Kai Li 7219dbb121 Check data size when converting images into leveldb		2014-02-11 19:40:21 +08:00
..
convert_cifar_data.cpp	script to convert cifar data	2013-10-30 16:52:34 -07:00
convert_imageset.cpp	Check data size when converting images into leveldb	2014-02-11 19:40:21 +08:00
convert_mnist_data.cpp	mnist updates	2013-10-16 13:03:03 -07:00
demo_compute_image_mean.cpp	distributed server update. bug in synchronous connections.	2013-11-06 15:27:26 -08:00
device_query.cpp	Rename devicequery.cpp to device_query.cpp	2014-02-05 11:09:00 -08:00
dump_network.cpp	Made a major change: when initializing a network, the input size are no longer provided by an additional vector of blobs, but should be specified in the netparameters proto by the field "input_dim". This avoid the often awkward code of creating a dummy input vector just for the sake of initializing the network.	2013-11-15 16:58:53 -08:00
finetune_net.cpp	Several changes:	2013-12-02 15:44:43 -08:00
imagenet.prototxt	Made a major change: when initializing a network, the input size are no longer provided by an additional vector of blobs, but should be specified in the netparameters proto by the field "input_dim". This avoid the often awkward code of creating a dummy input vector just for the sake of initializing the network.	2013-11-15 16:58:53 -08:00
imagenet_deploy.prototxt	imagenet deploy prototxt: instead of having a data layer, this network proto takes an external blob called data. The shape is hardcoded to accompany the imagenet python wrapper at python/caffe/imagenet/wrapper.py. You need to change the shape if you intend to use other shapes.	2013-11-18 16:06:33 -08:00
imagenet_solver.prototxt	fix ImageNet solver max iteration typo	2014-01-25 22:33:18 -08:00
imagenet_val.prototxt	change imagenet_val batch size from 200 to intended 50	2013-12-22 13:13:47 -08:00
net_speed_benchmark.cpp	More detailed net_speed_benchmark	2014-02-07 09:55:57 -08:00
synset_words.txt	cleanup whitespace	2014-01-19 14:34:12 -08:00
test_net.cpp	Made a major change: when initializing a network, the input size are no longer provided by an additional vector of blobs, but should be specified in the netparameters proto by the field "input_dim". This avoid the often awkward code of creating a dummy input vector just for the sake of initializing the network.	2013-11-15 16:58:53 -08:00
train_net.cpp	Several changes:	2013-12-02 15:44:43 -08:00