Merge pull request google#1 from kylemcdonald/patch-1

small typos
daben · Jul 2, 2015 · 7704c99 · 7704c99
2 parents b5a6690 + b2a5de3
commit 7704c99
Showing 1 changed file with 5 additions and 5 deletions.
diff --git a/dream.ipynb b/dream.ipynb
@@ -123,7 +123,7 @@
      "source": [
       "Making the \"dream\" images is very simple. Essentially it is just a gradient ascent process that tries to maximize the L2 norm of activations of a particular DNN layer. Here are a few simple tricks that we found useful for getting good images:\n",
       "* offset image by a random jitter\n",
-      "* normlize the magnitude of gradient ascent steps\n",
+      "* normalize the magnitude of gradient ascent steps\n",
       "* apply ascent across multiple scales (octaves)\n",
       "\n",
       "First we implement a basic gradient ascent step function, applying the first two tricks:"
@@ -136,17 +136,17 @@
       "def make_step(net, step_size=1.5, end='inception_4c/output', jitter=32, clip=True):\n",
       "    '''Basic gradient ascent step.'''\n",
       "\n",
-      "    src = net.blobs['data'] # input image is storred in Net's 'data' blob\n",
+      "    src = net.blobs['data'] # input image is stored in Net's 'data' blob\n",
       "    dst = net.blobs[end]\n",
       "\n",
       "    ox, oy = np.random.randint(-jitter, jitter+1, 2)\n",
       "    src.data[0] = np.roll(np.roll(src.data[0], ox, -1), oy, -2) # apply jitter shift\n",
       "            \n",
       "    net.forward(end=end)\n",
-      "    dst.diff[:] = dst.data  # specify the optimiation objective\n",
+      "    dst.diff[:] = dst.data  # specify the optimization objective\n",
       "    net.backward(start=end)\n",
       "    g = src.diff[0]\n",
-      "    # apply normaized ascent step to the input image\n",
+      "    # apply normalized ascent step to the input image\n",
       "    src.data[:] += step_size/np.abs(g).mean() * g\n",
       "\n",
       "    src.data[0] = np.roll(np.roll(src.data[0], -ox, -1), -oy, -2) # unshift image\n",
@@ -348,7 +348,7 @@
       "id": "rkzHz9E8OZOb"
      },
      "source": [
-      "We encorage readers to experiment with layer selection to see how it affects the results. Execute the next code cell to see the list of different layers. You can modify the `make_step` function to make it follow some different objective, say to select a subset of activations to maximize, or to maximize multiple layers at once. There is a huge design space to explore!"
+      "We encourage readers to experiment with layer selection to see how it affects the results. Execute the next code cell to see the list of different layers. You can modify the `make_step` function to make it follow some different objective, say to select a subset of activations to maximize, or to maximize multiple layers at once. There is a huge design space to explore!"
      ]
     },
     {