Tutorial

data/mnist/get_mnist.sh

@@ -6,19 +6,10 @@ cd $DIR
 
 echo "Downloading..."
 
-wget --no-check-certificate http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz
-wget --no-check-certificate http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz
-wget --no-check-certificate http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz
-wget --no-check-certificate http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz
-
-echo "Unzipping..."
-
-gunzip train-images-idx3-ubyte.gz
-gunzip train-labels-idx1-ubyte.gz
-gunzip t10k-images-idx3-ubyte.gz
-gunzip t10k-labels-idx1-ubyte.gz
-
-# Creation is split out because leveldb sometimes causes segfault
-# and needs to be re-created.
-
-echo "Done."
+for fname in train-images-idx3-ubyte train-labels-idx1-ubyte t10k-images-idx3-ubyte t10k-labels-idx1-ubyte
+do
+    if [ ! -e $fname ]; then
+        wget --no-check-certificate http://yann.lecun.com/exdb/mnist/${fname}.gz
+        gunzip ${fname}.gz
+    fi
+done

examples/00-caffe-intro.ipynb

@@ -0,0 +1,242 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# First Sip of Caffe\n",
+    "\n",
+    "This is a quick check to make sure we can brew."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "Before we begin, let's verify [WebSockets](http://en.wikipedia.org/wiki/WebSocket) are working on your system.  To do this, execute the cell block below by giving it focus (clicking on it with your mouse), and hitting Ctrl-Enter, or pressing the play button in the toolbar above.  If all goes well, you should see some output returned below the grey cell.  If not, please consult the [Self-paced Lab Troubleshooting FAQ](https://developer.nvidia.com/self-paced-labs-faq#Troubleshooting) to debug the issue. *This section courtesy the NVIDIA Caffe introduction.*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "print \"The answer should be three: \" + str(1+2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's execute the cell below to display information about the GPUs running on the server."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "!nvidia-smi"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now load the `caffe` Python module and switch to GPU mode for computation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "caffe_root = '../'  # this file should be run from {caffe_root}/examples (otherwise change this line)\n",
+    "\n",
+    "# make sure that caffe is in our import path\n",
+    "import sys\n",
+    "sys.path.insert(0, caffe_root + 'python')\n",
+    "\n",
+    "# load caffe and switch to the GPU\n",
+    "import caffe\n",
+    "caffe.set_mode_gpu()\n",
+    "caffe.set_device(0)\n",
+    "\n",
+    "# import standard array and plotting toolkit\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The next step is to collect the materials we'll need for our first sip:\n",
+    "\n",
+    "1. a pre-trained network for off-the-shelf use\n",
+    "2. the category names to understand the output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# make sure we have the CaffeNet model weights\n",
+    "import os\n",
+    "if os.path.isfile(caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'):\n",
+    "    print 'CaffeNet found.'\n",
+    "else:\n",
+    "    print 'Downloading pre-trained CaffeNet model...'\n",
+    "    !../scripts/download_model_binary.py ../models/bvlc_reference_caffenet\n",
+    "\n",
+    "# load ImageNet labels (for understanding the output)\n",
+    "labels_file = caffe_root + 'data/ilsvrc12/synset_words.txt'\n",
+    "if not os.path.exists(labels_file):\n",
+    "    !../data/ilsvrc12/get_ilsvrc_aux.sh\n",
+    "labels = np.loadtxt(labels_file, str, delimiter='\\t')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "With `caffe` ready, let's load our pre-trained CaffeNet (a variant of the ILSVRC2012-winning AlexNet by Krizhevsky et al.)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# load and run the net\n",
+    "model_def = caffe_root + 'models/bvlc_reference_caffenet/deploy.prototxt'\n",
+    "model_weights = caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'\n",
+    "\n",
+    "net = caffe.Net(model_def,      # defines the structure of the model\n",
+    "                model_weights,  # contains the trained weights\n",
+    "                caffe.TEST)     # for deployment (in contrast to caffe.TRAIN)\n",
+    "\n",
+    "print 'Loaded net.'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Before checking the net let's define an input pre-processor, `transformer`, to help feed an image into the net."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# configure input pre-processing\n",
+    "mu = np.load(caffe_root + 'python/caffe/imagenet/ilsvrc_2012_mean.npy')\n",
+    "mu = mu.mean(1).mean(1)  # average over pixels to obtain the mean (BGR) pixel values\n",
+    "transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})\n",
+    "transformer.set_transpose('data', (2,0,1))  # move image channels to outermost dimension\n",
+    "transformer.set_mean('data', mu)            # subtract the dataset-mean value in each channel\n",
+    "transformer.set_raw_scale('data', 255)      # rescale from [0, 1] to [0, 255]\n",
+    "transformer.set_channel_swap('data', (2,1,0))  # swap channels from RGB to BGR\n",
+    "print 'Configured input.'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Time for an image:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# download an image\n",
+    "image = caffe.io.load_image(caffe_root + 'examples/images/coffee.jpg')\n",
+    "transformed_image = transformer.preprocess('data', image)\n",
+    "plt.imshow(image)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "What a fine cup of coffee. Let's classify!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "net.blobs['data'].data[...] = transformed_image\n",
+    "net.forward()\n",
+    "output_prob = net.blobs['prob'].data[0]\n",
+    "\n",
+    "print 'What does the net say?\\n', labels[output_prob.argmax()]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Happy brewing!"
+   ]
+  }
+ ],
+ "metadata": {
+  "description": "Use the pre-trained ImageNet model to classify images with the Python interface.",
+  "example_name": "ImageNet classification",
+  "include_in_docs": true,
+  "kernelspec": {
+   "display_name": "Python 2",
+   "language": "python",
+   "name": "python2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.10"
+  },
+  "priority": 1
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}