summaryrefslogtreecommitdiff
path: root/examples
diff options
context:
space:
mode:
authorEvan Shelhamer <shelhamer@imaginarynumber.net>2015-01-16 15:59:50 -0800
committerEvan Shelhamer <shelhamer@imaginarynumber.net>2015-01-16 15:59:50 -0800
commit1f9bcf2957c01fe243406f5814129b70f2e28aa2 (patch)
tree53c3816ba1a34d664d1ce6927416a2a85d06a112 /examples
parent6af39c503677fad31c8c3c7ba784080090a01399 (diff)
parent0b6c663d9bcc7a77a4f63e7a5bb98ec18e18041f (diff)
downloadcaffeonacl-1f9bcf2957c01fe243406f5814129b70f2e28aa2.tar.gz
caffeonacl-1f9bcf2957c01fe243406f5814129b70f2e28aa2.tar.bz2
caffeonacl-1f9bcf2957c01fe243406f5814129b70f2e28aa2.zip
Merge pull request #1388 from rohitgirdhar/cifar_docu_bug
[docs] run CIFAR10 example from caffe root
Diffstat (limited to 'examples')
-rw-r--r--examples/cifar10/readme.md8
1 files changed, 4 insertions, 4 deletions
diff --git a/examples/cifar10/readme.md b/examples/cifar10/readme.md
index a329b49c..4a95cee9 100644
--- a/examples/cifar10/readme.md
+++ b/examples/cifar10/readme.md
@@ -24,8 +24,8 @@ You will first need to download and convert the data format from the [CIFAR-10 w
cd $CAFFE_ROOT/data/cifar10
./get_cifar10.sh
- cd $CAFFE_ROOT/examples/cifar10
- ./create_cifar10.sh
+ cd $CAFFE_ROOT
+ ./examples/cifar10/create_cifar10.sh
If it complains that `wget` or `gunzip` are not installed, you need to install them respectively. After running the script there should be the dataset, `./cifar10-leveldb`, and the data set image mean `./mean.binaryproto`.
@@ -39,8 +39,8 @@ Training and Testing the "Quick" Model
Training the model is simple after you have written the network definition protobuf and solver protobuf files (refer to [MNIST Tutorial](../examples/mnist.html)). Simply run `train_quick.sh`, or the following command directly:
- cd $CAFFE_ROOT/examples/cifar10
- ./train_quick.sh
+ cd $CAFFE_ROOT
+ ./examples/cifar10/train_quick.sh
`train_quick.sh` is a simple script, so have a look inside. The main tool for training is `caffe` with the `train` action, and the solver protobuf text file as its argument.