Import fixes

code/part2_classification_pytorch.ipynb

@@ -42,11 +42,15 @@
    "outputs": [],
    "source": [
     "% matplotlib inline\n",
-    "from IPython.display import display, clear_output\n",
     "import matplotlib.pyplot as plt\n",
-    "import numpy as np\n",
-    "np.random.seed(0)\n",
-    "from IPython.display import display, clear_output"
+    "from IPython.display import display, clear_output\n",
+    "import torch\n",
+    "from torch import nn\n",
+    "from torch.autograd import Variable\n",
+    "from torch.nn import functional as F\n",
+    "from torch import optim\n",
+    "import torchvision\n",
+    "from torchvision import datasets, transforms"
    ]
   },
   {
@@ -95,14 +99,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import torch\n",
-    "from torch import nn\n",
-    "from torch.autograd import Variable\n",
-    "from torch.nn import functional as F\n",
-    "from torch import optim\n",
-    "import torchvision\n",
-    "from torchvision import datasets, transforms\n",
-    "\n",
     "# Load training and test data (from the official MNIST example,\n",
     "# https://github.com/pytorch/examples/blob/master/mnist/main.py)\n",
     "trafo = transforms.Compose([\n",

code/part3_learned_reconstruction.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Learned Reconstruction\n",
+    "# Learned Reconstruction\n",
     "\n",
     "In inverse problems, we want to recover some signal $x$ from noisy measurements $y$ where we know the forward model $\\mathcal{T} : \\mathcal{X} \\to \\mathcal{Y}$\n",
     "$$\n",