dim in examples	2015-08-20 14:29:02 -07:00
Evan Shelhamer	a6cb8ec62c	[examples] sequence and revise notebooks ... - combine classification + filter visualization - order by classification, learning LeNet, brewing logreg, and fine-tuning to flickr style - improve flow of content in classification + filter visualization - include solver needed for learning LeNet - edit notebook descriptions for site catalogue	2015-06-30 15:15:02 -07:00
Sebastián Ramírez	2fed2a998a	Update IPython Notebooks to version 4	2015-05-18 10:21:44 -05:00
Jeff Donahue	cf0e6b7215	Update docs for ND blobs (#1970) and layer type is a string (#1694)	2015-05-14 18:38:16 -07:00
Takuya Narihira	101055c840	Fix siamese ipynb example	2015-02-26 14:52:54 -08:00
Jeff Donahue	e6c80dac40	Upgrade existing nets using upgrade_net_proto_text tool ... Restore comments afterwards	2015-02-05 15:17:24 -08:00
Pannous	b6f9dc8f86	fixed small bug: output label_file -> label_filename	2015-02-04 10:12:33 -08:00
Evan Shelhamer	403b56ba30	[example] groom siamese notebook	2014-09-18 21:38:43 -07:00
Nick Carlevaris-Bianco	d149c9a98d	Added contrastive loss layer, associated tests, and a siamese network example using shared weights and the contrastive loss.	2014-09-08 16:14:58 -04:00