From ea04cf82686af668a5da8827443a2c9f7e6daf2a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ozan=20=C3=87a=C4=9Flayan?= Date: Thu, 28 Aug 2014 14:05:09 +0300 Subject: [PATCH] [docs] Several documentation fixes - Fix a typo and a path in MNIST tutorial - Rework instructions about Fedora installation --- docs/installation.md | 6 +++--- examples/mnist/readme.md | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/installation.md b/docs/installation.md index 8e5078ab36a..898425a8b04 100644 --- a/docs/installation.md +++ b/docs/installation.md @@ -96,9 +96,9 @@ On **CentOS / RHEL / Fedora**, most of the dependencies can be installed with The Google flags library, Google logging library and LMDB already made their ways into newer versions of **CentOS / RHEL / Fedora** so it is better to first attempt to install them using `yum` - sudo yum install gflags-devel glog-devel lmdb + sudo yum install gflags-devel glog-devel lmdb-devel -**Finally** in case you couldn't find those 3 libraries in your distribution's repositories, here are the instructions to follow for manually building and installing them on **Ubuntu 12.04 / CentOS / RHEL / Fedora** +**Finally** in case you couldn't find those extra libraries mentioned above in your distribution's repositories, here are the instructions to follow for manually building and installing them on **Ubuntu 12.04 / CentOS / RHEL / Fedora** (or practically on any Linux distribution) # glog wget https://google-glog.googlecode.com/files/glog-0.3.3.tar.gz @@ -232,7 +232,7 @@ There is an unofficial Windows port of Caffe at [niuzhiheng/caffe:windows](https ## Compilation -Now that you have the prerequisites, edit your `Makefile.config` to change the paths for your setup. +Now that you have the prerequisites, edit your `Makefile.config` to change the paths for your setup (you should especially uncomment and set `BLAS_LIB` accordingly on distributions like **CentOS / RHEL / Fedora** where ATLAS is installed under `/usr/lib[64]/atlas`) The defaults should work, but uncomment the relevant lines if using Anaconda Python. cp Makefile.config.example Makefile.config diff --git a/examples/mnist/readme.md b/examples/mnist/readme.md index 266ff4c9689..975a77e5128 100644 --- a/examples/mnist/readme.md +++ b/examples/mnist/readme.md @@ -26,13 +26,13 @@ If it complains that `wget` or `gunzip` are not installed, you need to install t Before we actually run the training program, let's explain what will happen. We will use the [LeNet](http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf) network, which is known to work well on digit classification tasks. We will use a slightly different version from the original LeNet implementation, replacing the sigmoid activations with Rectified Linear Unit (ReLU) activations for the neurons. -The design of LeNet contains the essence of CNNs that are still used in larger models such as the ones in ImageNet. In general, it consists of a convolutional layer followed by a pooling layer, another convolution layer followed by a pooling layer, and then two fully connected layers similar to the conventional multilayer perceptrons. We have defined the layers in `CAFFE_ROOT/data/lenet.prototxt`. +The design of LeNet contains the essence of CNNs that are still used in larger models such as the ones in ImageNet. In general, it consists of a convolutional layer followed by a pooling layer, another convolution layer followed by a pooling layer, and then two fully connected layers similar to the conventional multilayer perceptrons. We have defined the layers in `CAFFE_ROOT/examples/lenet.prototxt`. ## Define the MNIST Network This section explains the prototxt file `lenet_train.prototxt` used in the MNIST demo. We assume that you are familiar with [Google Protobuf](https://developers.google.com/protocol-buffers/docs/overview), and assume that you have read the protobuf definitions used by Caffe, which can be found at [src/caffe/proto/caffe.proto](https://github.com/Yangqing/caffe/blob/master/src/caffe/proto/caffe.proto). -Specifically, we will write a `caffe::NetParameter` (or in python, `caffe.proto.caffe_pb2.NetParameter`) protubuf. We will start by giving the network a name: +Specifically, we will write a `caffe::NetParameter` (or in python, `caffe.proto.caffe_pb2.NetParameter`) protobuf. We will start by giving the network a name: name: "LeNet"