diff --git a/colab/README.md b/colab/README.md
index dc61ec9..6ddb958 100644
--- a/colab/README.md
+++ b/colab/README.md
@@ -15,12 +15,11 @@
 
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google/iree/blob/main/colab/low_level_invoke_function.ipynb)
 
-### [mnist_tensorflow\.ipynb](mnist_tensorflow.ipynb)
+### [mnist_training\.ipynb](mnist_training.ipynb)
 
-Trains a TensorFlow 2.0 model for recognizing handwritten digits and runs it
-using IREE
+Compile, train and execute a TensorFlow Keras neural network with IREE
 
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google/iree/blob/main/colab/mnist_tensorflow.ipynb)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google/iree/blob/main/colab/mnist_training.ipynb)
 
 ### [resnet\.ipynb](resnet.ipynb)
 
diff --git a/colab/mnist_tensorflow.ipynb b/colab/mnist_tensorflow.ipynb
deleted file mode 100644
index 9634861..0000000
--- a/colab/mnist_tensorflow.ipynb
+++ /dev/null
@@ -1,499 +0,0 @@
-{
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "name": "mnist_tensorflow.ipynb",
-      "provenance": [],
-      "collapsed_sections": []
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "PZtRtMMUZHJS"
-      },
-      "source": [
-        "##### Copyright 2020 Google LLC.\n",
-        "\n",
-        "Licensed under the Apache License, Version 2.0 (the \"License\");"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "cellView": "form",
-        "id": "TouZL3JZZSQe"
-      },
-      "source": [
-        "#@title License header\n",
-        "# Copyright 2020 Google LLC\n",
-        "#\n",
-        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
-        "# you may not use this file except in compliance with the License.\n",
-        "# You may obtain a copy of the License at\n",
-        "#\n",
-        "#      https://www.apache.org/licenses/LICENSE-2.0\n",
-        "#\n",
-        "# Unless required by applicable law or agreed to in writing, software\n",
-        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
-        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
-        "# See the License for the specific language governing permissions and\n",
-        "# limitations under the License."
-      ],
-      "execution_count": 1,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "O6c3qfq5Zv57"
-      },
-      "source": [
-        "# MNIST Model TensorFlow Training, IREE Execution\n",
-        "\n",
-        "## Overview\n",
-        "\n",
-        "This notebook creates and trains a TensorFlow 2.0 model for recognizing handwritten digits using the [MNIST dataset](https://en.wikipedia.org/wiki/MNIST_database), then compiles and executes that trained model using IREE."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "ZpkMjTQxLzLq",
-        "outputId": "f2c8bee0-5407-4fda-8950-ed7a9666292e"
-      },
-      "source": [
-        "!python -m pip install iree-compiler-snapshot iree-runtime-snapshot iree-tools-tf-snapshot -f https://github.com/google/iree/releases"
-      ],
-      "execution_count": 2,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "Looking in links: https://github.com/google/iree/releases\n",
-            "Collecting iree-compiler-snapshot\n",
-            "\u001b[?25l  Downloading https://github.com/google/iree/releases/download/snapshot-20210107.21/iree_compiler_snapshot-20210107.21-py3-none-manylinux2014_x86_64.whl (27.8MB)\n",
-            "\u001b[K     |████████████████████████████████| 27.9MB 154kB/s \n",
-            "\u001b[?25hCollecting iree-runtime-snapshot\n",
-            "\u001b[?25l  Downloading https://github.com/google/iree/releases/download/snapshot-20210107.21/iree_runtime_snapshot-20210107.21-cp36-cp36m-manylinux2014_x86_64.whl (1.0MB)\n",
-            "\u001b[K     |████████████████████████████████| 1.0MB 56.9MB/s \n",
-            "\u001b[?25hCollecting iree-tools-tf-snapshot\n",
-            "\u001b[?25l  Downloading https://github.com/google/iree/releases/download/snapshot-20210107.21/iree_tools_tf_snapshot-20210107.21-py3-none-manylinux2014_x86_64.whl (41.4MB)\n",
-            "\u001b[K     |████████████████████████████████| 41.4MB 85kB/s \n",
-            "\u001b[?25hInstalling collected packages: iree-compiler-snapshot, iree-runtime-snapshot, iree-tools-tf-snapshot\n",
-            "Successfully installed iree-compiler-snapshot-20210107.21 iree-runtime-snapshot-20210107.21 iree-tools-tf-snapshot-20210107.21\n"
-          ],
-          "name": "stdout"
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "EPF7RGQDYK-M",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "99323e03-bad5-4146-ec39-5fba2e62939b"
-      },
-      "source": [
-        "#@title Imports and Setup\n",
-        "\n",
-        "from pyiree import rt as ireert\n",
-        "from pyiree.tf.support import module_utils\n",
-        "from pyiree.compiler2 import tf as tfc\n",
-        "\n",
-        "from matplotlib import pyplot as plt\n",
-        "import numpy as np\n",
-        "import os\n",
-        "import tempfile\n",
-        "import tensorflow as tf\n",
-        "\n",
-        "ARTIFACTS_DIR = os.path.join(tempfile.gettempdir(), 'iree', 'modules')\n",
-        "print(\"Artifacts directory is: \", ARTIFACTS_DIR)\n",
-        "\n",
-        "plt.style.use(\"seaborn-whitegrid\")\n",
-        "plt.rcParams[\"font.family\"] = \"monospace\"\n",
-        "\n",
-        "# Print version information for future notebook users to reference.\n",
-        "print(\"TensorFlow version: \", tf.__version__)\n",
-        "print(\"Numpy version: \", np.__version__)\n",
-        "\n",
-        "# (Temporary) workaround for absl flags...\n",
-        "# https://github.com/googlecolab/colabtools/issues/1323#issuecomment-756343620\n",
-        "import sys\n",
-        "from absl import app\n",
-        "sys.argv = sys.argv[:1]\n",
-        "try:\n",
-        "  app.run(lambda argv: None)\n",
-        "except:\n",
-        "  pass"
-      ],
-      "execution_count": 3,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "Artifacts directory is:  /tmp/iree/modules\n",
-            "TensorFlow version:  2.4.0\n",
-            "Numpy version:  1.19.4\n"
-          ],
-          "name": "stdout"
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5vkQOMOMbXdy"
-      },
-      "source": [
-        "# Create and Train MNIST Model in TensorFlow\n",
-        "\n",
-        "The specific details of the training process here aren't critical to the model compilation and execution through IREE."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "XPo8ATGqqZbW",
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 348
-        },
-        "outputId": "b1a692a8-4523-4ba6-e00e-6cd71668fcc1"
-      },
-      "source": [
-        "#@title Load MNIST dataset, setup training and evaluation\n",
-        "\n",
-        "# Keras datasets don't provide metadata.\n",
-        "NUM_CLASSES = 10\n",
-        "NUM_ROWS, NUM_COLS = 28, 28\n",
-        "\n",
-        "(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()\n",
-        "\n",
-        "# Reshape into grayscale images:\n",
-        "x_train = np.reshape(x_train, (-1, NUM_ROWS, NUM_COLS, 1))\n",
-        "x_test = np.reshape(x_test, (-1, NUM_ROWS, NUM_COLS, 1))\n",
-        "\n",
-        "# Rescale uint8 pixel values into floats:\n",
-        "x_train = x_train / 255\n",
-        "x_test = x_test / 255\n",
-        "\n",
-        "# Explicitly cast to float32 because numpy defaults to double precision and\n",
-        "# IREE uses single precision:\n",
-        "x_train = x_train.astype(np.float32)\n",
-        "x_test = x_test.astype(np.float32)\n",
-        "\n",
-        "print(\"Sample image from the dataset:\")\n",
-        "sample_index = np.random.randint(x_train.shape[0])\n",
-        "plt.imshow(x_train[sample_index].reshape(NUM_ROWS, NUM_COLS), cmap=\"gray\")\n",
-        "plt.title(f\"Sample #{sample_index}, label: {y_train[sample_index]}\")\n",
-        "plt.axis(\"off\")\n",
-        "plt.tight_layout()"
-      ],
-      "execution_count": 4,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
-            "11493376/11490434 [==============================] - 0s 0us/step\n",
-            "Sample image from the dataset:\n"
-          ],
-          "name": "stdout"
-        },
-        {
-          "output_type": "display_data",
-          "data": {
-            "image/png": "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\n",
-            "text/plain": [
-              "<Figure size 432x288 with 1 Axes>"
-            ]
-          },
-          "metadata": {
-            "tags": []
-          }
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "tHq96SIJcNfx"
-      },
-      "source": [
-        "#@title Define a DNN model using tf.keras API\n",
-        "\n",
-        "def simple_dnn(num_classes):\n",
-        "  \"\"\"Creates a simple multi-layer perceptron model.\"\"\"\n",
-        "\n",
-        "  model = tf.keras.models.Sequential()\n",
-        "  # Flatten to a 1d array (e.g. 28x28x1 -> 784).\n",
-        "  model.add(tf.keras.layers.Flatten())\n",
-        "  # Fully-connected neural layer with 128 neurons, RELU activation.\n",
-        "  model.add(tf.keras.layers.Dense(128, activation=\"relu\"))\n",
-        "  # Fully-connected neural layer returning probability scores for each class.\n",
-        "  model.add(tf.keras.layers.Dense(num_classes, activation=\"softmax\"))\n",
-        "  return model"
-      ],
-      "execution_count": 5,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "43BH_9YcsGs8"
-      },
-      "source": [
-        "#@markdown ### Training Parameters\n",
-        "\n",
-        "batch_size = 32  #@param { type: \"slider\", min: 10, max: 400 }\n",
-        "num_epochs = 8    #@param { type: \"slider\", min:  1, max:  20 }"
-      ],
-      "execution_count": 6,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "7Gdxh7qWcPSO",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "ff0cf33d-353e-478b-b80c-3fb67d97744d"
-      },
-      "source": [
-        "#@title Train the Keras model\n",
-        "\n",
-        "tf_model = simple_dnn(NUM_CLASSES)\n",
-        "# Stateful optimizers like Adam create variable incompatible with compilation as\n",
-        "# currently implemented.\n",
-        "tf_model.compile(\n",
-        "    optimizer=\"sgd\", loss=\"sparse_categorical_crossentropy\", metrics=\"accuracy\")\n",
-        "tf_model.fit(x_train, y_train, batch_size, num_epochs, validation_split=0.1)"
-      ],
-      "execution_count": 7,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "Epoch 1/8\n",
-            "1688/1688 [==============================] - 4s 2ms/step - loss: 1.1068 - accuracy: 0.7158 - val_loss: 0.3270 - val_accuracy: 0.9142\n",
-            "Epoch 2/8\n",
-            "1688/1688 [==============================] - 3s 2ms/step - loss: 0.3705 - accuracy: 0.8982 - val_loss: 0.2648 - val_accuracy: 0.9288\n",
-            "Epoch 3/8\n",
-            "1688/1688 [==============================] - 3s 2ms/step - loss: 0.3143 - accuracy: 0.9133 - val_loss: 0.2326 - val_accuracy: 0.9397\n",
-            "Epoch 4/8\n",
-            "1688/1688 [==============================] - 3s 2ms/step - loss: 0.2728 - accuracy: 0.9236 - val_loss: 0.2127 - val_accuracy: 0.9440\n",
-            "Epoch 5/8\n",
-            "1688/1688 [==============================] - 3s 2ms/step - loss: 0.2529 - accuracy: 0.9294 - val_loss: 0.1982 - val_accuracy: 0.9477\n",
-            "Epoch 6/8\n",
-            "1688/1688 [==============================] - 3s 2ms/step - loss: 0.2327 - accuracy: 0.9347 - val_loss: 0.1853 - val_accuracy: 0.9523\n",
-            "Epoch 7/8\n",
-            "1688/1688 [==============================] - 3s 2ms/step - loss: 0.2141 - accuracy: 0.9403 - val_loss: 0.1720 - val_accuracy: 0.9572\n",
-            "Epoch 8/8\n",
-            "1688/1688 [==============================] - 3s 2ms/step - loss: 0.2040 - accuracy: 0.9417 - val_loss: 0.1652 - val_accuracy: 0.9588\n"
-          ],
-          "name": "stdout"
-        },
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "<tensorflow.python.keras.callbacks.History at 0x7fb807694160>"
-            ]
-          },
-          "metadata": {
-            "tags": []
-          },
-          "execution_count": 7
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "nZdVUd_dgTtc"
-      },
-      "source": [
-        "# Compile and Execute MNIST Model using IREE"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "DmespEaFcSEL"
-      },
-      "source": [
-        "#@title Wrap the model in a tf.Module with IREE-compatible settings and convert to MLIR.\n",
-        "\n",
-        "# Since the model was written in sequential style, explicitly wrap in a module.\n",
-        "inference_module = tf.Module()\n",
-        "inference_module.model = tf_model\n",
-        "\n",
-        "# Hack: Convert to static shape. Won't be necessary once dynamic shapes are in.\n",
-        "input_shape = list(tf_model.inputs[0].shape)\n",
-        "input_shape[0] = 1  # Make fixed (batch=1)\n",
-        "\n",
-        "# Produce a concrete function to compile.\n",
-        "inference_module.predict = tf.function(input_signature=[\n",
-        "    tf.TensorSpec(input_shape, tf_model.inputs[0].dtype)\n",
-        "])(lambda x: tf_model.call(x, training=False))\n",
-        "\n",
-        "# Only try to compile the function we care about:\n",
-        "exported_names = [\"predict\"]"
-      ],
-      "execution_count": 8,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "G7v-2EbjyggO"
-      },
-      "source": [
-        "#@markdown ### Backend Configuration\n",
-        "\n",
-        "backend_choice = \"iree_vmla (CPU)\" #@param [ \"iree_vmla (CPU)\", \"iree_llvmaot (CPU)\", \"iree_vulkan (GPU/SwiftShader)\" ]\n",
-        "backend_choice = backend_choice.split(\" \")[0]\n",
-        "backend = module_utils.BackendInfo(backend_choice)"
-      ],
-      "execution_count": 9,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "IDHI7h3khJr9",
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "outputId": "79f3191b-7e8e-4e10-9cea-cff168f7c958"
-      },
-      "source": [
-        "#@title Compile the mhlo MLIR to an IREE backend and prepare a context to execute it\n",
-        "\n",
-        "iree_module = module_utils.IreeCompiledModule.create_from_instance(\n",
-        "    inference_module, backend, exported_names, ARTIFACTS_DIR)\n",
-        "\n",
-        "print(\"* Module compiled! See intermediate .mlir files in\", ARTIFACTS_DIR, \"*\")"
-      ],
-      "execution_count": 10,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "I0107 21:49:35.160961 140429953972096 module_utils.py:88] Outputting intermediate artifacts (--artifacts_dir is set):\n",
-            "  output_file: /tmp/iree/modules/iree_vmla/compiled.vmfb\n",
-            "  saved_model_dir: /tmp/iree/modules/tfmodule.saved_model\n",
-            "  save_temp_tf_input: /tmp/iree/modules/tf_input.mlir\n",
-            "  save_temp_iree_input: /tmp/iree/modules/iree_input.mlir\n",
-            "  crash_reproducer_path: /tmp/iree/modules/reproducer__iree_vmla.mlir\n"
-          ],
-          "name": "stderr"
-        },
-        {
-          "output_type": "stream",
-          "text": [
-            "INFO:tensorflow:Assets written to: /tmp/iree/modules/tfmodule.saved_model/assets\n"
-          ],
-          "name": "stdout"
-        },
-        {
-          "output_type": "stream",
-          "text": [
-            "I0107 21:49:35.632078 140429953972096 builder_impl.py:775] Assets written to: /tmp/iree/modules/tfmodule.saved_model/assets\n"
-          ],
-          "name": "stderr"
-        },
-        {
-          "output_type": "stream",
-          "text": [
-            "* Module compiled! See intermediate .mlir files in /tmp/iree/modules *\n"
-          ],
-          "name": "stdout"
-        },
-        {
-          "output_type": "stream",
-          "text": [
-            "2021-01-07 21:49:35.767974: I external/org_tensorflow/tensorflow/cc/saved_model/bundle_v2.cc:32] Reading SavedModel from: /tmp/iree/modules/tfmodule.saved_model\n",
-            "2021-01-07 21:49:35.768968: I external/org_tensorflow/tensorflow/cc/saved_model/bundle_v2.cc:55] Reading SavedModel debug info (if present) from: /tmp/iree/modules/tfmodule.saved_model\n",
-            "Created IREE driver vmla: <pyiree.rt.binding.HalDriver object at 0x7fb803d9d2d0>\n",
-            "SystemContext driver=<pyiree.rt.binding.HalDriver object at 0x7fb803d9d2d0>\n"
-          ],
-          "name": "stderr"
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "S2FYao92Xd6r",
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 297
-        },
-        "outputId": "38a1c963-f484-455e-da78-1dcabdf1f92b"
-      },
-      "source": [
-        "#@title Execute the compiled module and compare the results with TensorFlow\n",
-        "\n",
-        "# Invoke the 'predict' function with a single image as an argument\n",
-        "iree_prediction = iree_module.predict(x_train[sample_index][None, :])[0]\n",
-        "tf_prediction = tf_model.predict(x_train[sample_index][None, :])[0]\n",
-        "error = tf_prediction - iree_prediction\n",
-        "\n",
-        "fig, axs = plt.subplots(1, 2)\n",
-        "fig.set_figwidth(12)\n",
-        "\n",
-        "ax = axs[0]\n",
-        "ax.plot(iree_prediction, linewidth=2, label=backend.backend_name)\n",
-        "ax.plot(tf_prediction, linewidth=2, label=\"tf\")\n",
-        "\n",
-        "ax.set_title(\"Predictions\")\n",
-        "ax.set_ylabel(\"Softmax 'Probability'\")\n",
-        "ax.set_xlabel(\"Digit\")\n",
-        "ax.set_ylim(0, 1)\n",
-        "ax.set_xlim(0, 9)\n",
-        "ax.legend(frameon=True)\n",
-        "\n",
-        "ax = axs[1]\n",
-        "ax.plot(error)\n",
-        "\n",
-        "ax.set_title(\"Error\")\n",
-        "ax.set_ylabel(\"Numerical between TF and IREE\")\n",
-        "ax.set_xlabel(\"Digit\")\n",
-        "ylim = 1.25 * np.max(np.abs(error))\n",
-        "ax.set_ylim(-ylim, ylim)\n",
-        "ax.set_xlim(0, 9)\n",
-        "\n",
-        "fig.tight_layout()"
-      ],
-      "execution_count": 11,
-      "outputs": [
-        {
-          "output_type": "display_data",
-          "data": {
-            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1gAAAEYCAYAAABBWFftAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdeVyVdd7/8dfFJouAsgnIIiIIYgiuZWKIM1nYZC41ebfYLE1m2cw0bXT/ZlrurJzRaZkym2ZybBlNM1PL+y7TTEtGExU3VASVfTuIgCwHzrl+fyBHEZDtnHNx4PN8PHjIuc51vtebA8dzfc73e32/iqqqKkIIIYQQQgghesxO6wBCCCGEEEII0VdIgSWEEEIIIYQQZiIFlhBCCCGEEEKYiRRYQgghhBBCCGEmUmAJIYQQQgghhJlIgSWEEEIIIYQQZiIFlhBWsHfvXqZOndpq+8yZM9m7d69Zj1VQUEB8fDwGg8Gs7QohhBBCiI45aB1AiN4gKSmJsrIy7O3tGThwIMnJyTz11FPY29tb9Lhffvlltx43cuRIvv76a0JDQ1vdFxgYyMGDB3saTQghRB915Xtes7fffpvJkydrmEqIvkMKLCEuWblyJZMnTyYrK4v777+fYcOGMX/+fK1jCSGEEGbX/J4nhDA/GSIoxFXCw8MZN24cmZmZADzzzDMsWbKERx99lPj4eKZNm0Z1dTUAX3/9NbfddhsTJkzgwQcfpKSkxNTOpk2bSExMZMqUKezevbvFMf7yl78QHx9PVFQUe/bsaZVh37593HnnnYwbN45bbrmFffv2AfDrX/+a+Ph4AGbNmkV8fDxLliwxPe7uu+8mLi6OkSNH0tjY2KLNrKws/uu//otx48YxZ84cDh06ZLrvmWee4dlnn2X+/PnEx8eTkpLS4rErV65kypQpjB07ljlz5lBcXNzl51UIIUTvd633vM8++4z58+fzxhtvMGnSJCZNmmQa5v7NN99wyy23MGHCBB566CFKS0tbtJuUlMRHH33EnDlziIuLY+HChVb/2YSwGlUIoU6bNk394YcfVFVV1RMnTqjXX3+9um7dOlVVVfXpp59WJ0yYoG7fvl1tbGxUjx07ptbW1qrp6enq+PHj1UOHDqkNDQ3qX//6V/Whhx5SVVVVCwoK1NjYWPXQoUNqVVWV+vOf/1xNSEi45nGb5eTkqPHx8eo333yjNjY2qllZWer+/ftb7BMZGamePXu2zZ8lNzdXjYyMVBsaGkzbjEaj+rOf/Ux955131IaGBnXjxo3qjTfeqNbW1pp+xqlTp6r5+flqfn6+GhcXp6anp6uqqqpZWVlqbGysmpOToxoMBjU9PV3V6XTdeZqFEEL0Am299zRr7z1PVVV1w4YNalxcnPraa6+pdXV1anFxsZqTk6MWFRWpY8aMUVNTU9X6+nr1j3/8o/rwww+3OuZtt92mnjp1Sm1oaFAPHjxo8Z9TCK3IEEEhLnnkkUewt7dn0KBB3HXXXcydO9d036RJk0hKSgJg1KhRAHz66afMnj2bMWPGAPDLX/6SSZMmodfr+f7774mNjTXdd/fdd/PXv/61Uzm+/PJLpkyZwvTp0wEYPnx4j3+2vLw8srOz+eUvf4mDgwN33HEHr7/+Ounp6UyaNAmAadOmERgYCDRd43XmzBliY2NRFAWDwUB2djb+/v7Exsb2OI8QfdHSpUvZtGkTXl5efPHFF11+/O7du1m2bJnpdlZWFuvXryc6OtqcMYUALr/nNfvqq6/w9vYG2n7Pa+bi4sLixYuxt7fHz88PgA0bNhATE8P1118PwIMPPsiMGTNobGzEweHyqeZdd91FREQEAHFxcZb74YTQmBRYQlxyrQt825pMorCwkH379vHZZ5+Ztjk6OlJSUsL58+dNb1QAPj4+nc5RWFjI0KFDu5C8YzqdDnd3d5ycnFpkKisrM9329PQ0fe/o6IherwcgLCyMF198kXfeeYff/e53JCQk8PLLLzNw4ECzZhTC1v30pz8lOTm51RDbzkpISCAhIQGAkpIS7r33XimuhMV09T2vWVBQUKsJoHQ6XYv3OR8fHwwGA+fPn8fX17dT7QrRl8g1WEJ0QluzCQYEBLBo0SL2799v+jpy5AhBQUF4eXmh0+lM+15ZyHQkICCA/Pz8a+6jKErnwwPe3t5UVVWZiqbmTFcWgdcyZ84c1q5dyzfffMPZs2f59NNPu3R8IfqDsWPHMnjw4BbbduzYwbx587j99tt55ZVXOt3W1q1bmTFjhrkjCtEp15pBt637vLy8WrzPNc9QePXr4creLCH6MimwhOim2bNns3btWo4dO4aqquh0OrZu3Qo0fRJ95MgR0tPTqa6uZu3atZ1ud+bMmezevZvt27djMBg4d+4caWlpLfbx8fExTcLRGUFBQYSFhfH+++/T2NjIpk2b0Ov1piGM15KTk0Nqaip6vR57e3tUVZXeKyE6QafTsWLFCj788EM2b95MYWEhqampnXrs5s2bmTlzpoUTCmEeCQkJHDt2jP/85z/o9Xree+89EhISpKAS/ZYUWEJ0U3x8PM888wwpKSmMGzeOuXPncvToUQCGDBnC//zP//Db3/6WW265hYkTJ5oeZzAYiI+PJz4+noKCAhYuXEh8fDzr168HIDg4mBUrVrBixQomTJjAb37zm1aLBj/++OO8+OKLJCQksHz5cqBpMeP4+Hhuu+02ACZMmEB8fDxnzpxBURT++te/snPnTiZNmsT777/Pm2++iYuLS4c/Z0NDA8uXL2fSpEnMmDGDuLg4Zs2aZZbnUIi+7NChQ+Tm5nL33Xcza9YsMjIyyMvL41//+he33XZbi6/XXnvN9Ljs7Gzq6uqIiorSML3o65rfe5q/Nm7c2O22hgwZwp///Geee+45Jk+eTEFBAS+88IIZ0wphWxRVVVWtQwghhBB9QV5eHgsXLuSLL75g+/btbN261fQhSGe9+eab2NnZ8eijj1oopRBCCEuSHiwhhBDCAuLi4khLS6OoqAiA/Pz8VmsDteWLL74gOTnZ0vGEEEJYiMUKrKVLlzJ58mTTcKVr2bp1KzfffDMzZsxgx44dlookhBBCWMwLL7zA3XffzZkzZ5g6dSqHDh3i+eefZ+HChfzsZz/j97//PbW1tddsIz09HVdXV7MszyCEEEIbFhsieODAARwdHUlJSbnmeiB6vZ5bbrmFdevWodfruf/++/n666+xs5PONSGEEEIIIYRtsVgV09Z0tW05fPgwERER+Pj4EBgYSEBAACdPnrRULCGEEEIIIYSwGM3nzywtLcXX15c1a9bg6emJj48PJSUlbS6uePVU1UIIIfqucePGaR2hU+S9SQgh+peO3p80L7CazZ8/H4Bt27Zdcz9beMPNyMhos0DsbSSn+ZxO/57hn91Gqts0bnyq+1PdWostPKcgOS3BVrLaWtFiC+9NYDu/f8lpXraSE2wnq+Q0L1vJCZ17f9L8QidfX98WsyqVlZXh5+enYSIhuq7syDbsFJURNYe0jiKEEEIIITRk9QJr+fLlLdYEiY2NJTMzE51OR2FhIUVFRYwcOdLasYToEYeSSwsMU055Sb7GaYQQQgghhFYsVmBdPV3t9u3bgaZrrq7ssXJycuKJJ55g/vz5LFiwgJSUFJlBUNgcn+rLE7Pkn9inYRIhhBBCCKEli12D9dxzz/Hcc8+12v7qq6+22pacnCyLKgqbVXuximBDHihNty+ePQBTZ2sbSphFQ0MDeXl51NXVdbhfRkaGlVL1TG/L6uzsTFBQEI6OjlpHEUIIIcyi10xyIYStysn4kZHK5eXkHEuPaphGmFNeXh7u7u4MGzYMRVHa3a+2thYXFxcrJuu+3pRVVVV0Oh15eXmEhYVpHUcIIYQwCxmLJ0QPVWQ3zSZz1i4EAN+Lso5bX1FXV4e3t/c1iyvRfYqi4O3t3WEPoRBCCGFLpMASoqeKDgNQGHo7Dao9QYYCLlZVaBxKmIsUV5Ylz68QQoi+RgosIXpocOUJANxHXM85u2DsFJXcjB81TiWEEEIIIbQgBZYQPdDYoCek4QwAwdHXU+wSDsCFMwe0jCWEEEIIITQiBZYQPZB3+jDOSgOF+OLp5UuNZwQAyqVhg0KYy/bt2/n73/+udYw2ZWdnM2vWLOLj4zly5IjWcYQQQghNSYElRA+UZTYNBSxyjQTA3i8KuDxsUAhzmT59Or/5zW+0jtGm4cOHs2nTJkaPHq11FCGEEEJzMk27ED3QmJ8OQJ1P04nloOAYSIfQxrM06OtxdBqgZTxhRr9YtY9vT5Z2vGMXTBvpy6pfTOxwv6eeeop9+/aRlJTEn/70JwD27t3LypUrcXd3Jzs7mxtuuIH//u//ZseOHaxYsQK9Xs8NN9xASkoKgGl7fX09kydPNm1vy5YtWzh48KDpWEuWLCEmJobc3Fz27t1LcXExU6ZMYc+ePaxZswYvL69221q4cCEFBQU4ODgwZ84c7r333q48RUIIIYTNkR4sIXrA/fxxAFxC4pv+dXMnT/HHSWkk99QhLaOJPuTPf/4zjz32WKvtBw4c4NFHH+WLL75g8eLF6HQ6VqxYwYcffsjmzZspLCwkNTW1xfZ169aZtrdn2rRp7Nq1C1VtWt9t165dJCUlAZCUlMRNN91EcHAwCQkJHDx48JrZn3/+eTZv3swnn3zChx9+SGmpeYtUIYQQoreRHiwhukk1GgnSnwYgIOpyL0SJWyRB1UXoTu9n+OhJWsUTZnatniatFu+NiYkhMrJpeKqHhwfbt28nNzeXu+++G4Camhry8vKoqakxbTcajdTV1ZGXl9duuwMHDiQ8PJwjR47g4OBAUFAQHh4eAHh6elJdXW36t6qq6poZ169fz/bt21FVlZKSEkpKSvD19TXTMyCEEEL0PlJgCdFNRbmZBHCR83jgFxhm2q73uQ6qd2EoSNcwnegP3N3dW22bMmUKy5cvb7Ft+/btpu2dLQZnzJjBtm3bcHR05OabbzZtVxSlxZfRaGy3jb179/LDDz+wZs0aXFxcmDNnzjX3F0IIIfoCGSIoRDcVnWya4CJvQDiK3eWXkktIHADuFcc1ySX6r7i4ONLS0igqKgIgPz+f0tLSdrdfS1JSEjt37mTHjh385Cc/6dTxBw8eTHFxsel2dXU1gwYNwsXFhczMTE6ePNnNn0wIIYSwHdKDJUQ31eU2XXtycfCoFtuHRk2CXRCsz0I1GlsUX0J0VV5eHo888ggXLlygrq6OtLQ0Hn/8cZydnVvt6+3tzfPPP8/ChQsxGAy4uLiwbNkyQkJCTNsbGhpwc3Nj2bJl1zzuoEGD8PX1paGhAW9v705lfeCBB0hJSeFvf/sbf//730lISGDdunUkJyczfPhwRo0a1XEjQgghhI2TAkuIbnLRHQPAISiuxXafwFDKGIQPFeSfPcnQ4dFaxBN9RFBQEJs2bWrzvkmTWl/jl5iYSGJiYrvbu3K92Pvvv9/i9uLFi6+5/9ixY/nqq69abHv33Xc7dSwhhBCir5CP1oXoJv+aTAB8I1pPflDg3LTgcPGpvVbNJIQQQgghtCU9WEJ0Q0VZEf6UUaMOICi89eKqF71GQcGP1OfJRBei95o1a1ab2z/77DPs7e2tnEYIYSnGS0suCCGsQwosIboh9/heBgE5jsOJcmj9MnIKGgMF4HppGKEQvVF7Qw+FEH3Huh9zeXHLOXY8MRw/j9bXbgohzE+GCArRDRfPpQFwwXNkm/f7RTYNGwyozbRaJiGEEOJKDQYjb2zPpFpv5J8/nNE6jhD9hhRYQnSDQ8lRAJSAMW3ePzRsFNWqC36Uoytuf0FXIYQQwlI2Hyogv6KWQHcHPko9x4WaBq0jCdEvSIElRDf4Xmxaz2dw+Pg277eztyfXaTgA+Rky0YUQQgjrMhpV3vkuiyh/d/47cQgX9QY+SD2rdSwh+gUpsITooprqCwQb8mlU7QiOGtfufpWDmqZnv5hzyFrRRB/2r3/9i9ra2hbb9u/fT3JyMrNmzeL06dMaJRNC9EZfHy/mdEk1DyeGM9xrAElRfqzac5ZavUHraEL0eVJgCdFFOSf2Y6eo5NqH4Ozi1u5+SmDT8EGn0iPWiib6sA8++KBVgbV582YeeughNm3axIgRIzRK1nukpaWZvi8uLm5x3zfffGPtOEJoRlVV3tl5mhAvV2ZeFwDAosRwyi/qWftjjsbphOj7pMASoosuZDedxJW5R15zP6/hTb1bftUnLZ5J9F179uxh1qxZlJSUsGDBAmbNmkVxcTGzZs3i//7v/3jjjTekB+uSl156yfT9woULW9z39ttvWzuOEJrZk6UjPe8CD900HAf7plO98cO8mDjMi7/vykbfaNQ4oRB9m0zTLkQXKUWHATD4XXfN/UKixqFX7RmqFnKxqgI390HWiCcs5eM7IfPrNu9y6W6bETfDPeuvucvkyZPZtGkTSUlJrF69Gi8vL6BpivVnnnmGxMREbrnllu4m6FPUK9b6Ua9a9+fq20L0ZW9/expf9wHMHRvUYvuiaeE8sOpHPj+Uz13jgzVKJ0TfJz1YQnTR4MoTALgPa//6KwCnAc7kOoQ2DSc8vs8a0YTo1xRFafP7tm4L0Vcdyq1gT5aOBxPCcHZsuWD4TZG+xAR6sPK7LAxG+dBBCEuRHiwhuqCxQU9Iw1lQIGjUpA7317lHEV6RzYUzaTDpZssHFJZzjZ6m2tpaXFy63Y8lzOTEiROMHTsWVVWpr69n7NixQFPvlV6v1zidENax4tvTeLo48l+TQlvdpygKDyeG8+i/D/LVsSKSL12fJYQwLymwhOiC3Mx0wpQGCpQhBA726XB/45DroGIrSrFMdCF6xs3NjQsXLpiGCIrWMjIytI4ghKYyi6v4+ngxjyWNYOCAtk/xbh0dQJjPKVbsPM2to/2ld1cIC5AhgkJ0QVnmjwAUuV57gotmHmFNn6B7XRpWKER33XfffTzyyCPMnz+f0tJSreP0SjKLoOjv3tmZhYujPQ/cGNbuPvZ2CgtvGs7R/Ep2Z5ZZMZ0Q/YcUWEJ0gaEgHYB6n5hO7R8cPRGAkMZzNOjrLZZL9H133XUXW7duZc2aNfj6+gLw6quvygQXV7DULILFxcXMnz+fmTNnMnv2bH744YdutyWEpeSW17ApvYD5E0PwcnO65r6z44Pw93Dm7W9l9lEhLEEKLCG6wP38cQBcQuI7t7+nF3lKAE5KIzknD1oymhD9nqVmEbS3t+e5557jyy+/5K233uKZZ57pdltCWMp7u7OxU+DBqe33XjVzcrDj1wlh7D1TTtq581ZIJ0T/IgWWEJ2kGo0E67MACIzqeIKLZiVuTcMJdad/tEguIUQTS80i6OPjQ1RUFABDhw6loaFBJs0QvUppVT2f/JjL7PihBHh2bsKd+RNDGOzqyDs7pRdLCHOTSS6E6KTCnEwCuUg5HvgGtJ6dqT31vqOh+juMhYctmE5YiqqqchG4BZlzfSprzCK4e/duYmJicHJqOQTLVibYqKurs4mskrNrVqWVo2808tOgtv8W28s5M3IgHx0qYeuedMIGX3tYobX0lue0I5LTvGwlZ2dJgSVEJxWd3EcgkOccgZdd5zt/3ULGwhnwqOg7/3H0F87Ozuh0Ory9vaXIsgBVVdHpdDg7O5ulPUu/OZeWlrJ06VJWrFjR6r7o6GiLHttcMjIybCKr5Oy8yroG/nftDpKvC+Cn149pc5/2cj4Rqmfj8R18lWPkjcm94/nuDc9pZ0hO87KVnNByQqX2SIElRCfpc5uuobo4uGv/AQRGT4TvILj+NEaDATt7+44fJHqFoKAg8vLyOpy1r6GhAUdHRyul6pneltXZ2ZmgoCCztVdaWkpxcTEjR47E0dERg8HAli1beP/999m8eXO3262vr+exxx7jqaeeIiQkxGx5heipD1PPUVXfyMOJ4V1+7CBXJ/5rUgj//P4Mf/jpSEK8XS2QUIj+RwosITrJWXcMAMeguC49zsc/hDIG4aNUkH/uBEOHd24GQqE9R0dHwsI6vmDclj55s6WsXbV27Vpef/11QkNDURSF3/72tzz77LOMHDmSF154odvtqqpKSkoKt912G1OnTjVjYiF6plZv4P3vzzA10pfRQz271cavE4azes853t2VxZLZ15k5oRD9kxRYQnRSYO0pAPwiJnT5sfnOEfjU/UjxyX1SYAlhIR9++CFbt27Fy8uLwsJCZs6cyV/+8hemT5/eo3bT0tL46quvyMrKYt26dQD8/e9/Z8iQIeaILUS3rdufi+6inkXd6L1qNsTDmbnjgli/P4/fTo/Az8M8Q3aF6M8sWmBt3bqV119/HUVRePrpp0lKSmp333/84x98/vnnGI1GkpOTefTRRy0ZTYguKS/Jx49yatQBBIV3/RO+Gu8YyP+R+rxDFkgnhABwcnLCy8sLgICAAAIDA3tcXAGMHz+eY8eO9bgdIcypwWDk77uyGRc6mElhXj1qa+FNw/nkxxz++f0ZUpL7Zg+3ENZksQJLr9ezbNky1q1bh16v5/777ycxMRG7NiYHKCoq4pNPPmHr1q2oqsqtt97KrFmzCA4OtlQ8Ibok/8Q+vIAcp3CiunEN1YCgOMgH1/Lj5g8nhAAgNze3xQLDRUVFLW6vXLlSi1hCWMTmQwXkV9Ty4qyYHk/CE+rtxm2xgXz0n3MsShyBp2vvuU5TCFtksQLr8OHDRERE4OPjAzR9mnjy5Ml2x/4bDAb0ej2qquLo6Ii7u7ulognRZRfPHgDggmdUtx7vFzEB9kJgbaY5YwkhrnD17H6//OUvNUoihGUZjSrvfJdFlL87SVF+Zmnz4cRwNqcX8EHqWRZPjzBLm0L0VxYrsEpLS/H19WXNmjV4enri4+NDSUlJmwWWv78/999/P9OmTcNgMPD0008zaNCgNtu1hTnybWUuf8nZBQVNMwhWuoReM0t7WY1GGKS64Kuc58c93zFwsHneELurVzynnSA5zc+WsnbVxIkTtY4ghFV8fbyY0yXVvHF3nNmWkIgO8CApyo/3fzjDrxLCcHWSy/SF6C6Lv3rmz58PwLZt29rd58KFC+zatYvt27fT0NDA/PnzSUxMxM+v9UmoLcx+ZSuzdEnOzstZnw3AsHHTibhGlmtlPe4UzqiGowyoLyU6+iaL5Oys3vCcdobkND9bydqZdUauNm/ePD799NMu3yeELVFVlXd2nibEy5WZ1wWYte1FieHMW5nK2n25/HJKxzOoCiHaZrECy9fXt8XaMWVlZW0WTACpqakEBASYhgWOGjWKjIyMdvcXwpouVlUQZCigAXtCosZ1u53KQdFQepSLOQeAeeYLKIQAoKSkhFWrVrXarqpqh2uZCWEr9mTpSM+7wJLZo3Gw7/yi950xfpgXE8O8eG93NvdeH4qTg3nbF6K/sNgrJzY2lszMTHQ6HYWFhRQVFTFy5EgAli9fzvLly037+vj4cOTIEfR6PXV1dRw/ftysC08K0RO5J/Zjp6jk2gczwLn7izDaBY4BYEDpUXNFE0JcwWg0cvHixVZfNTU1GAwGreMJYRYrdp7G130Ac8da5jxpUWI4hRfq+PxgvkXaF6I/sFgPlpOTE0888YRpiGBKSoppBsGrP0kcP348U6ZM4fbbb8fOzo558+YRHt79NR2EMKcL2U1DlXTuUQzvQTve4eMgHXwvykQXQliCj49Pu0t8fPPNN1ZOI4T5Hcqt4IfTOlJujcLZsesz2nbGTZG+xAR6sPK7LOaOC8LezjzXeAnRn1j0Gqzk5GSSk5NbbX/11VdbbXvqqad46qmnLBlHiG5Rig4DYBjSsxXug0eORa/aE0wB1ZXnGegx2BzxhBCXrF+/vlv3CWErVnx7Gg9nB+65PtRix1AUhUWJI3jk3wf46lgRyWa+zkuI/kAG1wrRgcGVJwBwHza2R+04DXAmx2EYALkZ+3oaSwhxFUfH9tfuudZ9QtiCzOIqvj5ezAOThzFwgGXnKLtltD/Dfdx4+9vTqKpq0WMJ0RdJgSXENTTo6wltPAtA8KhJPW6v3L3pOsTmYYdCCCFEZ7zzXRYujvY8cKPlZ/ezt1N46KbhHCuoZFdmmcWPJ0Rf026B9dZbb/HWW2+1OSOTEP1FXuYhnJRG8pUheAzy7nF7qn8sAHbFR3rclhBCiP4ht7yGTYcKuHtiMF5uTlY55uz4IPw9nFnx7WmrHE+IvqTdAmvo0KEMHTqUIUOGWDOPEL1KWeZ+AIpdR5qlPc+wpmnevapOmqU9IYQQfd97u7OxU+DBhJ5MtdQ1Tg52PDh1OHvPlJN2rtxqxxWiL2i3wJo9ezazZ89uc5IKIfoLQ0E6APW+MWZpLyh6AkZVIaTxLPr6OrO0KYQQou8qrarnkx9zmR0/lMBBLlY99vyJwQx2dWTFt1lWPa4Qtk6uwRLiGtwrjgPgGhJnlvYGegwm3y4AJ8VA7skDZmlTCCFE37XqhzPoDUYeusn6y9e4OjnwwOQwtp8o4URRpdWPL4St6rDAWr16NeXl0jUs+h/VaCRY3/SpXWDU9WZrt8QtEgBd1n6ztSmEgIKCgmt+CWFrKusa+DD1HLeO9ifcd6AmGRZMDsXNyZ53dkovlhCd1eE8n5WVldx7772EhIQwa9Yspk+fjpOTdS6wFEJLhedOEUgNOjzx8Q8xW7t639FQvRP10vBDIYR5PPTQQwDo9Xpyc3MJDAxEVVUKCgoIDg7m66+/1jihEF3zYeo5quobWZQ4QrMMg1yduOf6UP6xO5vHfxpJqLebZlmEsBUd9mAtXryYrVu3smjRIg4cOMDMmTN55plnSE1NtUY+ITRTfGovAPnOESh25htN6xbatJ6WR0WG2doUQsCWLVvYsmULUVFRbN68mW+++Ybt27ebtglhS+oaDKz64QxTI30ZPdRT0yy/mhKGg50d7+7K1jSHELaiU2eNdXV15OTkcO7cOdzd3Rk2bBirVq0iJSXF0vmE0Exd7iEALnqNMmu7gVETAQjWZ2M0GMzathACMjMzCQm53OscEhJCVpYMbxK2Zd3+XMqq9SxKtP61V1cb4uHM3HFBfLo/j5JKmaBJiI50OETwiSeeID09nenTp/P444+3+BRwxowZFg0nhJZcdccAcAoyzwQXzXz8gyllMNYyjpAAACAASURBVL7KefLOZBA0YrRZ2xeiv5s9ezY/+9nPGDduHKqqcujQIebOnat1LCE6rcFg5N3vshkXOphJYV5axwFg4U3D+eTHHP7x/RmeTY7WOo4QvVqHBdbMmTNZunQp9vb2re775JNPLBJKiN4goDYTAL+I8WZvu8AlAt/afRSf+lEKLCHM7MEHHyQ5OZnjx4+jKAqLFy8mMDBQ61hCdNrmQwXkV9Ty4qwYFEXROg4Aod5u3BYbyMf/OccjiSPwdHXUOpIQvVaHQwRHjx7dqrjS6XQADBo0yDKphNCYrjgPP8q5qDozdLj5C6Aar6Z1tfR5B83ethACnJycCAoKIiAggPPnz3Ps2DGtIwnRKUajyjvfZRHl705SlJ/WcVp4ODGci3oDq1PPah1FiF6twx6s3/zmN2zcuLHFtscee4yPP/7YYqGE0FrBiX14AzlOw4luo/e2pwYEx0E+uJUfN3vbQvR3f/zjH/n+++8JCgoybVMUhQ8++EDDVEJ0zraMYk6XVPPG3XG9pveqWXSAB9Oj/Fj1wxl+nRCGq1OHp5FC9EvtvjLq6+upra3FYDBw4cIFVFUFoKKigoqKCqsFFEIL1eeaepYqPS0zznxI5CT4DwTWZVqkfSH6s3379rFt2zYcHOTkT9gWVVVZ8e1pQrxcmXldgNZx2rRoWjhz30llzb5cfjUlTOs4QvRK7b77rF27ltWrV1NaWsqcOXNMBZa7uzsPPPCAtfIJoQmn0iMA2AWOsUj7AaGRVKku+CgVlBXlmHWdLSH6u4SEBI4dO8aYMZZ5/QphKXuydKTnXWDJ7NE42JtveRBzGhfqxcQwL/6xO5v7rg/FyaF35hRCS+0WWAsWLGDBggXccccdfP7559bMJITm/KpPAjA4fJxF2reztyd3wAhG6Y+Qn7FXCiwhzGjDhg189NFHODk54eDggKqqKIrCgQMHtI4mxDWt2HkaX/cBzB0b1PHOGlqUGM4Dq37k84P53DUhWOs4QvQ6HY6fePrpp62RQ4he42JVBUONhTRgT/DIsRY7TuWgaCg5Qu25g8CdFjuOEP3NwYMyeYywPYdyK/jhtI6UW6NwdjT/tb/mdFOkLzGBHrzzXRZzxwVhb9e7rhUTQmsd9uvecMMNrbbt2rXLImGE6A1yM37ETlHJcQhhgLOrxY5jf2n4oVPZEYsdQ4j+SqfTkZGRwbFjx0xfQvRmK749jYezA/dcH6p1lA4pisKixBGcKbvI/x0t0jqOEL1Ot64Afu2115g6daq5swjRK1w4kwZAuXsU4RY8jveICXAI/C6esuBRhOh/Pv74Yz744ANKS0sJCwvj5MmTxMTEyNqNotfKLK7i6+PFPJY0goEDbGNylltG+zPcx40VO0+TfJ1/r5vxUAgttfsqfu+993jwwQd56aWXWmxXVZXi4mKLBxNCK0rRYQAMQ66z6HGCI+PQqw4EUUTVhXLcPb0sejwh+ouNGzfy5ZdfMm/ePDZs2EBmZiZ/+9vfut3e0qVL2bRpE15eXnzxxRdmTCpEk3e+y8LF0Z4HbrSdWfns7RQW3hTOUxsOsyuzjJsifbWOJESv0e4QwfDwps/ut2/fTkxMjOlr9OjRODs7Wy2gENbmVXkCAI8wy0xw0czRaQA5Dk1DQXIz9ln0WEL0J42NjTg4OKAoCnq9noiICLKzs7vd3k9/+lPeffddMyYU4rLc8ho2HSrg7onBeLk5aR2nS+6IH0qApzNvf3ta6yhC9Crt9mAlJSUBMHHiRGbPnt3ivtWrV1s2lRAaadDXE9J4DhQIjp5o8eOVe0TB+Swqz6TB9bdY/HhC9Af+/v4UFxeTlJTEggULGDx4cItFh7tq7Nix5OXlmTGhEJe9tzsbOwUeTBiudZQuc3Kw49cJw/mfL46Tdq6ccaEyEkMI6MQ1WEuXLm217e2337ZIGCG0lnPyIOFKI3mKP0FWGLKn+sfC+S+xL5aJLoQwl5UrVwKwePFiJk2aRHV1NQkJCRY9ZkZGhkXbN5e6ujqbyNpfcp6vbWTtvlymhQ3kQuFZLhSaL9uVLPl8jvUw4jHAjqVb0nlhun+P2+svv3trkZza6NaVlE5OttWFLURnlWftJxwocYvEGquQeIaNgwzwqjphhaMJ0f9MnGj5nmiA6OhoqxynpzIyMmwia3/J+ef/O0GDUeXpWWMJ9x1oxmQtWfr5/HWpE3/ddgoGDSU6wKNHbfWX3721SE7zS0tL63Cfbi2//Zvf/KY7DxOi1zMUpAOg97HsBBfNgqMnYFQVghtz0NfXWeWYQgghtFdZ18CHqee4dbS/RYsra1hwwzDcnOx5Z2eW1lGE6BXa7cFqb82QwsJCamtrLRZICC15VDR1T7uExlvleG7ug8i1CyBYLeD0iTRGjLnRKscVQgihrQ9Tz1FV38iixBFaR+kxT1dH7rk+lH/szuYPN0cS6u2mdSQhNNVugXXvvfdy3XXXoaqqaZuiKAwePJhXXnnFKuGEsCajwUBw/WlQYOhI6wwrAigZOJLgqgLOZ+0HKbCE6HVeeOEFtm3bxvnz55k6dSrPPfcc06dP1zqWsGF1DQZW/XCGqZG+jB7qqXUcs/jVlDD+9cNZVn6XzStzrDMKRIjeqt0CKzQ0lA8++MCaWYTQVOG5EwxVailjED6BoVY7rt73Oqj6FuOl4YlCiN7lueee47nnntM6huhD1u3Ppaxaz6JESy5nb11DPJyZNz6IT/fn8bufRDDEQ5b0Ef1Xu9dgvfbaa9bMIYTmik/9CECBc4RVjzvw0nBEjwt9Z/YcIYQQbWswGHn3u2zGhgxiUljfmtb8oanDaTQa+ef3Z7SOIoSm2i2wwsLaX018165dFgkjhJbqcw8BcNFrlFWPGxjVNBwxRJ+N0WCw6rGF6Eu+/fZb0/fV1dUaJhGifZsPFZBfUcsj00agKIrWccwq1NuN22ID+fg/56io0WsdRwjNdGsWQendEn2Ra3nTxC5OQdaZ4KKZ95AgSvDCTakj/8xxqx5biL7kzTffNH1/3333aZhEiLYZjSrvfJdFlL87SVF+WsexiIcTw7moN7B6zzmtowihmXavwXrvvfd48MEHeemll1psV1WV4uJiiwcTwtoCazMBGBI5werHLnSJwK92LyWn9hE8Qi4OFqI7rpyU6crvhegttmUUc7qkmjfujutzvVfNogM8mB7lx7/2nOHBqWG4OnVryVUhbFq7PVjh4U0XXm7fvp2YmBjT1+jRo3F2lgsXRd9SVpSLL+epVl0IDLP+Qnc13jEA6PMOWf3YQvQVRqORCxcucP78edP3FRUVpi8htKSqKit2ZhHi5crM6wK0jmNRi6aFc76mgTX7crWOIoQm2v1YISkpCYCJEycye/bsFvetXr3asqmEsLKCjL34ALlOw4m2t7f68Z2D4yAP3MpliKAQ3VVdXc2cOXNMvVdXvncpisL27du1iiYEe7J0pOdWsGT2aBzsu3WFhs0YF+rFxDAv3tuVzb3XhzDAwfrvq0JoqcN+26VLl7ba9vbbb3eq8a1bt/L666+jKApPP/20qWhrS3p6Ov/v//0/GhsbiYyM5I033ujUMYQwh4s5BwGoHGT93iuAIZGTIBWG1mWiGo0odn37zVcIS9ixY4fWEYRo14qdp/F1H8DcsUFaR7GKR6aNYMH7+/j8YD4/nxCidRwhrKpTA2PT0tI4evQoiqJw3XXXER/f8SQAer2eZcuWsW7dOvR6Pffffz+JiYnYtXHiaDQaeeqpp1iyZAnjx4+nvLy86z+JED3gVHoUACVwjCbHDwiNpBJXvLlAWVGuVdfhEqKveP7553n++ee1jiFEK+m5FfxwWkfKrVE4O/aP3pypET7EBHqw8rts5o0Lxt6ub15zJkRbOvyY/OWXX2b58uVUVVVRWVnJsmXLeOWVVzps+PDhw0RERODj40NgYCABAQGcPHmyzX2PHj3K4MGDGT9+PABeXn1rXQjR+/ldPAWAd/h4TY6v2NmR69R03WP+ib2aZBDC1qWny2LdondasfM0Hs4O3HN9//nwTFEUFiWO4EzZRf73aKHWcYSwqg57sFJTU9myZYvp9qJFi5g1a1aHDZeWluLr68uaNWvw9PTEx8eHkpISoqNbD8EqLCzE3d2dX/3qV+h0Ou68807uueeeLv4oQnRPdeV5gtUC9Ko9wSPHapajatAoKDlCTc4B4C7Ncghhq3Q6HatWrWr3/l/84hdWTCNEk8ziKr46VsxjSSMYOKB/zah3y2h/hvu4seLbLGZeF9BnZ04U4modvtLj4uLYs2cPkydPBmDv3r3ExsZ2+gDz588HYNu2be3uU19fz4EDB9iyZQseHh7MnTuXqVOnEhwc3GrfjIyMTh9bK3V1dZLTjCyds/DkPpKAc3bBNGb3bPX5nmStcm36ZNO+8JDFfy/yuzcvW8kJtpW1q4xGIxcvXtQ6hhAtvPNdFi6O9jxwY5jWUazO3k5h4U3hPLXhMN+dKiVxZN9c+0uIq7VbYMXHx6MoCqqqsn79euwvzaxmMBhwcXFhyZIl12zY19eX0tJS0+2ysjL8/Np+Yfn4+DBixAgCAwMBiImJITs7u80Cq60esN4mIyNDcpqRpXNWpn8OwHnPUUzs4XF6ktXZ+BM4+2eG6rMZauHfi/zuzctWcoLtZE1LS+vyY3x8fHj00UctkEaI7sk7X8PmQwXcd0MoXm5OWsfRxB3xQ3ntm1Os2JklBZboN9otsA4ePNijhmNjY8nMzESn06HX6ykqKmLkyJEALF++HIA//OEPAFx33XUUFBRQUVGBq6srp06dIiiof8yyI7SnFB0GwDhE2wV+gyLiqFcdGUoxlRU6PAZ5a5pHCFvT/B4jRG/x3q5sFAUeTBiudRTNODnY8euE4fzPF8fZf7ac8cPkOnvR93VqMLBOp6OkpASj0WjaFhMTc83HODk58cQTT5iGCKakpJhmELyyZwvA3d2dZ599lgULFtDY2Mhtt91mWuhYCEvzqmqafMVz+DhNczg6DSDTIZQIw2nyMvYx6oZbNc0jhK1pa1kRIbRSWlXP2h9zmR0/lMBBLlrH0dT8icG8tSOTFTuzeP8BKbBE39dhgfXxxx/zwQcfUFpaSlhYGCdPniQmJoZPPvmkw8aTk5NJTk5utf3VV19tte3WW2/l1lvlhFJYl76+jpDGs6BAcPREreNw3iMKzp+m8kwaSIElhBA2a9UPZ9AbjDx0k3xg7OrkwC9uDOOv205xvKCSUYEeWkcSwqI6nKZ948aNfPnll4SEhLBhwwY2btzIkCFDrJFNCIvLPXkAJ8VAnhLAQI/BWsdB9W+aQMa++IjGSYQQQnRXZV0DH6ae49bR/oT7DtQ6Tq+w4IZhuDnZ8853WVpHEcLiOiywGhsbcXBwQFEU9Ho9ERERZGdnWyObEBany9oPQIlbpMZJmjQPU/SuOqFxEiGEEN310X/OUVXfyKLEEVpH6TU8XR259/pQvjxcwNkyme1T9G0dFlj+/v4UFxeTlJTEggULWLRokUxAIfoMY0HTBBf1vqM1TtIkJHoCRlUh2JBLfV2N1nGEEEJ0UV2Dgfe/P8PUSF9GD/XUOk6v8qspYTjY2/HuLvmgXvRtHV6DtXLlSgAWL17MpEmTqK6uJiEhweLBhLAGj4qm9YDcQrRbYPhKrgM9ybEPJMSYT+aJNCLi5LUmhBC2ZN3+XMqq9SxKlGuvrubn4cy8cUF8uj+P3/0kgiEezlpHEsIiOuzBgqb1SFavXs2JEycYPHgwjo6Ols4lhMUZDQZC9E1jwQOjJ2mc5rJSt6apps9ndX0dICFEk9LSUjIyMjh27JjpSwhLazAYefe7bMaGDGJSmMyW15aHpg6n0WjkH7ulF0v0XR32YL388sscPXqUyZMnA7Bs2TJGjx5NSkqKxcMJYUkFZzIIUmopZTC+/q0XtdZKg+9oqNqBWpiudRQhbNKf/vQndu/e3WI4u6IofPDBBxqmEv3BlvQC8itqeeH2GBRF0TpOrxTq7cbPxgTy8d4cHpk2gkGu/XMBZtG3dVhgpaamsmXLFtPtRYsWMWvWLIuGEsIaik/9SBBQ4DwCX63DXMFt2FjIBs8LMtGFEN2xd+9etm3bhoNDp5Z6FMIsjEaVFTuziPJ3JynKT+s4vdrDieFsOlTA6j3n+O1PIrSOI4TZdThEMC4ujj179phu7927l9jYWIuGEsIa9PmHAKjxvvai2dYWFH09ACH6LAyNjRqnEcL2JCQkyJBAYXXbMoo5XVLNw4nh2NlJ79W1RPl7MD3Kj1V7znCxXt7nRN/T7sd78fHxKIqCqqqsX78ee3t7AAwGAy4uLixZssRqIYWwBFdd0wnYgKA4jZO0NNg3gGK8GaLoyMk+Skhk78onRG+3YcMGPvroIxwdHXF0dERVVRRF4cCBA1pHE32Uqjb1XoV4uTLzugCt49iERdNGMPedPazZl8OvE4ZrHUcIs2q3wDp48KA1cwhhdUPrMgEYMnKixklaK3SJYEitjtLM/VJgCdFF8v4lrC01S0d6bgUv3TEaB/tOzR/W740LHcykMC/+sfsM990QygAHe60jCWE2nfpfoLy8nNTUVFJTUykvL7d0JiEsrqwoBx8qqFJdCAiN0jpOK3WXhi3q82SiCyG6Y+/evXz66acA6HQ6cnNzNU4k+rK3d57G130A88bJOqFdsWjaCIoq69h4IF/rKEKYVYcF1meffcbcuXNZu3Yta9asYd68eWzcuNEa2YSwmPyMvQDkOoVjZ9/7PjVzCo4HwO28XEciRFctXbqUf//737z33nsA1NfX8+STT2qcSvRV6bkV/HBax6+nhOHs2PveT3qzqRE+xAR68O6ubAxGVes4QphNh1MsrVq1ik2bNuHh4QFAZWUl99xzD7Nnz7Z4OCEspfZc0xCiykHRGidpm//IiZAKQXWZqEYjip0MORGis1JTU/n888+54447AAgMDKSmpkbjVKKvWrHzNB7ODtxzfajWUWyOoig8Mm0Eiz4+wP8eLeS22ECtIwlhFp06a3NycmrzeyFslVPZUQDsAsdonKRtASERVOKGF5WUFp7TOo4QNsXR0ZH6+nrTOkTFxcWmiZqEMKdzFXq+OlbMgsnDGDhAlgXojhkx/gz3cWPFt1moqvRiib6hw/8N7rzzTm6//XbGjx+PqqocOHCA++67zxrZhLAYv4unAPAeMUHjJG1T7OzIdQonRn+YghN78RsapnUkIWzGokWLuPfeeyksLOTJJ58kLS2N5557rtvtbd26lddffx1FUXj66adJSkoyY1phy9YfrcDF0Z5f3Cj/R3eXvZ3CwpvCeWrDYXaeKsVf60BCmEGHBdb999/P9OnTycjIAODRRx9l6NChFg8mhKVUXSgnSC1ErzoQMjJe6zjtqho8CooPU5tzELhb6zhC2Ixp06YxZswYDh1qWusuJSUFLy+vbrWl1+tZtmwZ69atQ6/Xc//995OYmIidDNvt9/LO17Azu5r7Jw/Dy01G9/TEHfFDee2bU7zzbRYv3DRI6zjCRqiqilEFg1HFqKqoKhhV9dJX0+Lfzd+b9lVVjMY29m3+3kiLtgyqanqs0aji4tS50RAdFlivvPIKixcv5ic/+UmPnwgheoPcjH2MAnIcQhnhNEDrOO2yDxwDxWsZUCYTXQjRVZmZmZSXlzNv3jzTLILBwcFdbufw4cNERETg4+MDQEBAACdPniQ6uuX1mxOXfGOW3JZmaGzEyakAO0VBUcBOUbC79O/l21d8b9d83+X97BSuun15f6UT+1w+3hX327Xcv7z8PINOHjGdGF0+GQK1eRu0OHlq3sf0L5dPqtQrTqKAq07GgCtOsJrabadNFVSaHnOhtgFFgQdlDacec3Kw48GE4bz4xXEWlFbi5FRo+ptRaPqboPnvBkx/S3D570a54n6at8EV7Vz6V2lrm3Jp38vtQfPfbNN+dnZN/zbnqKq8gMehOi7FuJRLMX3f/M2lRC32a77d6j7l8h4t223+Xrnisc2Pabmo9dXtlpeXM+j0MdQrCpHLr4nLr4srXw/G5qLC2PI1Zrj6scarH9v69dbqWMa2j6vXN2DnkH/tosnY8jha2XBnx/2sHRZYe/bsISUlxSyBhOgNKs+kAVDuPlLjJNfmEzEBDoJ/zSmtowhhU5YuXUpBQQEnTpxg3rx5plkE165d2+W2SktL8fX1Zc2aNXh6euLj40NJSUmrAmusv230YDQa7LGzs286iYFLJy8tCxZVNTZt4+pCo+mrsUURQqu24HIh1LT9isKIK0+qLhcrqmn/ywWP3blq7JpPaMF0cqzQfAJ8+YS4+SRUaWfb5ZNmTCfjSosT6JaPcTTtq1xxXEwn43ZAoKsD0ZHOXCg8y4VCy//ueqKurs40Eqm3GutpZFa0BxdqG7C3szf9TTX/bcLlwpkrTrCb/1ab7wdQjZe3NzRvu7Qvl7arV/wd03wsVNPfqelfLr8GrtxuNBpRyupNbV99+Vjb29QrjnXFjlw+Vuttlx9z1d2t21ev2P+KbfZKlelv3fRhB1cXmy0LzBavJdP+zR+CXHrsla+hS68f+6uKWNPr7dLrptUHOZfaNRrscHS0b1EUm/JCiyL66uMrCti383OYCmTT469+Dq481tX7Xj52c5sujgpN/7NdW4cFVlhYGFlZWYSHh3fYmBC2wK64aYIL1T9W4yTXFhwxhjrVkUCKuXC+DM/BPlpHEsImWGIWwfnz5wOwbdu2Nu9f+aupPWrfWjIyMloVh72R5DQvW8n5xnW2k1Vympet5ARIS0vrcJ8OC6zq6mrmzZtHTEwMAwcONG1fuXJlz9IJoRHvqhMAeIaN0zjJtTk4OpHtGEZk4ynyju/F88aZWkcSwiaYcxZBX19fSktLTbfLysrw8/MzS04hhBB9U4cF1sKFC62RQwir0NfXEdx4DiMKwaMmah2nQxUeI6H8FFXnDoAUWEJ0ysMPP2y2WQRjY2PJzMxEp9Oh1+spKipi5MjePbxYCCGEtjossCZO7P0noUJ0Vs6JNEYoBnKVQILde/9MRap/LJRvwb74iNZRhLAZSUlJxMXFmWUWQScnJ5544gnTEMGUlBSZQVAIIcQ1tVtg6fV61qxZQ05ODpGRkcybN08WahQ273zWfgBK3CLp+nxi1uc5fBwcB5+qk1pHEcJm3HzzzYSHhxMbG0tsbCyOjo49ai85OZnk5GQzpRNCCNHXtfsxXEpKCunp6YwYMYJvv/2WP//5z9bMJYRFGAsPA6D3Ha1xks4JjZ6IQVUINuRQV3tR6zhC2ISvvvqKJ598kuDgYL7//nvuvvtuZsyYoXUsIYQQ/US7PVgnT57kiy++AGDevHncddddVgslhKV4VDRNU+sWOlbjJJ3j4ubOOfsgQo25nDmRRkS8bcxUJoSWFEXBzc2Nw4cPU1NTwy233MINN9ygdSwhhBD9RLs9WFcOqejp8AohegOjwUCIPguAodGTNE7TeaVukcDl4Y1CiI4pioKdnR2qqtLY2EhDQ4PWkYQQQvQT7fZgnThxgrFjmz7lV1WV+vp6xo4di6qqKIrCgQMHrBZSCHPIP3OcYKWOErzwGxKkdZxOa/QbDVXbUYtkogshOsNoNHL+/HkiIyM5duwY27dv59tvv2Xz5s1aRxNCCNEPtFtg9fYVv4XoqpJT+wgGCl0isKVVbNxCx0EWeFbIa1KIzpgxYwbR0dHExsZy88038/jjj+Pm5qZ1LCGEEP1Eh9O0C9FX6POapmyu8RqlcZKuCR41CXZASEM2hsZG7B3kZSvEtXz88cetFgPW6XR4e3trlEgIIUR/Iot5iH7DrbypB2hAcJzGSbpmkI8/RfjgqtSTl3VU6zhC9HoPPfRQq22PPfaYBkmEEEL0R+1+FP7WW28B4Obmxi9+8QurBRLCUgLrMgEYEmk7E1w0K3SNxL+mjNLMfYSOtK0CUQhrqa+vp7a2FoPBwIULF1BVFYCKigoqKio0TieEEKK/aLfAGjp0KAADBgywWhghLKWs4Bw+VFCJK4HDRmodp8vqvEdBzR4a8tO1jiJEr7V27VpWr15NaWkpc+bMMRVY7u7uPPDAA9qGE0II0W+0W2DNnj3bmjmEsKj8E3vxAXKdwomxs72Rsc7B8ZALA8uPax1FiF5rwYIFLFiwgDvuuIPPP/9c6zhCCCH6Kds70xSiG2pympYVqBpkWxNcNPMfOQGAoPrTqEajxmmE6N2efvpprSMIIYTox6TAEv3CgLJjANgHxmqcpHv8gyO4gBuDqaSk4IzWcYTo1W644Qb27t3Lp59+CkBZWRm5ubkapxJCCNFfSIEl+gW/i6cA8B4xQeMk3aPY2ZE7IAKAwhP7NE4jRO+2dOlS/v3vf/Pee+8BoNfrefLJJzVOJYQQor+waIG1detWbr75ZmbMmMGOHTs63L+6upopU6bwz3/+05KxRD9TWaEjSC2iXnUkONJ2Z+CrHhQNQG3OQY2TCNG7paam8sYbb+Di4gJAYGAgNTU1GqcSQgjRX1iswNLr9Sxbtox///vfrFq1ipdffhljB9eOrFy5ktGjR1sqkuin8jKaenxyHEJxdLLdWTEdho4BwFl3TOMkQvRujo6O1NfXoygKAMXFxdjb22ucSgghRH9hsQLr8OHDRERE4OPjQ2BgIAEBAZw8ebLd/bOzs9HpdMTExFgqkuinKs+kAXDeI0rjJD3jE9E0vHFIzSmNkwjRuy1atIh7772XwsJCnnzySebPn8/vfvc7rWMJIYToJ9qdpr2nSktL8fX1Zc2aNXh6euLj40NJSQnR0dFt7r98+XKeffZZPvvss2u2m5GRYYm4ZlVXVyc5zainOQ15TQXWBddQi/+8lnxODY1O1KmOBFJC2r49uLoP7nZb/eV3by22khNsK2t3TZs2jTFjxnDo0CEAUlJS8PLy0jiVEEKI/qLDAuvcuXOEhoa22LZjxw6SkpI6dYD58+cDsG3btnb3w+2gAwAAIABJREFU2bFjB8OGDTMtbnwt7RVovUlGRobkNKOe5sz6tGnWveAx04iy8M9r6ef01KYwIhtPMaBBR3T05G63019+99ZiKznBdrKmpaX16PFnzpwhNzcXRVEYPHiwFFhCCCGspsMC6/e//z2zZ8/mvvvuo6amhpdeeonS0tIOCyxfX19KS0tNt8vKyvDz82tz3/T0dL7++mu2b9/O+fPnsbOzw9fXl9tvv72LP44QLdXX1RDSmIMRheBo25xB8ErnPaKg/BTVZw/AjT/TOo4QvdLLL7/M0aNHmTy56UOIZcuWMXr0aFJSUjROJoQQoj/osMBas2YNb775JgsWLKCyspJ7772XuXPndthwbGwsmZmZ6HQ69Ho9RUVFjBw5EmgaDgjwhz/8AWgq4n7/+98D8Le//Q1XV1cproRZ5J48wAjFQI7dUELcB2kdp+f8Y6F8M/YlR7VOIkSvlZqaypYtW0y3Fy1axKxZszRMJIQQoj/p1DVYDQ0NKIqCqqo0NjZ2qmEnJyeeeOIJ0xDBlJQU7Oya5tS4smdLCEsqP70fgFK3kYRonMUcBg0fB8fBp6r9CWOE6O/i4uLYs2ePqQdr7969xMba5iLjQgghbE+HBdbPf/5z7rzzTp599llqamp49dVX+dWvftWptaqSk5NJTk5utf3VV19t9zGLFy/usF0hOkstTAegwbdvTP8fEj0BwxaFYEMudTXVOLsO1DqSEL1GfHy86cPA9evX4+DQ9BbX2NiIi4sLS5Ys0TihEEKI/qDDAuvNN98kJKTps39XV1defPFFdu3aZfFgQpiDx4UTALiFxmucxDxc3Nw5ax/EMGMu2SfSiBx7k9aRhOg1Dh6URbiFEEJor8MCKyQkBJ1OR0lJiWmhYG9vb4sHE6KnjAYDIfpsUGBo9CSt45hN2cCRDKvM5XzWfpACSwghhBCiV+mwwPr444/54IMPKC0tJSwsjJMnTxITE8Mnn3xijXxCdFt+9lGClTpK8MLPr+MlAGxFo99oqPwGig5rHUUIIYQQQlzFrqMdNm7cyJdffklISAgbNmxg48b/3969B0dV3/8ff25uBEgIibnfAEOAGEHECCqKXBQdvABCLfyKgNWqUy+DiDq0VobqDFJ11M7UoUqnXmpVRC4iVGXAKVj5KgZNAANioiQhIWxCLiwk2Wxyfn+ERAIJIbCbz2729ZjJZPfs2ZNXwi7vfe/57Oezlri4uO7IJnJBjvywE4CS3kMMJ3GvsAGjAOh/cvijiIiIiHiPThssl8tFUFAQNpsNp9NJeno6BQUF3ZFN5II4i5snuKi7KNNwEvdKueSq5u8NP9F4jrN6ioiIiEj36HSIYHx8PGVlZUycOJF58+YRGRlJcnJyd2QTuSB9K/cC0CvlMsNJ3CviojgOE0O8zc7BH3MZMGyU6UgiIiIiclKnDdaKFSuA5unTx4wZg8Ph4LrrrvN4MJELYTU1kVx3AIC4IT1ngosWpX3SiT9hx35gpxosEQ9avnw569evJyoqio8//th0HBER8QGdDhGsrKzk888/56OPPqKkpISamho2btzYHdlEzlv54UKiqKGGviQM6FmfwYJfhj26DuUYTiLiG853gfsbb7yRv//9725OIyIiPVmnDdasWbP48ssvOXjwIMXFxa1fIt6sZN//AVAUkoYtoNOHuc8JTRkJQNjJYZAicnb33Xffed1v1KhRREZGujmNiIj0ZJ0OERw7dixJSUlERES0brPZbB4NJXKhThxsXnD0WOQlhpN4RsKwMfAlJNXnYzU19cgmUqSr9u5t/w2H0tJSamtrPfqz8/LyPHp8d6mrq/OJrMrpXr6SE3wnq3K6l6/kPFedNlhffPEF48ePx+FwdEceEbfoVd78QiswsWdNcNEiLjmNKsKI5BiHDxUQnzLYdCQR4+bMmcPw4cOxLKt1m81mIzIykmXLlp31vm+88QarV69us23SpEk8+uij5/SzMzIyuh7YgLy8PJ/Iqpzu5Ss5wXeyKqd7+UpOgOzs7E736bTBiouLIzExkYiICGw2G5Zl6QyWeL24Ez8AED34CsNJPMMWEEBxr8H0r/+Ow/u+VoMlAgwYMIC33nrrvO47f/585s+f795AIiLilzptsFpmDtQZLPEVNVUVJFll1FvBJKePNB3HYxyRmXD4O2qLvgX+n+k4Isa99NJLpiOIiIh03mD9+te/JiYmps22iooKjwUSuVBF339FJlAYPJD0kF6m43hMUOIIOPwOoeV7TEcR8QqDBg1qvVxRUcGRI0doampq3ZaZ2fVFx5cuXcrmzZuprKxk3LhxLFmyhEmTJrklr4iI9EydNlj33Xcfa9eubbPtkUce4Z133vFYKJELcezn5rGxlf2GGU7iWTHpV8IuiD9xwHQUEa/yzjvv8NZbb2G32xk0aBD79+8nMzOT999/v8vHWrJkCUuWLPFAShER6ak6nHqsvr6eqqoqGhsbqa6upqqqiqqqKn7++Weqqqq6M6NIlwSW7QbAih9hOIlnJadfRq0VQgJ2qivKTMcR8Rpr165l48aNpKam8uGHH7J27Vri4uJMxxIRET/R4Rms9957jzfffBO73c4dd9zROitTeHi4PggsXi362H4AIi7umRNctAgMCqIweBBDXfspyvuKiGtvNx1JxCu4XC6CgoKw2Ww4nU7S09MpKCgwHUtERPxEhw3WvHnzmDdvHtOmTWPdunXdmUnkvNXVHie5sYgmbKQOyzIdx+OqIjKgYj+On3eBGiwRAOLj4ykrK2PixInMmzePyMhIkpOTTccSERE/0elnsJ588snuyCHiFkX7d5Fua+RgQDIDwiI6v4Ovix8OFesIOrLbdBIRr7FixQoAHn744daZcK+77jrDqURExF90+Bms/Px8AGJjY7stjMiFqsz/BgB736GGk3SPyLTms3TRjv2Gk4h4j4MHD3L06FEARo8ezciRIykpKTGcSkRE/EWHDdaiRYvafBfxBVZpLgCu2EsNJ+keqcOycFkBpDQWU3dCa9WJACxcuJBevX5ZoqF379489thjBhOJiIg/6XCIoNPpZMOGDdTU1PDZZ5+dcfvkyZM9GkzkfERU5QHQd0DPnuCiRWifMH4OTGZgUyH5+75hyKjxpiOJGOdyuejbt2/r9d69e9PQ0GAwkYiI+JMOG6ylS5eyYcMGHA4Hn3/++Rm3q8ESb9PocpHaUAA2SM4YbTpOtykPG8rAmsLm4ZFqsERITEzk/fffZ8aMGQB8+OGHJCYmGk4lIiL+osMGKysri6ysLHJycli2bFl3ZhI5L4cK9pBqq6eMi4iLSTAdp9u44oZDzWY4nGs6iohXeOaZZ3jmmWd4+eWXsdlsjBkzhmeeecZ0LBER8ROdziL49ttvd0cOkQt25MBOUoHSPkPwpyVFwwZcDgcgsjrPdBQRrxAdHc0rr7xiOoaIiPipDie5aBEeHs7Ro0fZsWMHO3bsaJ2ZScTbNBR/B0DtRZmGk3SvlIwxAKQ2/ISrwWk4jYh32rZtm+kIIiLiJzptsNasWcOMGTN47733ePfdd5k5cyZr167tjmwiXRJ29HsAQlMuN5yke0VcFEcpMYTaGjj0o9bDEmnPSy+9ZDqCiIj4iU6HCP7zn/9k/fr19OvXD4Camhp+85vfMH36dI+HEzlXVlMTSfU/AhA/9ErDabrf4T5DSDhhx35gJwMy/GMGRZHTvf766/zud7/j2WefbbPdsizKysoMpRIREX/T6RksgJCQkHYvi3gLe+lBoqihmr7Ep6SbjtPt6qKb1/1yHfrOcBIRc9LS0gDYsmULmZmZrV+XXnopoaGhhtOJiIi/6PQM1q9+9SumTp3KFVdcgWVZ7Nq1i7vuuqs7somcs5J9XxELFIcMJjPgnN436FF6p4yEQgir0kQX4r8mTpwIwOjRo88YZfHmm2+aiCQiIn6o0wZr7ty5TJo0iby85hduDz30EElJSR4PJtIVtYXfAnAs8hLDScyIHzYa/gcp9Qewmpqw+WGTKdJi+fLlZ2z729/+ZiCJiIj4o3N6FZaUlMRVV11FaGgoJ06c8HQmkS4LLd8DQFDSZYaTmBGXdDGVhBPBccqK803HETFq2bJlOByONtv0xqCIiHSXDhusBQsWsG/fPgDsdjtTpkzhX//6FwsXLmTlypXdFlDkXMSd+AGA6HT/m+ACwBYQQHGvwQCU7vvKcBoRs7788kvCwsJMxxARET/VYYOVn5/PsGHDAFi9ejVXX301K1as4IMPPmDdunXdFlCkM9WV5SRaR6izgkkePMJ0HGOOnxweWVekiS7Evw0aNIj8fJ3JFRERMzr8DJZlWTQ2NhIYGMjWrVt54IEHAAgNDcVms3VbQJHOFH//FRFAYfAghgT77yyXQckj4fA7hFbsNR1FxCiHw8HMmTPJzMxscyZrxYoVBlOJiIi/6LDBuu2225gzZw5RUVHU1NRw3XXXAXDw4EFNdyte5djP2QBU9htmOIlZMYOz4BtIODlcUsRftbwhKCIiYkKHDdb999/PNddcQ0lJCddcc03r+leBgYE899xz53TwTZs28fLLL2Oz2XjyySdbp9A9XVlZGQsWLKCmpoaQkBAWLVrE2LFjz+PXEX8UeGR384V4/x0eCJA8eAQnrF7E28qpKj9M/+h405FEjBg9erTpCCIi4sfOOk378OHDGT58eJttycnJ53Rgp9PJCy+8wKpVq3A6ncydO5fx48cT0M700YGBgSxZsoRhw4Zx6NAhZs2axfbt27vwa4g/iz62H4D+F19hOIlZgUFBFAUPYqhrH8V5X9H/uqmmI4kY89VXX1FUVMTMmTMpLy+ntraWlJQU07FERMQPeGyxnNzcXNLT04mOjiYxMZGEhAT279/f7r7R0dGtE2okJSXR0NCA0+n0VDTpQepqj5PSWESjZSM1wz9nEDxVVUTz88hxcJfhJCLmLF++nH//+9+8/vrrQPMbfo8//rjhVCIi4i86XWj4fNntdmJiYnj33XeJiIggOjqaI0eOkJGRcdb7bd++nczMzNYhiadrWfDYm9XV1SmnG50t55GCHK63NfGzLYnawuJuTnYm03/Tmj4DoQKs4m/PmsN0znOlnO7nS1nP144dO1i3bh3Tpk0DIDExUWs4iohIt/FYg9Vi9uzZAGzevLnTfe12O8uXL+fVV1/tcJ/OGjRvkJeXp5xudLacx/b+B4Dy8AyyvOB3Mf03DaydCEUvk+gsYMBZcpjOea6U0/18JWt2dvZ53zc4OJj6+vrWGW/LysoIDAx0VzQREZGz8tgQwZiYGOx2e+v18vJyYmNjO9y/vr6eRx55hCeeeILU1FRPxZIexirNAcAVe6nhJN4hNSMLlxVAcmMxtcePmY4jYsTvf/975syZQ2lpKY8//jizZ89mwYIFpmOJiIif8NgZrBEjRnDgwAEqKipwOp0cPnyYoUOHAvDiiy8C8NhjjwHNa24tXryYW2+9lXHjxnkqkvRA/av3ARA2YJThJN4htHdffgpMYVDTQQrzdjI0q/2ZO0V6sgkTJnDZZZfx3XfNi24vXryYqKgow6lERMRfeKzBapluvWWI4OLFi1tnEDz1zBY0DwX59NNPyc/PZ9WqVQC89tprxMXFeSqe9ACNLhcpDT+BDZIzxpiO4zXKw4cyqPogVQXZoAZL/FBlZSU5OTk4HA6amprYtm0bQOtnss6VlhAREZHz4dHPYE2ZMoUpU6acsf30dbSysrLYu3evJ6NID1Scv4cBtnoOE0281nxq1Rg7HKo/g8O5pqOIGDFr1izGjRtHv379Wj+HdT60hIiIiJwPj09yIeIp9gNfMwAo7TMEtVe/CBt4ORyAyJp9pqOIGDF27FiSkpKIiIho3XY+jVZ0dDTR0dFA2yVEOprlVkREBNRgiQ9zFTd/vqLuokzDSbxLSsZVsBlSG37C1eAkKFgvBsW/fPHFF4wfPx6Hw+G2Y3a2hIiIiEgLNVjis/pWfg9AaMpIw0m8S0RUDCW2WBI5wk8Hchh0iRZgFv8SFxdHYmIiERER2Gw2LMvq9AzWG2+8werVq9tsmzRpEo8++ug5LSHiK2uL+co6aMrpXr6SE3wnq3K6l6/kPFdqsMQnWU1NJNf/CEDCME1wcbqyPkNIPH6Eih+/UYMlfmfMmDE4HI4uncGaP38+8+fPP2P7uS4h4gtri4HvrIOmnO7lKznBd7Iqp3v5Sk44t3Ua1WCJTzpS8hNxHKOKMOKS00zH8Tp10ZfC8S9wHcoxHUWk202YMMEtx9ESIiIicj7UYIlPKt33NXFAca/B9A/w2HrZPqt36uVwEMJPDqMU8SfPPfdc69DAxsZGCgoKSExMZM2aNV06jpYQERGR86EGS3xSbeG3ADj6+8bp5O6WMPRK2A4pzh+xmpqwqQkVP/L222+3uV5XV8fy5cu7fBwtISIiIudDr7rEJ4WW7wEgKEkTXLQnNnEQlfSjH8cpLTxgOo6IUU6nU42SiIh0G53BEp8Uf+IHAGLSNYFDe2wBART3Gkxk/S7KfthJ4sChpiOJdJvLL7+8zeyB/fr149577zUdS0RE/IQaLPE51RVlJGCn1gohOf0y03G8liPqEijdRV3Rt8Ac03FEus23335rOoKIiPgxNVjic4r2fU0EUBg8iKFBegh3JDh5JJT+i94VGhol/mHnzp1nvf3KK3XGW0REPE+vTsXnOH7eBUBVxDDDSbxbzOArYScknBxOKdLT/eMf/zhjm2VZ7Nq1C4fD0aMWsRQREe+lBkt8TlDZ7uYL8SPMBvFyyWmXcsLqRZytgkp7KZExCaYjiXjUihUrWi/n5+ezbt06duzYwYwZM5g2bZrBZCIi4k/UYInPiXbsByAyLctwEu8WGBREYfDFDHPlUZz3f0TGTDcdScSjqqqq2LhxI5988gmxsbFMnTqVhQsXYrPZTEcTERE/ogZLfErdCQfJjcW4CCB1mBqszlT3z4DyPI4f/BZQgyU927XXXkufPn0YP3484eHhbNu2jW3btrXe/tRTTxlMJyIi/kINlviUwn3ZDLE18XNAKgP7hJmO4/VsCSOgfA1BR/aYjiLicc8884zpCCIiImqwxLdU5n8DQHnYEAaajeITItOyYDfEHN9vOoqIx02frrO0IiJiXoDpACJdcjgXAFfscMNBfEPK0FG4rABSGg9xwlFtOo6IiIhIj6cGS3xK/+rmaZbDBo4ynMQ3hPbuS1FgKgE2i8K8s68RJCIiIiIXTg2W+IxGl4vUhp8ASMkYYziN7ygPHwpA9U+7DCcRERER6fnUYInPKD6QQ2+bk1JiiLgoznQcn9EY1zyc0nZyeKWIiIiIeI4aLPEZ9h+bJ7g43GeI4SS+JXzgFQBE1uwznERERESk51ODJT7DdSgHgLroTMNJfEtyxmgAUht+psFZbziNiIiISM+mBkt8RljlXgB6p1xuOIlviYiMpsQWRy9bA8UHvjMdR0RERKRHU4MlPsFqaiK5/kcA4oeNNpzG97QMqyw/8I3hJCIiIiI9mxos8Qllxfn0x0El4cQlXWw6js+pPzmssrFUE12IiIiIeJIaLPEJh/c3r+FU3GswtgA9bLuqz4DmYZXhld8bTiIiIiLSs+mVqviE2qJvATgeeYnhJL4pcdhVAKQ487GamgynEREREem51GCJTwgt3wNAUNJlhpP4puj4VI7Sj34cp/TgD6bjiIiIiPRYarDEJyScOABATPqVhpP4JltAAMWh6QCU/fCV4TQiIiIiPZcaLPF6J2qOEo+dE1YvkgePMB3HZx2PbJ7oor4ox3ASERERkZ5LDZZ4veriPACKggcRGBRkOI3vCkluHl4ZWrHXcBIRERGRnksNlni9Rvs+AKoihhlO4ttihzQPr0ys1WewRERERDxFDZZ4vbDqkw1BvIYHXoikiy/lhNWLWI7iqC43HUdERESkR1KDJV4vvi4fgMi0LMNJfFtAYCCFIWkA1BRpmKCIiIiIJ3i0wdq0aROTJ0/mpptuYuvWrW7bV/xH7fFjpDYdwmUFkJqhButCVZ8cZmnZ9xtOIiIiItIzeWzGAKfTyQsvvMCqVatwOp3MnTuX8ePHExBwZk/XlX3FvxTm7WSozeKngFQG9e5rOo7PsyVcBuVrCKs5YDqK+JCmxkYaGupxNThxOetpaHDiaqinsaEBV0M9Ta7m2xpdTpoanDS5Wi7XYzU20ORyYjU2YLV8b3RC63cXNDqxNbV8b8DW1EDgtY+Z/rVFRETOi8carNzcXNLT04mOjgYgISGB/fv3k5GRcUH7frf8Jk9FdgsbFi5XIzlBAWBZJ7cBWCe/wGY1X7advH7qNk7ua2u5wWrZ75RjWafe97TjYJ3yc9t+Bwub9cuxQ6wmfrIF/HKrzXZK2tYEzZdtHWxv/QknL9tOT9P+9tafY+vgeCe39204CkB5+FAGIRcqanAW7IZLarPJfe6GU26xOrjc8tjs4LbTrrd/n06O32a3trc1NTWSF2A7y/PhtMe41c7z4eTj/pefdfrzp+02m9XO8+b0R77V9nokFodPPq4tmh/Xv9zrl3u3bG+bvPl6k+20fU8+79pcP3m7deq+tl+Odepzp3V/W8AvP89mo6nByd6AJgIsF4GtXw0EWo0EWQ0E0kgwLgJxEWy5CKKRYFsjvYBedJ9s1GCJiIhvslnWGa+E3OI///kP//vf/8jMzCQiIoLNmzczbdo0rr/++vPeNzs72xNRRUTEC11xxRWmI5wT1SYREf/SWX3y+KJCs2fPBmDz5s0XvK+vFFsREfEfqk0iInIqj33IKSYmBrvd3nq9vLyc2NjYC95XRERERETEW3nsDNaIESM4cOAAFRUVOJ1ODh8+zNChQwF48cUXAXjsscc63VdERERERMRXeKzBCgkJYdGiRa3D/hYvXtw6K+CpZ6s621dERERERMRXeGySC3fatGkTL7/8MjabjSeffJKJEyeajtSu5cuXs379eqKiovj4449Nx+lQWVkZCxYsoKamprW5HTt2rOlYZ6isrOSee+7B5XJhs9l4+OGHueGGGzq/oyEOh4Obb76Zu+++m3vuucd0nA5lZGQwZMgQAK688kqeeuopw4nal5OTw1NPPYXL5WLIkCG88sorpiOdYfv27bzwwgut1/Pz8/nggw/anQHVtJUrV7Ju3TqampqYMmUKDz30kOlIHXrppZfYsmULwcHBPPjgg179vFd9ci/VJ8/whfqk2uReqk/u16XaZHm5+vp6a8KECZbdbrcOHTpkTZo0yWpsbDQdq13Z2dlWbm6udcstt5iOclZ2u93Ky8uzLMuyiouLrWuvvdZwovY5nU7L4XBYlmVZFRUV1tixY732396yLOv555+37r//fmvlypWmo5zVyJEjTUfoVGNjozV58mRr586dlmU1//t7u7KyMuvGG280HaNdpaWl1g033GA5nU6rvr7emjhxolVYWGg6Vrtyc3OtO+64w2poaLAqKiqscePGWceOHTMdq12qT+6n+uQZvlCfVJs8R/XpwnW1Nnn9OLxT18hKTExsXSPLG40aNYrIyEjTMToVHR3NsGHDAEhKSqKhoQGn02k41ZmCg4Pp27d5cWGHw4HT6cTlchlO1b6CggIqKirIzMw0HaVH2LNnD5GRkWRlZQEQFRVlOFHnNm3axE03ee86fY2NjTidTpxOJ8HBwYSHh5uO1K6ioiIyMjIICgoiKiqKuLg4du/ebTpWu1Sf3E/1yf1Un9zHF2sTqD65Q1drk9c3WHa7nZiYGN599102bdpEdHQ0R44cMR2rx9i+fTuZmZmEhISYjtIuh8PBbbfdxu23386SJUu8NueLL77otae0T1dfX8/06dOZNWsWO3fuNB2nXaWlpYSHh3PPPfcwbdo03nnnHdOROvXRRx9xyy23mI7Rrvj4eObOncuECRO4/vrr+e1vf0v//v1Nx2pXWloaOTk51NbWUlJSQn5+PuXl5aZjtUv1ybNUn9zDV+qTapPnqD5duK7WJo+vg+UuXVlPS86N3W5n+fLlvPrqq6ajdCgsLIwNGzaQn5/Pn/70JyZPnkxwcLDpWG1s3bqVgQMHkpSUZDrKOfnvf/9LTEwMubm5PPTQQ3z22WeEhoaajtVGfX09u3btYsOGDfTr148ZM2Ywbtw4UlJSTEdrV0FBAXV1da3vvHub6upqtm3bxpYtW2hoaGD27NmMHz/eK5fDGDp0KHfccQezZs0iLi6OMWPG0KtXL9Oxzkr1yf1Un9zDl+qTapNnqD65R1drk9c3WFojyzPq6+t55JFHeOKJJ0hNTTUdp1NpaWkEBQWxb98+hg8fbjpOGzk5OXz22Wds2bKFyspKAgICiImJ4fbbbzcdrV0xMTFA8/IIsbGxHDp0iLS0NMOp2oqOjmbw4MEkJiYCkJmZSUFBgdcWsY8//pgpU6aYjtGhHTt2kJCQ0Drs4pJLLiEvL89r/y+9++67ufvuuwG48847SUhIMJyofapPnqH65D6+VJ9UmzxD9cl9ulKbvH6I4KlrZJWWlmqNLDewLIvFixdz6623Mm7cONNxOlRWVkZlZSXQ/G5mfn4+cXFxhlOd6dFHH2Xz5s188sknzJkzh3vvvdcrixdAVVUVdXV1ABQXF1NWVuaVL16HDx9OSUkJVVVVOJ1OfvjhB5KTk03H6pC3F7Do6Gh2796N0+mkrq6O77//3qv/ni3P+6+//prq6mouvfRSw4nap/rkfqpP7uUr9Um1yXNUn9ynK7XJ689g+dIaWUuXLmXz5s1UVlYybtw4lixZwqRJk0zHOkN2djaffvop+fn5rFq1CoDXXnvN64pDSUkJTz/9NND8AchFixZ55TsavqSgoIDFixcTEhJCYGAgzz77LH369DEd6wzh4eH84Q9/YN68ebhcLm699VaveyezRU5ODn369OHiiy82HaVDWVlZXHvttdx+++0EBAQwc+ZMr/17QvP/84WFhQQFBfH8889js9lMR2o4LEYsAAACqElEQVSX6pP7qT75J9Umz1B9cq+u1CafWAdLRERERETEF3jnW20iIiIiIiI+SA2WiIiIiIiIm6jBEhERERERcRM1WCIiIiIiIm6iBktERERERMRN1GCJdIM1a9Zw1VVXMXXqVO6//36Kiopab9uyZQuvvfbaOR+ro/3feOMNamtr3ZJXRET8g+qTiPtpmnaRbrBmzRr27NnD008/zY4dO1i6dCkbN24kMDDQbT9j4sSJrF69mqioKLcdU0REejbVJxH30xkskW529dVXExkZye7du3niiScYP348f/7zn9vss3LlSm6++WYeeOABbrjhBoqLiwHa3f/LL79k6tSpHDlyhHnz5jF16lTKysq69XcSERHfp/ok4h5BpgOI+KPExESKi4v5y1/+0vruYYuSkhLef/991q9fT2lpKbfcckvrbe3tf80117B+/XomTpzIm2++qXcIRUTkvKk+iVw4ncES8TJ79+4lKyuLPn36kJaWRmJioulIIiIiqk8i50gNlogBJSUlJCcnm44hIiLShuqTyIVTgyXSzXbs2MHRo0cZPnx4u7dnZmaSnZ1NbW0t+fn5lJSUnNNx+/btS3V1tTujioiIH1F9EnEPfQZLpJts2rSJ7OxsYmNjef311yktLeXBBx+kurqauro6srOzWbhwIddffz133nkn06dPZ/DgwSQnJxMSEkJxcXGH+wPcddddPPjgg0RERPDXv/6VmJgYw7+xiIj4AtUnEffSNO0iXsjhcBAWFsbRo0eZMWMGW7duxWazmY4lIiJ+TvVJpHM6gyXihZYtW0Zubi4Af/zjH1W8RETEK6g+iXROZ7BERERERETcRJNciIiIiIiIuIkaLBERERERETdRgyUiIiIiIuImarBERERERETcRA2WiIiIiIiIm/x/EGOEhBFzbOwAAAAASUVORK5CYII=\n",
-            "text/plain": [
-              "<Figure size 864x288 with 2 Axes>"
-            ]
-          },
-          "metadata": {
-            "tags": []
-          }
-        }
-      ]
-    }
-  ]
-}
\ No newline at end of file
diff --git a/colab/mnist_training.ipynb b/colab/mnist_training.ipynb
new file mode 100644
index 0000000..da9012b
--- /dev/null
+++ b/colab/mnist_training.ipynb
@@ -0,0 +1,858 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "training_and_executing_an_mnist_model_with_iree.ipynb",
+      "provenance": [
+        {
+          "file_id": "https://github.com/google/iree/blob/main/colab/mnist_tensorflow.ipynb",
+          "timestamp": 1610576812089
+        }
+      ],
+      "collapsed_sections": [
+        "DSpbh8jA0Vue",
+        "6boR75_O0780"
+      ]
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "PZtRtMMUZHJS"
+      },
+      "source": [
+        "##### Copyright 2021 Google LLC.\n",
+        "\n",
+        "Licensed under the Apache License, Version 2.0 (the \"License\");"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "cellView": "form",
+        "id": "TouZL3JZZSQe",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653577084,
+          "user_tz": 480,
+          "elapsed": 459,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        }
+      },
+      "source": [
+        "#@title License header\n",
+        "# Copyright 2020 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#      https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ],
+      "execution_count": 1,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "O6c3qfq5Zv57"
+      },
+      "source": [
+        "# Training and Executing an MNIST Model with IREE"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5ZY4oApRz0Cc"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook covers installing IREE and using it to train a simple neural network on the MNIST dataset."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Bn2JUIHS0P_Q"
+      },
+      "source": [
+        "## 1. Install and Import IREE"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "ZpkMjTQxLzLq",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653579700,
+          "user_tz": 480,
+          "elapsed": 3069,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        }
+      },
+      "source": [
+        "%%capture\n",
+        "!python -m pip install iree-compiler-snapshot iree-runtime-snapshot iree-tools-tf-snapshot -f https://github.com/google/iree/releases"
+      ],
+      "execution_count": 2,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "D0bOS2B50bL3",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653581582,
+          "user_tz": 480,
+          "elapsed": 4948,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        }
+      },
+      "source": [
+        "from pyiree import rt as ireert\n",
+        "from pyiree.tf.support import module_utils\n",
+        "from pyiree.compiler2 import tf as tfc"
+      ],
+      "execution_count": 3,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "7YkXQ0AG0gRM",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653581584,
+          "user_tz": 480,
+          "elapsed": 4945,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        }
+      },
+      "source": [
+        "# (Temporary) workaround for absl flags...\n",
+        "# https://github.com/googlecolab/colabtools/issues/1323#issuecomment-756343620\n",
+        "import sys\n",
+        "from absl import app\n",
+        "sys.argv = sys.argv[:1]\n",
+        "try:\n",
+        "  app.run(lambda argv: None)\n",
+        "except:\n",
+        "  pass"
+      ],
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "DSpbh8jA0Vue"
+      },
+      "source": [
+        "## 2. Import TensorFlow and Other Dependencies"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "EPF7RGQDYK-M",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653581585,
+          "user_tz": 480,
+          "elapsed": 4942,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        },
+        "outputId": "d12ae9b8-4812-4cdc-ae5d-a3654fe91b9f"
+      },
+      "source": [
+        "from matplotlib import pyplot as plt\n",
+        "import numpy as np\n",
+        "import os\n",
+        "import tempfile\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "plt.style.use(\"seaborn-whitegrid\")\n",
+        "plt.rcParams[\"font.family\"] = \"monospace\"\n",
+        "plt.rcParams[\"figure.figsize\"] = [8, 4.5]\n",
+        "plt.rcParams[\"figure.dpi\"] = 150\n",
+        "\n",
+        "# Print version information for future notebook users to reference.\n",
+        "print(\"TensorFlow version: \", tf.__version__)\n",
+        "print(\"Numpy version: \", np.__version__)"
+      ],
+      "execution_count": 5,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "TensorFlow version:  2.4.0\n",
+            "Numpy version:  1.19.5\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6boR75_O0780"
+      },
+      "source": [
+        "## 3. Load the MNIST Dataset"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "sVVzmkKW07gi",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653582060,
+          "user_tz": 480,
+          "elapsed": 5413,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        }
+      },
+      "source": [
+        "# Keras datasets don't provide metadata.\n",
+        "NUM_CLASSES = 10\n",
+        "NUM_ROWS, NUM_COLS = 28, 28\n",
+        "\n",
+        "(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()\n",
+        "\n",
+        "# Reshape into grayscale images:\n",
+        "x_train = np.reshape(x_train, (-1, NUM_ROWS, NUM_COLS, 1))\n",
+        "x_test = np.reshape(x_test, (-1, NUM_ROWS, NUM_COLS, 1))\n",
+        "\n",
+        "# Rescale uint8 pixel values into float32 values between 0 and 1:\n",
+        "x_train = x_train.astype(np.float32) / 255\n",
+        "x_test = x_test.astype(np.float32) / 255\n",
+        "\n",
+        "# IREE doesn't currently support int8 tensors, so we cast them to int32:\n",
+        "y_train = y_train.astype(np.int32)\n",
+        "y_test = y_test.astype(np.int32)"
+      ],
+      "execution_count": 6,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "k51ZHOdl1DVM",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 0
+        },
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653582229,
+          "user_tz": 480,
+          "elapsed": 5579,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        },
+        "outputId": "fd163ba4-3db7-456b-c5ff-99691f88fd17"
+      },
+      "source": [
+        "print(\"Sample image from the dataset:\")\n",
+        "sample_index = np.random.randint(x_train.shape[0])\n",
+        "plt.figure(figsize=(5, 5))\n",
+        "plt.imshow(x_train[sample_index].reshape(NUM_ROWS, NUM_COLS), cmap=\"gray\")\n",
+        "plt.title(f\"Sample #{sample_index}, label: {y_train[sample_index]}\")\n",
+        "plt.axis(\"off\")\n",
+        "plt.tight_layout()"
+      ],
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Sample image from the dataset:\n"
+          ],
+          "name": "stdout"
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 750x750 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "TtdoBkSx2LU-"
+      },
+      "source": [
+        "## 4. Create a Simple DNN"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "DvQ8Hwkb4-eQ"
+      },
+      "source": [
+        "MLIR-HLO (the MLIR dialect we use to convert TensorFlow models into assembly that IREE can compile) does not currently support training with a dynamic number of examples, so we compile the model with a fixed batch size (by specifying the batch size in the `tf.TensorSpec`s)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "PhgIfpyo2ik1",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653582230,
+          "user_tz": 480,
+          "elapsed": 5576,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        }
+      },
+      "source": [
+        "BATCH_SIZE = 32"
+      ],
+      "execution_count": 8,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "CSIHhP-M2OVf",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653582231,
+          "user_tz": 480,
+          "elapsed": 5573,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        }
+      },
+      "source": [
+        "class TrainableDNN(tf.Module):\n",
+        "\n",
+        "  def __init__(self):\n",
+        "    super().__init__()\n",
+        "\n",
+        "    # Create a Keras model to train.\n",
+        "    inputs = tf.keras.layers.Input((NUM_COLS, NUM_ROWS, 1))\n",
+        "    x = tf.keras.layers.Flatten()(inputs)\n",
+        "    x = tf.keras.layers.Dense(128)(x)\n",
+        "    x = tf.keras.layers.Activation(\"relu\")(x)\n",
+        "    x = tf.keras.layers.Dense(10)(x)\n",
+        "    outputs = tf.keras.layers.Softmax()(x)\n",
+        "    self.model = tf.keras.Model(inputs, outputs)\n",
+        "\n",
+        "    # Create a loss function and optimizer to use during training.\n",
+        "    self.loss = tf.keras.losses.SparseCategoricalCrossentropy()\n",
+        "    self.optimizer = tf.keras.optimizers.SGD(learning_rate=1e-2)\n",
+        "  \n",
+        "  @tf.function(input_signature=[\n",
+        "      tf.TensorSpec([BATCH_SIZE, NUM_ROWS, NUM_COLS, 1])  # inputs\n",
+        "  ])\n",
+        "  def predict(self, inputs):\n",
+        "    return self.model(inputs, training=False)\n",
+        "\n",
+        "  # We compile the entire training step by making it a method on the model.\n",
+        "  @tf.function(input_signature=[\n",
+        "      tf.TensorSpec([BATCH_SIZE, NUM_ROWS, NUM_COLS, 1]),  # inputs\n",
+        "      tf.TensorSpec([BATCH_SIZE], tf.int32)  # labels\n",
+        "  ])\n",
+        "  def learn(self, inputs, labels):\n",
+        "    # Capture the gradients from forward prop...\n",
+        "    with tf.GradientTape() as tape:\n",
+        "      probs = self.model(inputs, training=True)\n",
+        "      loss = self.loss(labels, probs)\n",
+        "\n",
+        "    # ...and use them to update the model's weights.\n",
+        "    variables = self.model.trainable_variables\n",
+        "    gradients = tape.gradient(loss, variables)\n",
+        "    self.optimizer.apply_gradients(zip(gradients, variables))\n",
+        "    return loss"
+      ],
+      "execution_count": 9,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "wgw3qscBAj5r"
+      },
+      "source": [
+        "## 5. Compile the Model with IREE"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "YU1MPQpLARFg"
+      },
+      "source": [
+        "tf.keras adds a large number of methods to TrainableDNN, and most of them\n",
+        "cannot be compiled with IREE. To get around this we tell IREE exactly which\n",
+        "methods we would like it to compile."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "077f7oM5_sXo",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653582368,
+          "user_tz": 480,
+          "elapsed": 5707,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        }
+      },
+      "source": [
+        "exported_names = [\"predict\", \"learn\"]"
+      ],
+      "execution_count": 10,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2mAHqesFATKr"
+      },
+      "source": [
+        "Choose one of IREE's three backends to compile to. (*Note: Using Vulkan requires installing additional drivers.*)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "mJyGShXIAOGr",
+        "cellView": "form",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653582368,
+          "user_tz": 480,
+          "elapsed": 5704,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        }
+      },
+      "source": [
+        "backend_choice = \"llvmaot (CPU)\" #@param [ \"vmla (CPU)\", \"llvmaot (CPU)\", \"vulkan (GPU/SwiftShader – requires additional drivers) \" ]\n",
+        "backend_choice = f\"iree_{backend_choice.split(' ')[0]}\""
+      ],
+      "execution_count": 11,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "9x8Vm_dQ8tib",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653584427,
+          "user_tz": 480,
+          "elapsed": 7759,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        },
+        "outputId": "425f7a7c-f2fb-4f09-a933-81fddb628f0a"
+      },
+      "source": [
+        "# Compile the TrainableDNN module\n",
+        "compiled_model = module_utils.IreeCompiledModule.create_from_class(\n",
+        "    TrainableDNN, \n",
+        "    module_utils.BackendInfo(backend_choice), \n",
+        "    exported_names=exported_names)"
+      ],
+      "execution_count": 12,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "INFO:tensorflow:Assets written to: /tmp/tmprccz86q3.sm/assets\n"
+          ],
+          "name": "stdout"
+        },
+        {
+          "output_type": "stream",
+          "text": [
+            "I0114 19:46:22.975932 140420144105344 builder_impl.py:775] Assets written to: /tmp/tmprccz86q3.sm/assets\n",
+            "2021-01-14 19:46:23.145960: I external/org_tensorflow/tensorflow/cc/saved_model/bundle_v2.cc:32] Reading SavedModel from: /tmp/tmprccz86q3.sm\n",
+            "2021-01-14 19:46:23.147528: I external/org_tensorflow/tensorflow/cc/saved_model/bundle_v2.cc:55] Reading SavedModel debug info (if present) from: /tmp/tmprccz86q3.sm\n",
+            "2021-01-14 19:46:23.175245: W external/org_tensorflow/tensorflow/compiler/mlir/tensorflow/translate/import_model.cc:1795] Unmodelled op type `StaticRegexFullMatch` is not stateful but will be treated as such conservatively\n",
+            "2021-01-14 19:46:23.175427: W external/org_tensorflow/tensorflow/compiler/mlir/tensorflow/translate/import_model.cc:1795] Unmodelled op type `SaveV2` is stateful but effects not modelled\n",
+            "Created IREE driver dylib: <pyiree.rt.binding.HalDriver object at 0x7fb5afc56d18>\n",
+            "SystemContext driver=<pyiree.rt.binding.HalDriver object at 0x7fb5afc56d18>\n"
+          ],
+          "name": "stderr"
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "DtOS_rd_BP5V"
+      },
+      "source": [
+        "## 6. Train the Compiled Model on MNIST"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2MVsxIy5BdqF"
+      },
+      "source": [
+        "This compiled model is portable, demonstrating that IREE can be used for training on a mobile device. On mobile, IREE has a ~1000 fold binary size advantage over the current TensorFlow solution (which is to use the now-deprecated TF Mobile, as TFLite does not support training at this time)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "RuNlrIqTB1yn",
+        "cellView": "form",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653596006,
+          "user_tz": 480,
+          "elapsed": 19333,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        },
+        "outputId": "8fcb06b3-c3e3-4af1-ae63-a674495b6e6b"
+      },
+      "source": [
+        "#@title Benchmark inference and training\n",
+        "print(\"Inference latency:\\n  \", end=\"\")\n",
+        "%timeit -n 100 compiled_model.predict(x_train[:BATCH_SIZE])\n",
+        "print(\"Training latancy:\\n  \", end=\"\")\n",
+        "%timeit -n 100 compiled_model.learn(x_train[:BATCH_SIZE], y_train[:BATCH_SIZE])"
+      ],
+      "execution_count": 13,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Inference latency:\n",
+            "  100 loops, best of 3: 17.1 ms per loop\n",
+            "Training latancy:\n",
+            "  100 loops, best of 3: 21 ms per loop\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "uY2D4QVXBWAD",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653638844,
+          "user_tz": 480,
+          "elapsed": 62166,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        },
+        "outputId": "217c9952-4b8d-4996-c3fe-2b4503b6099b"
+      },
+      "source": [
+        "# Run the core training loop.\n",
+        "losses = []\n",
+        "\n",
+        "step = 0\n",
+        "max_steps = x_train.shape[0] // BATCH_SIZE\n",
+        "\n",
+        "for batch_start in range(0, x_train.shape[0], BATCH_SIZE):\n",
+        "  if batch_start + BATCH_SIZE > x_train.shape[0]:\n",
+        "    continue\n",
+        "\n",
+        "  inputs = x_train[batch_start:batch_start + BATCH_SIZE]\n",
+        "  labels = y_train[batch_start:batch_start + BATCH_SIZE]\n",
+        "\n",
+        "  loss = compiled_model.learn(inputs, labels)\n",
+        "  losses.append(loss)\n",
+        "\n",
+        "  step += 1\n",
+        "  print(f\"\\rStep {step:4d}/{max_steps}: loss = {loss:.4f}\", end=\"\")"
+      ],
+      "execution_count": 14,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Step 1875/1875: loss = 0.2015"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 643
+        },
+        "id": "FLi6jmABCom3",
+        "cellView": "form",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653639482,
+          "user_tz": 480,
+          "elapsed": 62798,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        },
+        "outputId": "af51aea9-638e-4d84-ee46-a68898f7c326"
+      },
+      "source": [
+        "#@title Plot the training results\n",
+        "import bottleneck as bn\n",
+        "smoothed_losses = bn.move_mean(losses, 32)\n",
+        "x = np.arange(len(losses))\n",
+        "\n",
+        "plt.plot(x, smoothed_losses, linewidth=2, label='loss (moving average)')\n",
+        "plt.scatter(x, losses, s=16, alpha=0.2, label='loss (per training step)')\n",
+        "\n",
+        "plt.ylim(0)\n",
+        "plt.legend(frameon=True)\n",
+        "plt.xlabel(\"training step\")\n",
+        "plt.ylabel(\"cross-entropy\")\n",
+        "plt.title(\"training loss\");"
+      ],
+      "execution_count": 15,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 1200x675 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "HL2mmtEqHHjk"
+      },
+      "source": [
+        "## 7. Evaluate on Heldout Test Examples"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "cellView": "form",
+        "id": "ObYYinU5HxCK",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653645185,
+          "user_tz": 480,
+          "elapsed": 68495,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        },
+        "outputId": "8dbf8d34-d210-4716-fb07-1ac82e4d8f5f"
+      },
+      "source": [
+        "#@title Evaluate the network on the test data.\n",
+        "accuracies = []\n",
+        "\n",
+        "step = 0\n",
+        "max_steps = x_test.shape[0] // BATCH_SIZE\n",
+        "\n",
+        "for batch_start in range(0, x_test.shape[0], BATCH_SIZE):\n",
+        "  if batch_start + BATCH_SIZE > x_test.shape[0]:\n",
+        "    continue\n",
+        "\n",
+        "  inputs = x_test[batch_start:batch_start + BATCH_SIZE]\n",
+        "  labels = y_test[batch_start:batch_start + BATCH_SIZE]\n",
+        "\n",
+        "  prediction = compiled_model.predict(inputs)\n",
+        "  prediction = np.argmax(prediction, -1)\n",
+        "  accuracies.append(np.sum(prediction == labels) / BATCH_SIZE)\n",
+        "\n",
+        "  step += 1\n",
+        "  print(f\"\\rStep {step:4d}/{max_steps}\", end=\"\")\n",
+        "print()\n",
+        "\n",
+        "accuracy = np.mean(accuracies)\n",
+        "print(f\"Test accuracy: {accuracy:.3f}\")"
+      ],
+      "execution_count": 16,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Step  312/312\n",
+            "Test accuracy: 0.904\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 676
+        },
+        "cellView": "form",
+        "id": "tFKFfdpVJBK3",
+        "executionInfo": {
+          "status": "ok",
+          "timestamp": 1610653657859,
+          "user_tz": 480,
+          "elapsed": 1185,
+          "user": {
+            "displayName": "Phoenix Meadowlark",
+            "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14Gg1s3aB1Ho9jND1l14tYSizBMuDi8y1thOD0m5z=s64",
+            "userId": "03779344908574432788"
+          }
+        },
+        "outputId": "cc00468f-dbe1-4693-86d2-caa5f46643c6"
+      },
+      "source": [
+        "#@title Display inference predictions on a random selection of heldout data\n",
+        "rows = 4\n",
+        "columns = 4\n",
+        "images_to_display = rows * columns\n",
+        "assert BATCH_SIZE >= images_to_display\n",
+        "\n",
+        "random_index = np.arange(x_test.shape[0])\n",
+        "np.random.shuffle(random_index)\n",
+        "x_test = x_test[random_index]\n",
+        "y_test = y_test[random_index]\n",
+        "\n",
+        "predictions = compiled_model.predict(x_test[:BATCH_SIZE])\n",
+        "predictions = np.argmax(predictions, -1)\n",
+        "\n",
+        "fig, axs = plt.subplots(rows, columns)\n",
+        "\n",
+        "for i, ax in enumerate(np.ndarray.flatten(axs)):\n",
+        "  ax.imshow(x_test[i, :, :, 0])\n",
+        "  color = \"#000000\" if predictions[i] == y_test[i] else \"#ff7f0e\"\n",
+        "  ax.set_xlabel(f\"prediction={predictions[i]}\", color=color)\n",
+        "  ax.grid(False)\n",
+        "  ax.set_yticks([])\n",
+        "  ax.set_xticks([])\n",
+        "\n",
+        "fig.tight_layout()"
+      ],
+      "execution_count": 19,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 1200x675 with 16 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    }
+  ]
+}