diff --git a/examples/dataset_examples/SNN_Tutorial_Derrick_Lee.ipynb b/examples/dataset_examples/SNN_Tutorial_Derrick_Lee.ipynb
new file mode 100644
index 00000000..089b0e7f
--- /dev/null
+++ b/examples/dataset_examples/SNN_Tutorial_Derrick_Lee.ipynb
@@ -0,0 +1,1736 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/DerrickL25/snntorch/blob/master/examples/dataset_examples/SNN_Tutorial_Derrick_Lee.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[<img src='https://github.com/jeshraghian/snntorch/blob/master/docs/_static/img/snntorch_alpha_w.png?raw=true' width=\"400\">](https://github.com/jeshraghian/snntorch/)\n",
+        "\n",
+        "\n",
+        "# snnTorch - Training Spiking Neural Networks with snnTorch\n",
+        "### By Derrick Lee\n",
+        "\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "LPxYaNwaj6zk"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "The snnTorch tutorial series is based on the following paper. If you find these resources or code useful in your work, please consider citing the following source:\n",
+        "\n",
+        "> <cite> [Jason K. Eshraghian, Max Ward, Emre Neftci, Xinxin Wang, Gregor Lenz, Girish Dwivedi, Mohammed Bennamoun, Doo Seok Jeong, and Wei D. Lu. \"Training Spiking Neural Networks Using Lessons From Deep Learning\". Proceedings of the IEEE, 111(9) September 2023.](https://ieeexplore.ieee.org/abstract/document/10242251) </cite>\n"
+      ],
+      "metadata": {
+        "id": "2KZ5Jo9mkd_y"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "\n",
+        "## Introduction\n",
+        "In this tutorial you will learn how to:\n",
+        "\n",
+        "* Train a spiking convolutional SNN\n",
+        "* Construct a dataloader using [Tonic](https://tonic.readthedocs.io/en/latest/#)\n",
+        "* To train a model on the [DVS Gesture Dataset](https://research.ibm.com/interactive/dvsgesture/)\n",
+        "\n",
+        "If running in Google Colab:\n",
+        "* You may connect to GPU by checking `Runtime` > `Change runtime type` > `Hardware accelerator: GPU`\n",
+        "* Next, install the latest PyPi distribution of snnTorch by clicking into the following cell and pressing `Shift+Enter`."
+      ],
+      "metadata": {
+        "id": "AEIyFscwk9Cx"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "KJAF2tZPvPMk",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "8e60c8cd-1f7e-4c56-f60a-e4fd0da674bf"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m109.7/109.7 kB\u001b[0m \u001b[31m2.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m112.7/112.7 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.4/50.4 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m109.0/109.0 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25h"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install tonic --quiet\n",
+        "!pip install snntorch --quiet"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# imports\n",
+        "import tonic\n",
+        "import matplotlib.pyplot as plt\n",
+        "import tonic.transforms as transforms\n",
+        "\n",
+        "import torch\n",
+        "import torchvision\n",
+        "\n",
+        "import snntorch as snn\n",
+        "from snntorch import surrogate\n",
+        "from snntorch import functional as SF\n",
+        "from snntorch import utils\n",
+        "import torch.nn as nn"
+      ],
+      "metadata": {
+        "id": "C9F9ihlGls9u"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# 1. Dataset"
+      ],
+      "metadata": {
+        "id": "IRW_OSVfmMF1"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "T-KcsehPANDP"
+      },
+      "source": [
+        "The dataset used in this tutorial will be DVSGesture from IBM.\n",
+        "\\\n",
+        "This dataset is comprised of 11 classes, where each corresponds to a hand gesture, like waving or clapping. All events were recorded on a DVS128 camera, which is a vision sensor that captures changes in the environment (events), represented by illuminated pixels, while static backdrops are ignored or produce little noise.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "L9ALJIrHL7AW"
+      },
+      "source": [
+        "## 1.1 Loading the dataset with Tonic"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 156,
+          "referenced_widgets": [
+            "3974416247f7451bb2bb82bdb83138fc",
+            "0f504b5f4ad74595ae37ebf795d46514",
+            "5fd4888429c342f2b1493c1689e6fc6b",
+            "b4a14c5ad41441a7bbb76aa96f72778b",
+            "766a82612ccc442fb46264421109c713",
+            "92e3de6e58a24ea1a870432e8d907504",
+            "c0c3f6d088534ceb9d70af69d7e08392",
+            "0b28db65ac3743c2abb7ddd085fbed21",
+            "1071d5988c9b4cf7b846b51db4f66a32",
+            "daa45045ae794990867fce4f0be28245",
+            "c710df2cd11e4ec2b1c9da6585c76016"
+          ]
+        },
+        "id": "peDXjxJUwEVX",
+        "outputId": "0a85d931-90d1-4fc4-8867-32266e8cd4fb"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Downloading https://s3-eu-west-1.amazonaws.com/pfigshare-u-files/38022171/ibmGestureTrain.tar.gz?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAIYCQYOYV5JSSROOA/20231102/eu-west-1/s3/aws4_request&X-Amz-Date=20231102T212615Z&X-Amz-Expires=10&X-Amz-SignedHeaders=host&X-Amz-Signature=587183aaf756ad2dc11fa835233d8e4b110563001b4e86117a308156d072b349 to ./data/DVSGesture/ibmGestureTrain.tar.gz\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "  0%|          | 0/2443675558 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "3974416247f7451bb2bb82bdb83138fc"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Extracting ./data/DVSGesture/ibmGestureTrain.tar.gz to ./data/DVSGesture\n",
+            "Dataset contains  1077  samples.\n",
+            "There are  787770  events in the first sample.\n",
+            "A single event:  (119, 113, False, 6)\n"
+          ]
+        }
+      ],
+      "source": [
+        "dataset = tonic.datasets.DVSGesture(save_to='./data', train=True)\n",
+        "events, label = dataset[0]\n",
+        "\n",
+        "# Dataset size\n",
+        "print(\"Dataset contains \", len(dataset), \" samples.\")\n",
+        "\n",
+        "# Number of events in the first sample\n",
+        "print(\"There are \", len(events), \" events in the first sample.\")\n",
+        "\n",
+        "# (x-pos, y-pos, polarity, timestamp)\n",
+        "print(\"A single event: \", events[0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ZSTk0p-HQUPk"
+      },
+      "source": [
+        "## 1.2 Visualizing the Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "tIUgiH4z52IC",
+        "outputId": "386e6579-be2f-46ba-d5a6-3424cad3878e"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "(787, 2, 128, 128)\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<matplotlib.image.AxesImage at 0x7f72f1e0b670>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 4
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 3 Axes>"
+            ],
+            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAgMAAAClCAYAAADBAf6NAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAA6sUlEQVR4nO3deWxky34f9m9VnV7YzZ1s7hwuw1k4nBnOeu/MXXzfgyXbsiRLjvwcww8JFClwkAgxIsVOECAIgiB/xLFjRHEcxRGkCLYhJLESRVlsRzJ033v33pl7Z9+Hs3Hfd7LZzV5OVeWPQzbZ7L15emH37wPMH8M+S/Xps9Spqt+vmNZagxBCCCFVi5e6AIQQQggpLaoMEEIIIVWOKgOEEEJIlaPKACGEEFLlqDJACCGEVDmqDBBCCCFVjioDhBBCSJWjygAhhBBS5YxsF/xp/oNCloNUiT9R/6zo+6Rzl9iBzt3KwlwumJ+MQHz5qNRFKbhszl1qGSCEEFJ1dDgM46tnpS5G2aDKACHkZOMC7OYlgLFSl4ScMNo0S12EskGVAULIyaYVxPwaQNOsEJI3qgwQQk42rWHOzZe6FOQQZhgwerpLXQySA6oMEEIIsRUzDKjWhlIXg+SAKgOEELKHOZwVN/aAOZxF36cKhaCevCr6fkn+qDJACCF71EcXIBrqS10MW8lbI+Beb6mLQcpc1nkGCCGk0rFvnkCWuhA24189hip1IYitjO4uyK4W6PvP7dumbVsihBBCSMGZ8wvAwpKt26TKACGEEHKSaA1oe9uwaMwAIYQQUuWoMkAIIYTYjBkGjN4e27crmpogWppt3y5VBgghhBC7CQHVYn9kCqv1gtXV2r5dGjOQI+ZyQUci5ZH6lAswzii/Nqko3OOBlhI6HC51UQjJmw6HoQuQa8GcmbV9mwC1DORM3Rgumzhko68HbORMqYtBiK22f+4yzNsjpS4GIcVTBomuqGUgR+UUh2xOTJW6CITYrvZ/+7bURSCkqOQXV2HcfVnS1jCqDBBCCCElJH7yFFqV9jWTugkIIYSQUipxRQCgykDFESPnSjIxCSGEkJOLKgOVJhwpdQkIIYScMDRmoMLI9xOlLgIhhJAThloGCCGkyjGXC+Ci1MUgJUSVAUIIqXJ69CyEr6XUxSAlRN0EhBBS7e49L5v8KaQ0qGWAEEIIqXJUGSDk1uW8+kuZywV8dKkABSKEkOKiygCpemJiEdAq5/V01ISYWipAiQghpLhozACpenJpOb8Vlcx/XUIIKSPUMkAIIYRUOaoMEEIIIRWCOZx5paSnygAhhBByQjHDABjb+w8DP9MPfqb/4G9ZosoAIYQQcgJxjwez/+FHML9/zWoRuD6CcEcdwh11YNdHctoWDSAkhBBCThheV4fo9TNoexjGxC9rnHKPYrvPgHtDY7eFY/u0A6ddV8C+eZLV9qgyQAghhJwwvL4OK6NuAEDXH0lM/wygvVE0PnDCtalQO8OhnBz89mhW26PKACGEkDjM4QQbHoR6NlbqolQVMTQA+ANpQ5aNnm5AcEAqSKsugKCPw7EJeMYE6uZN8LCGM6DAlIbxfj6rfVNlgBBCCIyOduhoFHJtHdAK3L+L3FNxkeNggV3ocDjtMtHeVgS7rVpAqE3BvczhCADObQYR0gjXC3iWTdQ9W4Z2GFj7maGs9k2VAUIIIYDbBbY3Al2bJsyJqRIXqPqYC4sZl4k0ObF5WkALQIQ06icVuNSAFtjpA5QBiIiAa3oWorcb6xey2zdFExBCCIE5OZ3Vw+gw7vEUqDRVgLFjHT/HDtD94yjq/tdvsTUoIGuAcHcU0Y4oIrUMrKYG0Y5GnPrjSFbbo8oAIYScJIxZseWZ5DH5Vk64gHnzXM7x7MTCPR6Y187mtS7TgHQBa8NWciEmgdCZEIRbouGxE2131qB2dsAfvAZTOrvy5FUSQgghJWH0n8Liv/tR2mWYywX5RXajyPOmJPiPHwM6u4cNiacCAfCvn+S1rmtdo3nMjP2/7VEI2uQwPrhRs6pieQZ0NALxo0dZbZPGDBBCyAliTkyh/R/Opl1Gh8MQP3pcnAIVgKivh3lpMOsYeTsZfb1QjbVQT18Xfd+ZbP3wFlZuAo4thoZxibYnUQDA0nU3+v4gCs/997EBoLlW0ahlgBCSN+ZwQmcZx0xspGTmZY68sYf/4k2oz68WqED2kn4/xEN7wxr9f+0WxMi5zPueW4B+9cHWfdtFc4bmpwzuNWDuCxeMR++hPxlFy8soNk87wDxuQEkY7W3glzJ/18OoMkAIyZs2ozDepX9LJeXB+3QOjrET8ltpDRUK2brJpm/ngZkFAFb2vlQVA22a0NHsBt0Vkxg5B9MD+AeAQJeGew1QOzsw3s3Df8pA7YKEDu4dM8OAdubW8E/dBISQ/GkNubpW6lKQLJhz2SWfqUTGYL/1xr8fwx+Ngm0HSluoHG1ebILpYYg0Sjg3BDq+2YLWGnJlBc2veuBY2AQaaiEa6wCpIOZWYXIBcbovq+1Ty0AJiJZmcLe71MUgFY4ZBoTPV+piEFJy2u2M5VAAABUKwZzJrZVEtLaAuVx2Fy1r0smg957Yrg1AP3wZ+4x/9Rjy/QQAQLucQCQaCxPVruymM6aWgRLQ3W1gC2uAzc1ghBzGXC6ovnZgZaX4+3Y4wQS3vamXVB7u9UIFCvuWLl+9PfY2dHcb+KyGzJAhsFAaxnchXTVw+DlESIO73QnX136FIJY5UkmoF9mNvaCWgRJQz8Ygc7lBFzpemFQkFQhAP3hRkn2Lrnbg3EBJ9k1OFvPa2ZK+cWdLPX1tjdQ/Lsbyzs1QPxlBz59G0PwmDD1y+uADLg7+5bltahkoc6K1BebZHrA7T0tdFEKyZk7NAJTNlmSBf/U45zC4k0yc7od2u7J+Yz9s46wL7k2Fpifrca0d8otR6L1KgPvtIszZuZy3TZWBMidX18DsqI0SQkgRiPY2yL524N7zUhelLO035eerbnIX8tVbiPp6RK4PARo4nFPCzDMJFHUTnASU4YsQckLIlTWwx29KXYyK1PghAuUSEGetLgLNGDRn0J+MghmO2LPC6GgHHx3OadtUGSgAcW4IorWl1MUghFSIE3VPUbIs4/SPS1w4C9HUZO9GuQC7OpL14oFOB0ItDsAQkDsBuJ5OwPV0AsbYNLQZjS0nNzbBJnLrKqBuggJQ9TUQO8FSF4MQUiHY9g5UuPIesCcJ29qBsjuSQCuIDT/MzEsCAKIeBhHZGyCoZNIBjaK9DQAgl5ZzKgpVBgqAb+xAB3dLXQxCSIXIdWphYj9zbh6iqQlcCCi/356Nag1zcjrjYkZHO/w+J4xdDSOkYTZ5wG9eglnrgPjSmohItLcBrU3QgoGvbedclIquDDDDAHM6oYLFfUvPNECEezzQkQi0mW19MAPGwGtr7TtBCSHkhDC6u2DOL2Q9too5nGAOI7/ngq8ZfDdc9Htt4PoprF0w4HsahWslhJ0+D1auc0Tbohies8YPBE83Y3PIgebXYbinF3LeR0WPGeAtzdAXBlMvwFhJYvjVxdMQvlbbtsddLpijpzMvSAghFWb2B/3gNTVZLy862oAzaVL0pnkuyLcfcs5caIe1Cw4Ez4ThXtoF7r+Aa0vC7IjAcJt485/V491/Xoflaw6YHmB11IXg7bM576OiKwNyaTlt0hWjox24caGIJbIwm4MDVCiU97zYhBByknX8t3dyess3Z2bTTk9s9PWCjZ63o2i28o65EOzxwDjVA8cfP8D5/9oPJRlqntdA4+C50vmVH65/cT/n7Vd0N0Em5sIiUIK+OH3/edYDRggpFdHYAHNkoCRzyhNCDrQ9DGP8rzP0/KtdmFMzMLq7EG6vRf/vMUCH4fhvXkDLvWmtKc8AIcROcmsb/N6rlJ+Lxgawm5dy2ia7PnJyQuTKlNHbg7VfvV3qYpwY+tMrYEb2773m9BzwPHOeBHHhLP6tN8VJs7l62YWefy5g1rliYySMOy/h+PoFHN+8sMafaQ1++TyMzo689kGVAZvx0WFwr7fUxSDk+LROGy+udgLg7zKPhD6Mv5uB2qKBrsehVlbR/q+K3299UhmvpnIbrK1kVsvrqTn81t/6wTFKlgUuwK6PQDmBnS4B5/KONWW41tDhcOxfzPgs5PqGtarXm1PiIaoM2IyvbUNHopkXJOSE06YJubmV0zpye7siE9IUkwqFrLkfSFbkxkZBtqsCAbj/73sF2fY+xhmiDW4EuhUcOxpsYzv+4X+0TH5/7HMdieYUYkiVAQBgDEZ3lz3bsitckBBCikS0t4G73Uk/Mzo7aObUUuManhUTOpR90iMdjeQ0YRFVBgCAccgue/oxZWcrmNNx8AcuwOvqbNk2IYQUgm5vBvN6kn4mu1vBHFU91rw0GANvqIfpFWh5zKEcDMhy7ANzOHPurqbKAGD1Ed23Z4Yt/fglVCAQ+7+or4UaoXndSfnLZZAVqSzq2VjS1LYAoB+8SNs0TQpD1NUh+NFpbJw10Pw/f4ugT4B54/Mp7F+zR69d0dqcPpdCElQZKDC5uQV8+6zUxSAkI3n7EkR9famLQQgBwOpqsTbiQNujEKA1Wn77blzqYlFfD3nbiuYxP78M5nDGPjMXFqGepI4ESoZeBQghhJAyYnS0Y+dqD7hEbO6Bo+T2NvhXjwFYyxw3l11xWgYYg/rsStUMQuFXLuQd60lIqYhvX0Ju5z7BCSHFwEeH7RvoXeZUWxO2TxlofVa87pniVAa0huPFBKBkUXZXch9mIFeT978RUq4o5I+UtffTkMurxd0nY2A3LlrzFRwiGhvALxcuZXG0xYNgt4br/jurGNdH4roBssUMwyp/Foo2ZiDXeOSTTPn9ed9YxdnTYC6XzSUipcAcTohzQ6UuRs6Mzg5r3g5SNYzB/rKPelKBQNEqrNzrhRgaALSGWEzMU6BDYfCVzcLs++J5bA66YOwwoMMHABBLmwfphnOgpUxa/qT7zXnrJG9GT3dCDTNBps8JKQPc64Xw+UpdDGIjRveeeHvHw5ydi+X7Fy3NEPX1VuKnJPPaiNaWYw3CFa0tCHfVAgDqJ1Xs7+bsXH4t61pnnWuAKgMFdDTWU3Y0ASz9IZdv3lMYT4XQ0Qjkm/elLkbOzIVFmItLaZfhdbVAc0ORSkSywT2elImDMjHHJ2m8yCEqEIB8N574QVMDWP1eCwpjiQ/+pgawutqE1URjQ9oXPdHYANHYADXQBSUYahdM1E3uAosrx/kaOaHKgI2O9umItlZg6FTs//rBi+oZN0FONsbS5h0wF5dOZEWnkrHeLrCezlIXo/QynLvHId9PxN60ucsF89Jg/OfvxmHOzSesZ44MgKfp/o1cOY3wtSFE65wIthvY6Tag3AJmhhw1zOHMayxBMlQZsJH52cX4WM+5+bTzZhNSroyebmD0XKmLQXIg37yHfD9R6mKUXLHOXRUKZT29N/vmCVQolH4ZrcEOTT8sAlGwu09TLi/q62F+dhHmZ9kNEMyEKgM2El8+ShjgIpqaoD+9UpoCEZInc2YW+uFL+zd86zJEe5v92yVVS37/WvxLWAHOXfXF1YT0vtzthvriat7b5F5v3PqOu68gvnwE5QAi9Qy4lz4rrtzehvjyUco8BLmipEMFJjc2wL/zHzshBCGFpm+Pwng5UdC+Y/bgFWQeo6JJHvbyu/BvnlV096Tx1bOcpig2erqhmuugno2lXEY0NSF6sf9gne9eQ4VCEBfOgu2GYU5MWf//5nlO93Z+8Ty4PwBzagYqEIitb3z9DGrvO9TOmYhuFv89nVoGiiCnubRJ2TM6O05kyGAm4sU45E4g84KHMIcz6zhmYO9a0FQ1Lgqt4Xj6oaIrAkDi/VW0t0EMn0m5vFxaAT6knwJabm3D8fRD7N9+E7+enIWcP4giSHVvF01NyfMQjE9DLi4nrn/lfKx1o2bWD9eWhBgpbjddZVQGGIO4cDbn1URjA4zB/swLcpHX9kllUjsBYK0wc6QnyPPczofy+zM+OIzBfmtk9B4tJcRC/gm2mMOZ9MYtfD4YvT15b5dYqjFCQO8EgNXN1J/vdeWKs6dTb0RJyO3t2D8AEEMDYIaRXbSX0wHpTRwwqILBpOuLhXXwoT5wrxeyzg3p5MBycRPXVUZlAACkyrzMUUpn/5aSz/ZJRVJ+P+TqWvF2WE7nnlLWdRP7v4wbPW10tIN7kk+Fm9KR7ydaW8DqvNSCQPKiAgHIlQwheXvnVi4VTiYVdJbnpA7uwrGUfaI9c24eZrMXzO2CsbmLmoUsvoPNKqMyoHVeYU5yexvmxFTmBZUsehjVcWKGSQXJ89w+Du7xWM2cRzLSicYGmNNzad82dUsjWE3m81Y0NsDoaLdyMbz9cPD3+nrA1wyEI1knSyFkH/d4sqqMqmAQamIGsi37XBnmxBSgVMr7sqivj4U0Kr8f5vhk1ts+TL58Azx7lzQjJK+rK1iG2sqoDFQQXldnxcn2dYN3ZpESljHb4kzJyWTXzYE5nNb51NOJ6EgfMBj/1hS9NAhR602xtkW+fAO5lrl507zQj+3b/Ql/V2dPASvrca0NdH6TbLH+HrDe+MmMUl0fOhrJGHVw9Nxjfd3gHcmjYdTZU+CN+Sfi4hEZa3XjzY3Qh3LU7NNnT0Gk2P9xUWWgzMz/yiUY7W2Qr99l1WohWpqhbgwXoWSkHDHDgPnJiC3bkrdGIBrqId9+AP/6SdIcGdk2k2bC7jyF5w+/S9z+gxdxXTDc44H5qT1x1KQKJDk/zU9G8kpCxN3uhHNPvnoLc3I6+a6PnLtZOZSVUN9/DrlhjUWSS8vQj1/GL1fgdNFUGSgzHb95J2Mq2MPk6lraxBSksmnTtC3OeOVqDdhe06TR2wN2Pb6Swb96bA0yTOejS2U/yRG7PgKjr7fUxSAFIF+/S+hWE18+yjuiS3MG+f1rABd2FC+O0dGOxf/gdlbLzv+t25j/27cR7E3fMnes8hRsyxVufyTq4f7OTNTnVyHuPqdQwzKkPxmFeD6e+WFXwTr/p0cw90Y6m7NzwNxCTusv/3ufoOuPJqFbGmF4avLuMz1MBYMw7r6E/Pwq+NdPgJsXoVwGnNOrMKeSh4fN/iefoHlMJm15WP0bt+Fdkqhb3YbR2QHZ1ZK2qdjo7cH8L5xC69PdY38XUlzM4YS8NQL+1eO81lehEBw/sV60tJJgNy6CTy3ZNrDPXFpG129tIZvhwT3/wKrwa6lgmlFb9n8UVQbypKZmc17HePI+lliClBfxfBxqZ6fUxcgo9HMfoWYuEN+EmCV2dQTs/XTKCk9culStAZ08zFAMDYCZEnp9E3qwB+rJKwBA1x+OQ3a0QKxsQq6kn3c+/LM3sd1rwPc/3s1Ybh0OW9eO1uAvx8GGBxDpbQFvb7S+l9LWvB97+v/pNHQwCLS2QHf4oF69A25cAO49R8Nk9CAagnPr357xv3Mb/f88hJ1uF1ybEq7VEHYbXTA9wMqVmozlJOVFRyPWeXOcbRy6X2uDAzx1Uz0fHQabXow19WfeuM6YonhftssdB3UT5EmHwznPLljNb53lTvn9RQllM/p6j5WO1/tmFXw+vzcTsbAKHbJhRszVdej1TajdENjCwUPfXFgEn11G5HQb2Ln4CVbEyDmIkXNgLlcsnKt2IftkOPvXjgoEwCfmYfjDYBowVrZh1jkPtm8YgOAAY9A7AbBwBDu/dAOTP18LcAH302nUvJyDWrUGOUYanNj9hY+sdRWwNuzG6ijDyqgD/gEvzBoOJYDt85WduKdSZXvPFcNnMg7EFR8WoLdSR9KwxTWoYDCn8mXERdGSD1HLwBFGTzfkyipNI0xyYvT2QC4sZu4CMiVwjHS8SadVPUS0t0EHd5PeBHMZi5K2DJsH8dNyaTn+s5UViO02sOiR7xjdOy5KA0rB824dLBhCsqMlfD4gGonbT9w+1tYhmhoA6YKcXYDTYd3GIt0NcHww9o6xAjiHdjkRbuCI1uuE8vLGBoRaHFj4C1E4FpqhDCDcxGA2RwFmwN/LIcIcNcsaWtjfZ1xNjO4uqLX1jG+4oqkJ4CyriBRbmZmvyUzdA0evhaMyHYOkn2t1cO0UGLUMHKEa68CcFMpEcqNa6uNGLDPDiMvUt8+cmy9swqKGOjCPjU3ajEG0NOe0in78EvL1u7i/ybcfIN9+gI5GrGPw9kPqPAINtWA16b8D2w2DB0OxPAXy7QdAWw94vbsLFQyCN9Qj3OFFzbpC4xizbqyHyxkOgymNz8+/w63vv4RstG66xpoBI8gQadIIdms0jodx6v/NPoEMSaSa6rO6r7JaL1hdbRFKFE++Gy/4C2C0zweWJjQ36THSOqdxacdBLQNHqBepJ68oJ8wwoJUGtAIzHAmzJVrNpQKQMva2ylwuavEokP1+8328oR5qoAt4UNyHiN03DmY4YJ7rBbtTvDe1dNPwMocT2owmnTMeACJDnZBuAff0JhDYBThDoJ2j9dluQjeQXF1Dw7MmfP12CDrKUffaAaYB3xMToRaB3RYOx44Gi6q8xmiQA9neV82Z3MdilVIu91QekfHnIGMQdXWxJF6lfvZQZeCEYueHIIIh6G0/zDM9CeGF7MIQoi0eONaC0M/GAC5gfjIC8aPHlOa1COTaOlDsps4C0NEI2J3yCV1VN4ZhvJtN2rrCtIa4/xo7v3QVu20+ND7bhOOPH8CXZnsssIvaZ21oexQCYDXPOh9/gKfdZw0WW1hG9OJAmi2QasU9Hpg3z4H/OItoBS6sPASH/iTafJj7a0Po+M07BStjLqgycEKpF2OxUbIsyY1RPRuDAA5G0ippWzw6KR12dQRiw58y8UmlY3efIlXvLv/xY2gA9b//LcTZ09BOR3bbNBF3bUgA2BuvkKyrhxDh88E805VdRQDAwq9/jJ7fG4sbCyGXltHxm+nHGRQTjRkg5ATRT8dSxteXO/XZldwnMTq6fhbzdfDRYbBIFOrlG/C6OuhPr6RcVm/74XuWZkDX6R7wO8/zLTKpUHJlBezbF5kX3NP13z+MqwiI9jawm5cKUbS8UWWAkHLGBXDr8kEqUiWTd/N8dKnsc/gbj99B7eafvMd4/A7qSP+saG3Bxi8fyeL2ZgJybtGK497ZgXgSP5jxMOn3w3HvTfLPlpbBXk9knNaZZM/oPwVxZrDUxUjAblzMuqJq9HRDnBvK6bw4Oq5Ara2DvSzOwMBsUWWgWjAGfvF8wfNbE5spCWNyKeM4D2N6GTqHzGSipRliqDB94UZvD4zODgDWgD9+8bx17g30go+cs2YmTFWus6dTfq4CgbjjIBoboDt8aHkQn+RFhUIHA2q1ttZLJc3nvKEerKsd4MIqPzk2tbYBrOx1a5bRceUzy9CRSOYFAaiNTWA5t4ggMXIurrKuTTOvnATGYD9Ea0vO62Ujr8qAaG3JOdyIlB4LR2jw4DEJn8+KhS6ibPIDmIsHFYboT11H+C/eTL9C1AQLFyatKaJR6OjetrUCC0fi/ukUeRaMvl5Aqdjn3OOB0dOddFnR1ITdW2cx/fPN4P6Dh7nR053YlcAYjP7EGeCOmvwvb8dXRFqbETzbCiYEIm2FywlfTZTff5A/Yu/cOIp7vbHKZLHIpeWs08SrQAByYwPMMLKf4yIcSQhtzUskChQoi21elQHm9YAdo++PlIDWcQlrRH19Vv2vJB6r9dgbx3+EHb/L9oATm6fTD56T29sFC+MyF5dio/21aUK+G4/7l+pNXDXWQs3MA5xDtLaAtzRD16d4CLc0YmvAQHAwCtVoxaWLlmao5iR5Qhg/WKapKT4fhMtltZAwhr/zr/8TsHproibu9UJ5XNCcgTc3wrFR+HSwVefIPWkfq3FD1xc/10DOhIidV5nI9xPWpGLHvL7N2bmkybhES/OxW33zqgyYUzMnLh40k2p7MOrBHvDO8p5drhyZE1MpY9xt0dMB7muN+1Ou52bLb99F+z+wP1yJuVyF7WZ6M2ElAurpgHm2B7q2BvLVWwBI2hrT9CaCs78Tjk21HLnUD7ydjMVtxygJNmVNuqSGesAPJX4RrS1Y+HOdEM1N+I1/+UPogNV0yzrbwINheO9PInqmi/IMFJFcXUuYebAc6XA46TTfaSW5vu1gnusFM7KLnkmFxgzAStATvXWh1MUgxJov/XBFmwvr3Nx/CB/3YXyM9eXNYfDawr2xmTeHwT0eyNfvwO48jWUxZA4nZn51OGFOeqZ0bNIh5nCCaW1NPMSYNfBy77tytxszvzpszVfw4EXcm5X276DpfQQzv3IeZ/7mvYP55N9PgO0EERnuAaOeNWKThOvbJuzO04TEc7miPAPYmxP+RxSDT8qQkjh8brIrF46VZ4BdH4FY3EidCjgN/vWTY80Al3H7Xz1Oun0djaDr793B4WeyfD8BsZepkHu9eP/bZ3D633wO+fFFSJeA/5QTTr+C93//DioUQtffs1pK9KdXYLyaiptZjpka7Q9CCeNpzLl5iEK2AhFSRqhloFIwBvXF1dRvflzEfa6evq7axDX7eF0dFn/9k4S/r/6N23j7uzdKUKLM9JNXx8ozoB++LGw3RxHwy+ex9cNbCP7ljwEAajeEnn/sgPz0EpSTY/OMEzyqUfduKyHPALv7HKq/C5v/xm2Efu6jEn0DUs2MwX6oL64WPM+AqK+H/mQ06+WpZaBSaA3jwVuoVNECSsZ/TlEFUDs76P799wkZ7dr/j7fo+JPapDPqldxxf7cy/935lQtgM4tpZ63TbybQxAYR9nmgb4+CSQX3V68Q/egcnM8m0RI5BWMjCPVhCjoSgXj8Ni4TJ3v9AS2TNUBLI/RAN5zfWTnhC9nqQY7h1mWwB6+yHu1f7uTMPIylFWvemELux++HePIu6/OaKgPAXrzrGQCAfvX+xJ50aeOps/i86middNpRuboGpJhZ0OjrBSJRmAuLhS5dWqKpCfA1F21GM7uJ9jYwTw3Miam4v7PZJaidFHH/F89bbZkTc8D7abh3OxDuaQTTGvx0L1yv56A7fHBMr0KtrccSvRyO5xbDZ6Cn5yE3NsB3d8G8HshD14W4cBZ6ao6ulTIiJhYhjzHtd7nR0cix+/ez25HOKZdBTt0ERl+vNaK40mgFFgyDBcPWTIBHMQZjoK/45coSM4ys4qiJDcKRgxj6EtKmCSgFY6CvrM/NlCJRIHSQlW3/e6jNrZSzwEVbPWBhE9zXAuYwoOcW4Zpeh3NmAywYhrm4BBbYteaET3ETNJu9sdBDFQoltECw3TBQQQ+ecsS93pT5I5KRS8tl36JVCXJqGVB1XrAVUdCmjWLhXi/AOZTfb70hJpk2lblc1ujmrW2o+vLNq8CcToT7WyEmpyHODYFt+SHXNqwZ5xxO8MYGQKvkM73tf8eNjSRbJkdlkwCoGJTfDx6NQp/LLYugaGyADoWhQsWNmxc+H+TKSuz/sfONCwhfC0IDrXCu7wLzImVSFcd6EGx7B7LHB6E11Pwi2Npm3LmbaRyMsbmbNtPc0ZYKYj/mdEJ7C5eroxoJnw9ydfVYlaacWgbUi7G8UiiWI97WCtbZln6Zxgbovk5wpyP3eNJiUgoiZIJ7PFj+Mz6Eh7vB62vBDAOi3Yfw5VPYvX7w0DA6OyAaG8A9HoiuDkRGB+Ji2bnbDTAGZhjgHs+xWoOYy5U2/SzJnwqFoJ6+zunc1D2d4E2Nee9TNDbkfj4wBvNMlxXudxgXEA31ME93QoRMqKev084Nr56NQXa1QDk4EDUhmhohz2XIAMdY3LktX76hLoASkxsbmfMIHPnd7MBcrsRz0Cb798xSMYe6KM9AvsyJqYz9rXJpGfgwA3m9PPJnp6JCIeC754jcGkbL79yD+PIR5No6RG83wkPtkC6O9fMHWdnG/qN+rP2lC4h+fB5b1zuwNuKGeePgO8qr5yCam8BP9yNyexh69Gz+hbt0Bmu/MHKcr0dycfiGxFjCg1u9GDvWeIfVX7wANnw6t5W0BrvzNGFiF+FrgTl8CuzOU+vzNG81+5PI6Icvwe4+O4iISNatd3i92tq4cztvNKdHUfHaWvvvu5fOwGj32bvNPebNYfCaLFs79vNg2IjdpTwDBaf8frBvnpS6GHkxJ6bgDO6CD3ai4zfvx/4+9OvfAgDE0AAcKy54/2Asbr39OeMjN0/D32ug5Wn+J5l+8AKND/JeneSIXbsAsboNc2oGYvgMXv9GPc7+2/b9AE2/d9eWUffGQB9CA60QocyDdbnXi+vfbOPhLS9UKAQ+OoxIcw34cgC4l356YeX3g3/95FhlZQ4nop+X13Szla4Q91394EXBIoRS5chIJvpnryHSaMD7B98VqDT5qcjKAB8dBt8KlCSOXn96Bcbz8cSUqAXE3W6YN4dhfPko7u3KGOiDqqsB+/ZZ0vXkh8m0262Z2ECkvhXrF2vRfM/OEpOj1OdXYdx/fey+fP3oFcy9c0C+fodzv+aEBqC+uApx52VhRjEzBvnFVYifJL79p2JOTMHYvz731//x4/hZCX0+REZ6oaTGw0/eQIWsLkr19DUMJA8F1LdHYbydSRuamCsdjVjXFiE2cPzpExyvQb8wTlY3wUeXsupH0mPjkLOlSawiHo5B+v2F38+5odiMWSochvHwjXUjPXSM5MwcmNRY/+VbwEdJ3my0Prj5cgF9ezSuOVSNT6PhX76C7w/HEtcltjIevoFK01+e0v7vtu9wU7vWsT544/6bwoUzaQ3HvbG4ioDR0w1xIbF7iV+5AH17FPr2KMT5odg56Lg3ltBNINfW4bg3Zh2bI+GBRndX0m4F8fgN5IaVblj4fOCjwzl9FXbjIkR9vTVV7OEpnstsNDtzOON/9xPC6D8FcTbHbqYssJuXwOvqbN9u5h2zhPtmRkpmXWkuphNVGRDj81CRzGFdOhzOK1cAH03Mf54rFUpMa1oQC8tQq3tvP1pD7e6Cjw5DTC3FjhG7eBbBvnr4vlmGGM9QOVISxvv5uLLraAQQAvDRdNWFpoLB/M6b/d9tjxgasKZZbmmOu+kWauAvMwzwy+cTtq/WN4D5xMgLNrUA4/08jO0QtPPgWktaPiWhgsHEz+aXrO0noUIhzP7HHyP4lz+G2t4Gm04+PsLo6U46/SyfXLD2ubIGvbRqDbIdOZd0G6WkzWjc735SqJU1YHEl84I54hPz0Lu72S9fV5e0spozrRPum7biIucKbb7KppvAGOy3wnrSHNRkoXE576evF2ppBazWCwgRl3SGbweBUz1Q84tFD73K1X43BPd4wHq7EOmqhzG1DnN5JXYM+XYQNUolHShpdHZAh8JxYVmHQ7/2MbcLkbY6OKN9FHZVpuTKinX9TM6A7YatyrDW4MHCncOisQHM64W5sATh301oslfBIBC0KgviVA/M8UkAAKv1Qq1vgM2b4C5nxn5W5nBC9HYBQGwbyaZwPax+SqFm2ToO8lBrizHYb5VtfhE6FAIYt6JdOttjXYqxqZf3WveYywUeyP4hUzRaJ71ey12hIjn2fzfhswYIZjw20SiYTb9rQX8HrcCTXF+FUDaVAVVXnLhT7XEDDgfQ3AjtdACHKgPmxJRVWxSFCT8BrClT1eaWbVkOmWFANnmwedqFtlfxb5exG7DDCT7UF5sFDgBQ4waUsm52td6Ufaw6FIbhD0N5ayDarVBMeajCQQrv8HEXDfXQkWjim3itG4yzuHkHVCG7qxxO6BoXoGT6SiLjULVWt5Xw+aDrPGB+f/Z5LTg7uDcwltV5V//73yb9u6rdC/8SIvbw4B5P2ph3HQ5X/RweBcMYxIWzkC/f2LdJtyurc0SFQlDHmOMDgBUa29Jc4MqAjt3HC61sugnU09fHfsBwjydj3418/S7tTVK+elvQOGQ10GVbFkdmGFDhMPiz92j8EIY52Jn0+/P6Wix/Ys2hvX+MzPFJyKVl8Lpa6J72lPuQW9vWPPNj7xG80YfgjT6I5iYKtSoWLmAOdsIc7ARzOqEGesDb4udD5x4P1LOxoqbRlisrcYm69kP/jtLRCNQza8yJHOgAllYht3ey3s/+nPF23B/UszFrW4eubxUM2vowKgZmGBCtLaUuxrExpxNLnzXbei8xZ2ZznpEz1bmbCXMY1jldIcqmMmAH8/o58GwftEqBqeJPTaLvP0+sbOxfDDnGnoqeLrBzA9Z3MTXYdy8ObpiMxbYr19bR8jt3AQDRj85D1NVZ++ICcm09bdIao90HefUcmGFg7YIDqxcdCH58GqKFxhEUhZJgd59accThsHXOHnooMsOAedOmPu1szr9kN27GrDJkWv/ec6jB7sKdO6n2X6BEM6Uierqw+AMb+rsLKYsHvA6H0fqP7pa2lTHbczcJHQ5nDG09SSqqMsC/epx1X798PwH56m2BS5SZaGm2pplkDOb3ruQ0gNGcnLbedkIh8K+fwPzeldhJzS+fT5mzfu5XLiL4izdgfu8KeIbBUaq9GesjHmjTRNvDMJgGVi85sPPZ6aQDsEhhqaev46Yw1qYJ/uPH9mz708uZs0XevAij88jbkNZWGbIYIa3vPy9Ys6r8M6MJ0Ua8rg7q88sF2V+pmJPT8P3W3VIXIyWjox34+ITkZcjh3K10ZVsZUJ9fxc5fvZV2GeHzJQ2Z46PDaSfu4VcupHyQ6U9GrRnhikSurceyrxlfPrKnqffWZbDFtaR9TeLHj9Hx330H78QO3JNrUC/fgHu9UJ9dSbop9fQ1Wn73HrRpwvjyEdoehMGjwMZZAxu3uyGGzxy/vKQs8K+fZM6Pcf9FLIOhaGrKab509flVyO9di42BsMPhc1f8OPFlQPn94D95Ytv+KoFoaS5oWKK5uAR8VzlvzNWibAYQHmXcf416hyPtKEq5tg62vZ0wcZJ+9QFSp15Tv3wPM8XMZPzhGGSaiUwKYr+Z7DjNZVrDeecl5McXYYxNA11tMNyuuLfI2D60BF68g+7rhjh7GvLtBxgPxpIf6/3lD+3Dx0awPuzCTjeHdLSi2WmU99wNVYLduAj+fibjaPuUsjn/Di0jNzfBHwaznrjMuG+dIzKL8OBsCJ8P6lTbwbmbqvw5Xlf88nnwlc2ST1NdKHJ9A/xRwNYJ59j1EfDx+YOBoTTA+MQp35aBUChhoB8fHY4ffKdk0olNdDSS9g1bRyMpm4V0OHziTmTmcoFfuQCcH4Txft4a9DezALWyBtHYEPf2zkeHrYQl0QiiHQ0Inm6y8hQceaMSQwPJ3+DODYBJjboZE44djVArw/poI/iVC1YZSDzGrONShAGXfGIeaqeIk/AcSmqUDRUKWeeZTU2yanMLfHze9jBgNr0AmSKPQUXI8XfLBh8v8rlHbFe0yoA4M3jsGyLfCtBc48lICb4VAN8KWP2xSoJ5PWA1buhIFMx/EIbGtwLAXquJc34TnsktMIczFoO9L3imFbojccQy3wqAaY3atxto+BBBzYoCUxrrlxoQaa6xfucKG7B1LFrvHfPCVzDl2npRIwpKTUcjBZl6W25u2f6wrHRyY6NwGS5JURStMqBdToAdb3fm5LQtNzvR1JR3OEk50qYJc2IqLt5btTWBNdRDBYNxoTaHj6E5PmkNouTMihnHXkw7F1BOBm0k/l7m5DQcyzvQ0/Ooeb2AxjcBuLYUgu0MoRYDW1d8MLo7wRzOhHUr2f5xSyZTsiajI3Vop52Ez3fs30W0NNs2tazw+XIac1AIzDBiiWoIqWZFqwyoF2PlM2Kz05cwpzv3ektTFptxr9eaujYUBaLZVZx0OByLtZZ97WBCoPbdJsRi8rcu+fodICXk0jLE/BqY0hARINApsD4ssP5ZD/jgqYqqcGWiTrWDO/OYfoQxmP3tRelGUKfarKQsx6C728CO5IDP99pRPW2Y+SnvsbZxHMwwwJuaoPqKUxkj5cmOc2//vnuSle2YgYLhAnLsA8z5hdifmGHAvGHF7TKH80T/qObVM9Zc4G/ew5yZPfggU9P9/uf3nlvNr6/eWsco1bE4PwjR0Q4oBceOCd/TXbS8CCNyZherPx/C+A99UBdPA1xURSuBvv88c991st9Aa+DbZxm7EXJJVMUMI2mIqn74MveshEfKrJ6NxYUGMpcL5rUsY96PbEs/folT/8Udq0J042z+112e3VLC1wp1qg36wYv89kvsU6quxf1z75j7N6+eAa8pThbdQqm6yoC+fQnm967EhRYejtVe+ndupIzPPwn4108gLw7GNX1yjydtrDX3epN+Ls4MppzMQz15BXN2DubCIviPH0N8Y4USeZ7XQJoHpxW7fgHrP7ye79epKPrji3k3Sc/9+9ezDnkN/bmrCP7ctbz2c5hoaoL6JH28uA6Hwb/KLs+B+vxy8rew/VjvPMZVpDp3s2EuLEI/fJnXusRe+valooZ0H+zYnjwD/OsnBZsMrFiOFVpo9J/C/M/2oO0f3rGrPEXhejYJM8WkR23/w3cwy6U7I0/s22fY+sHHkI7TaHq+CfVsLG2stQoE4j7Xn4zCeDMTN8ERMwyYn12G+FHyed1jeQhwDfoRw8b5g7e8qJdBfv/4D6dq1vX3v4PM8rx0/YsHtuyTNdZj9YoHbV/bsjnwnzyBsnkg5dFzl9iDu90wPx62LaFVMofvKezOU8gTFsVVaY7VMmBOz6Hzn5y8Jrbo+V4YPd2x/zOXC8u/9onVTHnCKwIAwK5dQON3c2j6P59Dvx63/pjpQjv0OX84lhBapU0Txl3rLWr8v7oNfvH8wfJ1dVbyJ63h+OYFRFgBGhj/pVp8+Cu12OnVEP/pMlau2DPw7KTij8YgV1dzXElAf3oF+val7LsKtLYlesGcmkXnP05/fTOHM24QILs6krL1Q9+6bE0JPHwmbVKwnOXwXdnNSxCNDfbtu0KpUAji21cF3cfhe8r+b2gM9sdNvU2K53hJh5TMnLEsB3x0GHgzUdDpg42XE4AQUIGDJh3GGKK1Bdtl8nL0nwKkiu/Xtwn/MAsZ2IWORqwbX1d/TqmXj4ZVcY8H6vIQpv5CLeo/aAz8X0H4zzXAvHILri0F7/gWxLtZSACbf+UqInUM20MKzc8ZoIHQX9rC3z39B/j1n/2rNn/TkyWvcDUlrSRSQNGSYRl9vYDSMGdmM17f2ozCeDsLdXUE+ukY+MQsVIqpYY2xachQGHx2EbpEIcL8/SzFw2cp1/NVDA2A7QStDIR57kMtLpdkzJadzx6juwuyrQk8HE163zW6uwCnA2phCTg3UDYJ246fgZALiNN9kO/Gj7+pdT9kgeOkk2VnU5EoOr8J2vI2lS29EwBkYSZKOvwddSQKvpX9LHHizCDUxDT0tWEYq36Y45PQURPG8jaaX3ngmQ/B2AjCayoop0C03oGtC41oiJoQvmYEujk8CxqObQ7XtoTDLxF40Ihf3Po19HXn+FZMAFj5A8SZQbCt7aLkEdCBHK4FrSFX12DUemFqlTb74X5OAOX3Q7Q0Q/R0gkXNjKGXdipEXgKyxx+A3j3ew7RU/e583Q9p0/1YBwIQG0bKaC4d3AUiUWjThFj3p82yW0zHrgwwzoB8QqqSKMRbcla0gvPDIpL9dMwwwFuaIZeWbd2lTDFmwW4qGMztAtv7LVWNAe0wwN1usFovzPFJ1O7PdXBuCPzlOBAIwDvYj8CwD9rtQKTVi3CTRtePdsBNL5ybJlyLAfRuOLA94cX8SBfwZ+3/jlXBpmssG/mcm+bkdG4rcAFdxO9ECoALRH/qKhx/8tCqFOZwj9yfhjmXVoRCsvPZIze3gCwqxXbv97iOHU2gTbNk84FztzvnSU+415sYRsI4zN7k/ZzM5YLqqZ6kJPLlGyu98VfPIN+8B6v1QnfEf3/55n1sGmZzfBLu/+8x+FYAplfArFMQ72bR9HQdNe+WwRaWwYNRSCdD/x9l30JB4smXb050dkF+JDeBXFmBejEWN0iVFN/R3yUXzGFg+qcdYCL3sDzmdEJW0X31JLAttDCXqXdt2+dAL1Z+NvvBJswwoC6dhmg4Mk2rkinnpVaBQNWFHx0+RnJ1zUoYlYboaMf0D3qxcdbA6X8WgdoJQL56C+1xY/Onz2L1oya0/C+PwV9PFqH01ceujIBJY61zjb/mIrHPlzGYV4YoTXW5OebvosNhnP7bd3OvpDIGFQpnld+hGM+VUjy7ypFtlQHz88tFP6jy9Ts0/27283qbn10Gf/KW+g0z+fZZTsdIb/vR9iiMtkch8B8/TshRvutjmP6Na3j/j2iUsN24243Zv3nNlkFX6pNLEPUHFWXR1AR9O8d56W9cgHG0tU5rKxdBBUTqVJQS/S5GRztwI/OkZswwYOaZQyJrjJXk2VWObKsMiC8fnbhmTKOjHexmjje7E4JfPl+05ElyexvGnz6E+NFjyO9dS8g46AgAHd+F0fu7J+PN0OjrBbs6UupiJNCfjEK0NMf9TYVC6Pq7d20Z/Mq/fhIXPSA3NsC+eZJ02ZTH6N7zsukHzsTo7kq4/vWnVyj0sED4lQtxyd7SEfX1kLcuQnyZPK+JbbQ+kc+uQqiq6pBx9yXU4VAWxmDWOsBvj4LdfWr//rq7oFobEkJHtv/6LTQ+28zY/H4c+tV7mCr1A0KMnAPbDtg7gEVrrFxxo+u+A9v/2jXUjwfQdG8RrjOtUAbD2sjJSEtszsyDzS1kXrDI+P3XkGY08YMSJGsp12OUC3N+AWw5PsKF33uV/BiTY9Mv3lr3JK3AVteR7qyVfj/Ed6/SLkPsVXHpiPnF86lr9heG4t5a5eo6XG8XoZ2FOQxydQ0YT3zYNv9kBpiaS7KGfbRppm3+09PzUCv2h/o1TJrQpommr6exfqEWa7c7UHPvAzwvF6BOyuBxJcvuTSH2Fl4uWdrK6RhxAXY9j5YcrRO6tHQ0Uj7HuMLE7klJjnviwlksUyJGZ4c1VXuFqbzKwNomdCh5sgyzwQUmDr6yjkYgl1fh/GBv2GBs++Fw0olhzNm53CeMsZny+2MJNnhdHSJ//oYt2617OA8diWD+F/sh3YB3IQpWXwu5uISun1Cyl5wxBnFuCGJ9u2SJesqeVhDLqUO5SPXhbjfE0EBBtq0DQWCztPfvQqi4bgJzYTG3FbQCqvwmyxiDcthTL9zvdpAuoG5Owj2xCnAObZoF6YqpeIwj3N0A48tH5fnGygWMTmsKYHN+oTRl1Lqs4rVJaqK+HhCi8IO4Obf+FYCdWXfLScW1DKRj7ESgj2SZYk4nZFdLiUpUHuT2Ntz/zz1bt9n59++g7qk1kGw/w9zhkeokew5/xAr1TBMxIOrTf14oTAjIrhbrGmJVdTsheWBNDUBLY8H3o4LBwuewYOxYeRrKTVVdvfrBi4R+KBUMFjWPQDWFsJgTU7GKADMMREcptDBnSkLff47oxQEwZ+oBmNHLg2k/LxQdjUDffw59/zmFDpKMzKkZyA+T5X8fZCxjGbnLBXm5cu5pVVUZKAfy9qWqfEPWppn1vPckEf/6SdqJYzJ9Tki5MDraoa8Nl7oYaYnmJqiP0g9KVaFQytDbk6g6KgNcQH4/dWIWZhjW54eEf+Ymdn/hI/uL8tXjiu1zqhTlkmeAe72Q37+W9tw9yYTPB317NPOCpKKYC4spM74WHWPW9XUkC6NcWwe7U11jnMq8rcYmSsL4+gV0isFN2jStzw/9zf2nz6zPilC8cmUM9kO7HJCv35W6KEVVLjH0KhCA8bWVsjXVuXuSydVV8M2tqr7GSIlpbd37qYurSloGgIwxqwnxxuFwZTW7MgZ242JOb5hqfhG6wPkQylIZxdDraKRs462PrYxjyUn1yPccZC5XfvktylTVVAaqntYQixs5hX6pUCjp9MfizCC4x2Nn6YjNRGND0dJR50O0tsDo7Sl1MQjJm46aEEubpS6Gbaq6MsA9npynQD7JzNkqfMvPgtHTXZF98oRUGtHUBNHUlPN6RmdHwpwpx6ZkRd1Tq7oywDw1QGvuJ1a1k+/Gk7YYnFSyo6niYuTl5lYsrLMcydW14iQK4qIqo3cqFWuoA2vM/feUHS1gjvIYIsdcrrJsWa2sO2CO5Ooa5Ms3pS5GxbC95l0k+sGLso+RP6nHttR4jRvmSGHS0pI8ZRHDn4o5OZ1XJVc/flk2LzCiqwOsv/y6yKq6MkDswwwD5mcXS12MimV+ehHc7S51MU4cFQhQGuwycxLyDBSSOTEF+eptqYuRgOlKjFkihBBCSNaoZYAQQgipclQZIIQQQqocVQYIIYSQKkeVAUIIIaTKUWWAEEIIqXJUGSCEEEKqHFUGCCGEkCpHlQFCCCGkylFlgBBCCKly/z/WkTfs8t6rVwAAAABJRU5ErkJggg==\n"
+          },
+          "metadata": {}
+        }
+      ],
+      "source": [
+        "# This is not necessary, but is cool to see\n",
+        "# Converting 1000 event blocks into frames with tonic.transforms.ToFrame\n",
+        "sensor_size = tonic.datasets.DVSGesture.sensor_size\n",
+        "frame_transform = tonic.transforms.ToFrame(sensor_size=sensor_size, event_count=1000)\n",
+        "\n",
+        "# Applying the transform to the raw events array\n",
+        "frames = frame_transform(events)\n",
+        "\n",
+        "# Shape of the frames object represents (num frames, polarity, width, height)\n",
+        "print(frames.shape)\n",
+        "\n",
+        "# Plot some frames\n",
+        "fig, ax = plt.subplots(1, 3)\n",
+        "ax[0].axis('off')\n",
+        "ax[1].axis('off')\n",
+        "ax[2].axis('off')\n",
+        "ax[0].imshow(frames[0][0])\n",
+        "ax[1].imshow(frames[10][0])\n",
+        "ax[2].imshow(frames[20][0])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "F2zffSFnmJaz"
+      },
+      "source": [
+        "# 2. Transforming the Raw Data"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "EroKAOeGmXzx"
+      },
+      "source": [
+        "## 2.1 Transforms\n",
+        "A neural network takes in a tensor as input, so the event array must be transformed into a suitable format.\n",
+        "\\\n",
+        "The following code bins events into 1ms groups and denoises each group, or frame. These transforms are then applied to the train and test sets before being passed into dataloaders, which efficiently preprocess the data before passing it into the network."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 545,
+          "referenced_widgets": [
+            "c7222ad280f149c0bfabb3bd9123d134",
+            "6d73acd3f31e410b9ffa05613e9382c0",
+            "0a9dcf16760442a5a9287b05c5219fb8",
+            "317bda85de40423c92713d730d0c1a34",
+            "8b6ceadcc29e4c19b0f8b80900bbbccc",
+            "28b9dc4e8f54454cbeeaefabefb7b95b",
+            "a7ed5a6af9584f648458fed77457a9c0",
+            "3e12fd4fd10e4fce90a6a450a2743a4f",
+            "498f640d575f4be2b4f28e36f3496bf2",
+            "c40d412efb10481ebbab0ebce8a2d5c1",
+            "cc48248f20ce4b71bb7954fd4bd09342"
+          ]
+        },
+        "id": "RPRswuWZ2tr4",
+        "outputId": "db3e7c41-1ef6-4533-92a7-9a982a690e81"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Shape of frames object:  (25, 2, 128, 128)\n",
+            "Downloading https://s3-eu-west-1.amazonaws.com/pfigshare-u-files/38020584/ibmGestureTest.tar.gz?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAIYCQYOYV5JSSROOA/20231102/eu-west-1/s3/aws4_request&X-Amz-Date=20231102T213032Z&X-Amz-Expires=10&X-Amz-SignedHeaders=host&X-Amz-Signature=cf4be39f5df82cca543009978dec3e12d1aa67930ec4f0d713dc174e4c2d50ec to ./data/DVSGesture/ibmGestureTest.tar.gz\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "  0%|          | 0/691455012 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "c7222ad280f149c0bfabb3bd9123d134"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Extracting ./data/DVSGesture/ibmGestureTest.tar.gz to ./data/DVSGesture\n",
+            "1077\n",
+            "264\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ],
+      "source": [
+        "size = tonic.datasets.DVSGesture.sensor_size\n",
+        "\n",
+        "# Denoise transform removes outlier events with inactive surrounding pixels for 10ms\n",
+        "denoise_transform = transforms.Denoise(filter_time=10000)\n",
+        "\n",
+        "# ToFrame transform bins events into 25 clusters of frames\n",
+        "frame_transform = transforms.ToFrame(sensor_size=size, n_time_bins=25)\n",
+        "\n",
+        "# Chain the transforms\n",
+        "all_transform = transforms.Compose([denoise_transform, frame_transform])\n",
+        "\n",
+        "# View the transformed data\n",
+        "tf_frames = all_transform(events)\n",
+        "print(\"Shape of frames object: \", tf_frames.shape)\n",
+        "plt.axis('off')\n",
+        "plt.imshow(tf_frames[0][0])\n",
+        "\n",
+        "train_set = tonic.datasets.DVSGesture(save_to='./data', transform=all_transform, train=True)\n",
+        "test_set = tonic.datasets.DVSGesture(save_to='./data', transform=all_transform, train=False)\n",
+        "print(len(train_set))\n",
+        "print(len(test_set))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "elh6NQrnpwFl"
+      },
+      "source": [
+        "## 2.2 Caching and Dataloaders\n",
+        "- To optimize and expedite the training process, caching and dataloaders are helpful.\n",
+        "- A dataloader efficiently prepares data for iteration through shuffling, batch size processing, etc.\n",
+        "- Caching the dataset makes iterating through the dataloader much faster, as samples are read from the cache rather than from the disk."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "LIZvmu6RgUuT",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "0f0d3787-55d8-455c-f5a5-2e9746a3f4b7"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Shape of sample object:  torch.Size([25, 64, 2, 128, 128])\n"
+          ]
+        }
+      ],
+      "source": [
+        "cached_trainset = tonic.DiskCachedDataset(train_set, cache_path='./cache/dvsgesture/train')\n",
+        "cached_testset = tonic.DiskCachedDataset(test_set, cache_path='./cache/dvsgesture/test')\n",
+        "\n",
+        "# Create DataLoaders\n",
+        "train_loader = torch.utils.data.DataLoader(cached_trainset, batch_size=64, shuffle=True, drop_last=True, collate_fn=tonic.collation.PadTensors(batch_first=False))\n",
+        "test_loader = torch.utils.data.DataLoader(cached_testset, batch_size=32, shuffle=True, drop_last=True, collate_fn=tonic.collation.PadTensors(batch_first=False))\n",
+        "\n",
+        "# Visualize shape of sample in dataloader (similar to frames object above, but 2nd element is batch size)\n",
+        "for sample in iter(train_loader):\n",
+        "  print(\"Shape of sample object: \", sample[0].shape)\n",
+        "  break"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b08XtlkJeUAO"
+      },
+      "source": [
+        "# 3. Building the Network"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ilBQ1RCCW5oZ"
+      },
+      "source": [
+        "The network will be fairly simple; 2 convolution layers with 5 filters each, followed by a fully connected layer."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cMT7KY2d301F"
+      },
+      "outputs": [],
+      "source": [
+        "device = torch.device(\"cuda\") if torch.cuda.is_available() else torch.device(\"cpu\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7TBtMTdLfy-P"
+      },
+      "outputs": [],
+      "source": [
+        "# Network parameters\n",
+        "gradient = surrogate.fast_sigmoid(slope=25)\n",
+        "beta = 0.5\n",
+        "\n",
+        "# Initializing the network\n",
+        "net = nn.Sequential(nn.Conv2d(2, 12, 5),\n",
+        "                    nn.MaxPool2d(2),\n",
+        "                    snn.Leaky(beta=beta, spike_grad=gradient, init_hidden=True),\n",
+        "                    nn.Conv2d(12, 32, 5),\n",
+        "                    nn.MaxPool2d(2),\n",
+        "                    snn.Leaky(beta=beta, spike_grad=gradient, init_hidden=True),\n",
+        "                    nn.Flatten(),\n",
+        "                    nn.Linear(800, 11),\n",
+        "                    snn.Leaky(beta=beta, spike_grad=gradient, init_hidden=True, output=True)\n",
+        "                    ).to(device)\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## 3.1 Forward Propagation\n",
+        "\n",
+        "Since the samples can be interpreted as a short video of 25 frames, a custom forward propagation function helps feed each frame, or cluster of events, into the network one at a time.\n",
+        "\n",
+        "- In this case, data.size(0) == 25.\n",
+        "\n",
+        "A single forward pass returns a tensor representing the spiking activity from one sample (or batch if batch size > 1).\n",
+        "\n",
+        "This should be of size (frame count, batch size, num classes), or (25, 64, 11)."
+      ],
+      "metadata": {
+        "id": "kwOY2WJ0da_z"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Defining a forward propagation function\n",
+        "def forward_pass(net, data):\n",
+        "  spk_rec = []\n",
+        "  snn.utils.reset(net)\n",
+        "  for step in range(data.size(0)):\n",
+        "      spk_out, mem_out = net(data[step])\n",
+        "      spk_rec.append(spk_out)\n",
+        "  return torch.stack(spk_rec)"
+      ],
+      "metadata": {
+        "id": "rOoGQW6Wdbwr"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "CpiF5fUl3d-B"
+      },
+      "outputs": [],
+      "source": [
+        "# some hyperparameters\n",
+        "optimizer = torch.optim.Adam(net.parameters(), lr=0.002, betas=(0.9, 0.999))\n",
+        "loss_fn = SF.mse_count_loss(correct_rate=0.8, incorrect_rate=0.2)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "C0adurQH-bw3"
+      },
+      "source": [
+        "# 4. Training"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Note: Dataloading will be slow for the first (num samples/batch size) training steps due to first time loading into the cache"
+      ],
+      "metadata": {
+        "id": "UdgXx_9VXp74"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "_2T7HO4m3eXL",
+        "outputId": "49505b99-6af7-47b7-93d1-011ec4d5d790"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Epoch 0, Iteration 0 \n",
+            "Train Loss: 2.36\n",
+            "Train Accuracy: 10.94%\n",
+            "\n",
+            "========== Test Set Accuracy: 8.98% ==========\n",
+            "\n",
+            "Epoch 1, Iteration 0 \n",
+            "Train Loss: 1.28\n",
+            "Train Accuracy: 29.69%\n",
+            "\n",
+            "========== Test Set Accuracy: 35.16% ==========\n",
+            "\n",
+            "Epoch 2, Iteration 0 \n",
+            "Train Loss: 0.93\n",
+            "Train Accuracy: 65.62%\n",
+            "\n",
+            "========== Test Set Accuracy: 58.20% ==========\n",
+            "\n",
+            "Epoch 3, Iteration 0 \n",
+            "Train Loss: 0.72\n",
+            "Train Accuracy: 50.00%\n",
+            "\n",
+            "========== Test Set Accuracy: 60.16% ==========\n",
+            "\n",
+            "Epoch 4, Iteration 0 \n",
+            "Train Loss: 0.62\n",
+            "Train Accuracy: 57.81%\n",
+            "\n",
+            "========== Test Set Accuracy: 61.33% ==========\n",
+            "\n",
+            "Epoch 5, Iteration 0 \n",
+            "Train Loss: 0.57\n",
+            "Train Accuracy: 70.31%\n",
+            "\n",
+            "========== Test Set Accuracy: 65.23% ==========\n",
+            "\n",
+            "Epoch 6, Iteration 0 \n",
+            "Train Loss: 0.45\n",
+            "Train Accuracy: 71.88%\n",
+            "\n",
+            "========== Test Set Accuracy: 64.45% ==========\n",
+            "\n",
+            "Epoch 7, Iteration 0 \n",
+            "Train Loss: 0.45\n",
+            "Train Accuracy: 71.88%\n",
+            "\n",
+            "========== Test Set Accuracy: 64.84% ==========\n",
+            "\n",
+            "Epoch 8, Iteration 0 \n",
+            "Train Loss: 0.38\n",
+            "Train Accuracy: 84.38%\n",
+            "\n",
+            "========== Test Set Accuracy: 66.80% ==========\n",
+            "\n",
+            "Epoch 9, Iteration 0 \n",
+            "Train Loss: 0.46\n",
+            "Train Accuracy: 70.31%\n",
+            "\n",
+            "========== Test Set Accuracy: 64.84% ==========\n",
+            "\n",
+            "Epoch 10, Iteration 0 \n",
+            "Train Loss: 0.40\n",
+            "Train Accuracy: 73.44%\n",
+            "\n",
+            "========== Test Set Accuracy: 74.22% ==========\n",
+            "\n",
+            "Epoch 11, Iteration 0 \n",
+            "Train Loss: 0.44\n",
+            "Train Accuracy: 79.69%\n",
+            "\n",
+            "========== Test Set Accuracy: 73.83% ==========\n",
+            "\n",
+            "Epoch 12, Iteration 0 \n",
+            "Train Loss: 0.36\n",
+            "Train Accuracy: 81.25%\n",
+            "\n",
+            "========== Test Set Accuracy: 69.92% ==========\n",
+            "\n",
+            "Epoch 13, Iteration 0 \n",
+            "Train Loss: 0.39\n",
+            "Train Accuracy: 81.25%\n",
+            "\n",
+            "========== Test Set Accuracy: 72.66% ==========\n",
+            "\n",
+            "Epoch 14, Iteration 0 \n",
+            "Train Loss: 0.38\n",
+            "Train Accuracy: 82.81%\n",
+            "\n",
+            "========== Test Set Accuracy: 73.83% ==========\n",
+            "\n",
+            "Epoch 15, Iteration 0 \n",
+            "Train Loss: 0.33\n",
+            "Train Accuracy: 90.62%\n",
+            "\n",
+            "========== Test Set Accuracy: 78.91% ==========\n",
+            "\n",
+            "Epoch 16, Iteration 0 \n",
+            "Train Loss: 0.34\n",
+            "Train Accuracy: 89.06%\n",
+            "\n",
+            "========== Test Set Accuracy: 78.52% ==========\n",
+            "\n",
+            "Epoch 17, Iteration 0 \n",
+            "Train Loss: 0.28\n",
+            "Train Accuracy: 89.06%\n",
+            "\n",
+            "========== Test Set Accuracy: 76.95% ==========\n",
+            "\n",
+            "Epoch 18, Iteration 0 \n",
+            "Train Loss: 0.33\n",
+            "Train Accuracy: 92.19%\n",
+            "\n",
+            "========== Test Set Accuracy: 82.42% ==========\n",
+            "\n",
+            "Epoch 19, Iteration 0 \n",
+            "Train Loss: 0.31\n",
+            "Train Accuracy: 90.62%\n",
+            "\n",
+            "========== Test Set Accuracy: 82.42% ==========\n",
+            "\n",
+            "Epoch 20, Iteration 0 \n",
+            "Train Loss: 0.29\n",
+            "Train Accuracy: 93.75%\n",
+            "\n",
+            "========== Test Set Accuracy: 79.69% ==========\n",
+            "\n",
+            "Epoch 21, Iteration 0 \n",
+            "Train Loss: 0.31\n",
+            "Train Accuracy: 90.62%\n",
+            "\n",
+            "========== Test Set Accuracy: 84.38% ==========\n",
+            "\n",
+            "Epoch 22, Iteration 0 \n",
+            "Train Loss: 0.29\n",
+            "Train Accuracy: 92.19%\n",
+            "\n",
+            "========== Test Set Accuracy: 81.64% ==========\n",
+            "\n",
+            "Epoch 23, Iteration 0 \n",
+            "Train Loss: 0.31\n",
+            "Train Accuracy: 90.62%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.55% ==========\n",
+            "\n",
+            "Epoch 24, Iteration 0 \n",
+            "Train Loss: 0.26\n",
+            "Train Accuracy: 92.19%\n",
+            "\n",
+            "========== Test Set Accuracy: 84.77% ==========\n",
+            "\n",
+            "Epoch 25, Iteration 0 \n",
+            "Train Loss: 0.21\n",
+            "Train Accuracy: 92.19%\n",
+            "\n",
+            "========== Test Set Accuracy: 86.72% ==========\n",
+            "\n",
+            "Epoch 26, Iteration 0 \n",
+            "Train Loss: 0.23\n",
+            "Train Accuracy: 96.88%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.94% ==========\n",
+            "\n",
+            "Epoch 27, Iteration 0 \n",
+            "Train Loss: 0.20\n",
+            "Train Accuracy: 95.31%\n",
+            "\n",
+            "========== Test Set Accuracy: 83.20% ==========\n",
+            "\n",
+            "Epoch 28, Iteration 0 \n",
+            "Train Loss: 0.27\n",
+            "Train Accuracy: 92.19%\n",
+            "\n",
+            "========== Test Set Accuracy: 87.11% ==========\n",
+            "\n",
+            "Epoch 29, Iteration 0 \n",
+            "Train Loss: 0.28\n",
+            "Train Accuracy: 93.75%\n",
+            "\n",
+            "========== Test Set Accuracy: 83.98% ==========\n",
+            "\n",
+            "Epoch 30, Iteration 0 \n",
+            "Train Loss: 0.22\n",
+            "Train Accuracy: 93.75%\n",
+            "\n",
+            "========== Test Set Accuracy: 86.33% ==========\n",
+            "\n",
+            "Epoch 31, Iteration 0 \n",
+            "Train Loss: 0.16\n",
+            "Train Accuracy: 100.00%\n",
+            "\n",
+            "========== Test Set Accuracy: 83.59% ==========\n",
+            "\n",
+            "Epoch 32, Iteration 0 \n",
+            "Train Loss: 0.21\n",
+            "Train Accuracy: 96.88%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.94% ==========\n",
+            "\n",
+            "Epoch 33, Iteration 0 \n",
+            "Train Loss: 0.23\n",
+            "Train Accuracy: 95.31%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.55% ==========\n",
+            "\n",
+            "Epoch 34, Iteration 0 \n",
+            "Train Loss: 0.22\n",
+            "Train Accuracy: 96.88%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.16% ==========\n",
+            "\n",
+            "Epoch 35, Iteration 0 \n",
+            "Train Loss: 0.19\n",
+            "Train Accuracy: 96.88%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.94% ==========\n",
+            "\n",
+            "Epoch 36, Iteration 0 \n",
+            "Train Loss: 0.15\n",
+            "Train Accuracy: 98.44%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.16% ==========\n",
+            "\n",
+            "Epoch 37, Iteration 0 \n",
+            "Train Loss: 0.18\n",
+            "Train Accuracy: 98.44%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.94% ==========\n",
+            "\n",
+            "Epoch 38, Iteration 0 \n",
+            "Train Loss: 0.18\n",
+            "Train Accuracy: 95.31%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.94% ==========\n",
+            "\n",
+            "Epoch 39, Iteration 0 \n",
+            "Train Loss: 0.17\n",
+            "Train Accuracy: 98.44%\n",
+            "\n",
+            "========== Test Set Accuracy: 86.72% ==========\n",
+            "\n",
+            "Epoch 40, Iteration 0 \n",
+            "Train Loss: 0.15\n",
+            "Train Accuracy: 95.31%\n",
+            "\n",
+            "========== Test Set Accuracy: 87.11% ==========\n",
+            "\n",
+            "Epoch 41, Iteration 0 \n",
+            "Train Loss: 0.16\n",
+            "Train Accuracy: 96.88%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.55% ==========\n",
+            "\n",
+            "Epoch 42, Iteration 0 \n",
+            "Train Loss: 0.23\n",
+            "Train Accuracy: 96.88%\n",
+            "\n",
+            "========== Test Set Accuracy: 86.72% ==========\n",
+            "\n",
+            "Epoch 43, Iteration 0 \n",
+            "Train Loss: 0.18\n",
+            "Train Accuracy: 95.31%\n",
+            "\n",
+            "========== Test Set Accuracy: 83.98% ==========\n",
+            "\n",
+            "Epoch 44, Iteration 0 \n",
+            "Train Loss: 0.19\n",
+            "Train Accuracy: 95.31%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.55% ==========\n",
+            "\n",
+            "Epoch 45, Iteration 0 \n",
+            "Train Loss: 0.16\n",
+            "Train Accuracy: 98.44%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.55% ==========\n",
+            "\n",
+            "Epoch 46, Iteration 0 \n",
+            "Train Loss: 0.16\n",
+            "Train Accuracy: 98.44%\n",
+            "\n",
+            "========== Test Set Accuracy: 87.11% ==========\n",
+            "\n",
+            "Epoch 47, Iteration 0 \n",
+            "Train Loss: 0.14\n",
+            "Train Accuracy: 98.44%\n",
+            "\n",
+            "========== Test Set Accuracy: 86.33% ==========\n",
+            "\n",
+            "Epoch 48, Iteration 0 \n",
+            "Train Loss: 0.14\n",
+            "Train Accuracy: 98.44%\n",
+            "\n",
+            "========== Test Set Accuracy: 88.28% ==========\n",
+            "\n",
+            "Epoch 49, Iteration 0 \n",
+            "Train Loss: 0.19\n",
+            "Train Accuracy: 96.88%\n",
+            "\n",
+            "========== Test Set Accuracy: 85.94% ==========\n",
+            "\n"
+          ]
+        }
+      ],
+      "source": [
+        "# 50 epochs; counter just used for test set validation\n",
+        "num_epochs = 50\n",
+        "counter = 0\n",
+        "\n",
+        "loss_hist = []\n",
+        "acc_hist = []\n",
+        "test_acc_hist = []\n",
+        "\n",
+        "# Training loop\n",
+        "for epoch in range(num_epochs):\n",
+        "    for i, (data, targets) in enumerate(iter(train_loader)):\n",
+        "        # Downsampling image from (128 x 128) to (32 x 32)\n",
+        "        data = nn.functional.interpolate(data, size=(2, 32, 32))\n",
+        "        data = data.to(device)\n",
+        "        targets = targets.to(device)\n",
+        "\n",
+        "        net.train()\n",
+        "        # propagating one batch through the network and evaluating loss\n",
+        "        spk_rec = forward_pass(net, data)\n",
+        "        loss_val = loss_fn(spk_rec, targets)\n",
+        "\n",
+        "        # Gradient calculation + weight update\n",
+        "        optimizer.zero_grad()\n",
+        "        loss_val.backward()\n",
+        "        optimizer.step()\n",
+        "\n",
+        "        # Store loss history for future plotting\n",
+        "        loss_hist.append(loss_val.item())\n",
+        "\n",
+        "        acc = SF.accuracy_rate(spk_rec, targets)\n",
+        "        acc_hist.append(acc)\n",
+        "\n",
+        "        # print metrics every so often\n",
+        "        if counter % 16 == 0:\n",
+        "          print(f\"Epoch {epoch}, Iteration {i} \\nTrain Loss: {loss_val.item():.2f}\")\n",
+        "          print(f\"Train Accuracy: {acc * 100:.2f}%\\n\")\n",
+        "\n",
+        "          correct = 0\n",
+        "          total = 0\n",
+        "\n",
+        "          for i, (data, targets) in enumerate(iter(test_loader)):\n",
+        "            data = nn.functional.interpolate(data, size=(2, 32, 32))\n",
+        "            data = data.to(device)\n",
+        "            targets = targets.to(device)\n",
+        "            spk_rec = forward_pass(net, data)\n",
+        "            correct += SF.accuracy_rate(spk_rec, targets) * spk_rec.size(1)\n",
+        "            total += spk_rec.size(1)\n",
+        "\n",
+        "          test_acc = (correct/total) * 100\n",
+        "          test_acc_hist.append(test_acc)\n",
+        "          print(f\"========== Test Set Accuracy: {test_acc:.2f}% ==========\\n\")\n",
+        "\n",
+        "        counter += 1"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# 5. Results"
+      ],
+      "metadata": {
+        "id": "iPImE6gMmgza"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "S0_GFlUe-vax"
+      },
+      "source": [
+        "Plotting the accuracy on the training set, loss, and test set accuracy can help visualize how well the model is performing.\n",
+        "As we can see from the plots below, loss is converging and train/test accuracy is plateauing accordingly."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "JnYIf5CKKYzq",
+        "outputId": "89e082d0-6bb1-4cce-e236-170094889ef6"
+      },
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 1800x400 with 3 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ],
+      "source": [
+        "fig, axes = plt.subplots(1, 3, figsize=(18,4))\n",
+        "\n",
+        "# Plot Train Accuracy\n",
+        "axes[0].plot(acc_hist)\n",
+        "axes[0].set_title(\"Train Set Accuracy\")\n",
+        "axes[0].set_xlabel(\"Iteration\")\n",
+        "axes[0].set_ylabel(\"Accuracy\")\n",
+        "\n",
+        "# Plot Test Accuracy\n",
+        "axes[1].plot(test_acc_hist)\n",
+        "axes[1].set_title(\"Test Set Accuracy\")\n",
+        "axes[1].set_xlabel(\"Iteration\")\n",
+        "axes[1].set_ylabel(\"Accuracy\")\n",
+        "\n",
+        "# Plot Training Loss\n",
+        "axes[2].plot(loss_hist)\n",
+        "axes[2].set_title(\"Loss History\")\n",
+        "axes[2].set_xlabel(\"Iteration\")\n",
+        "axes[2].set_ylabel(\"Loss\")\n",
+        "\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Nj7skndR0I8m",
+        "outputId": "2ea12ea2-6241-4f69-db6d-c3c794f75fa0"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Test Set Accuracy:  85.546875 %\n"
+          ]
+        }
+      ],
+      "source": [
+        "# Evaluate Test Set Accuracy\n",
+        "correct = 0\n",
+        "total = 0\n",
+        "\n",
+        "for i, (data, targets) in enumerate(iter(test_loader)):\n",
+        "  data = nn.functional.interpolate(data, size=(2, 32, 32))\n",
+        "  data = data.to(device)\n",
+        "  targets = targets.to(device)\n",
+        "  spk_rec = forward_pass(net, data)\n",
+        "  correct += SF.accuracy_rate(spk_rec, targets) * spk_rec.size(1)\n",
+        "  total += spk_rec.size(1)\n",
+        "\n",
+        "print(\"Test Set Accuracy: \", (correct/total) * 100, \"%\")"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "provenance": [],
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "3974416247f7451bb2bb82bdb83138fc": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_0f504b5f4ad74595ae37ebf795d46514",
+              "IPY_MODEL_5fd4888429c342f2b1493c1689e6fc6b",
+              "IPY_MODEL_b4a14c5ad41441a7bbb76aa96f72778b"
+            ],
+            "layout": "IPY_MODEL_766a82612ccc442fb46264421109c713"
+          }
+        },
+        "0f504b5f4ad74595ae37ebf795d46514": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_92e3de6e58a24ea1a870432e8d907504",
+            "placeholder": "​",
+            "style": "IPY_MODEL_c0c3f6d088534ceb9d70af69d7e08392",
+            "value": ""
+          }
+        },
+        "5fd4888429c342f2b1493c1689e6fc6b": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_0b28db65ac3743c2abb7ddd085fbed21",
+            "max": 2443675558,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_1071d5988c9b4cf7b846b51db4f66a32",
+            "value": 2443675558
+          }
+        },
+        "b4a14c5ad41441a7bbb76aa96f72778b": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_daa45045ae794990867fce4f0be28245",
+            "placeholder": "​",
+            "style": "IPY_MODEL_c710df2cd11e4ec2b1c9da6585c76016",
+            "value": " 2443675648/? [02:26&lt;00:00, 18174892.03it/s]"
+          }
+        },
+        "766a82612ccc442fb46264421109c713": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "92e3de6e58a24ea1a870432e8d907504": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "c0c3f6d088534ceb9d70af69d7e08392": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "0b28db65ac3743c2abb7ddd085fbed21": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "1071d5988c9b4cf7b846b51db4f66a32": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "daa45045ae794990867fce4f0be28245": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "c710df2cd11e4ec2b1c9da6585c76016": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "c7222ad280f149c0bfabb3bd9123d134": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_6d73acd3f31e410b9ffa05613e9382c0",
+              "IPY_MODEL_0a9dcf16760442a5a9287b05c5219fb8",
+              "IPY_MODEL_317bda85de40423c92713d730d0c1a34"
+            ],
+            "layout": "IPY_MODEL_8b6ceadcc29e4c19b0f8b80900bbbccc"
+          }
+        },
+        "6d73acd3f31e410b9ffa05613e9382c0": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_28b9dc4e8f54454cbeeaefabefb7b95b",
+            "placeholder": "​",
+            "style": "IPY_MODEL_a7ed5a6af9584f648458fed77457a9c0",
+            "value": ""
+          }
+        },
+        "0a9dcf16760442a5a9287b05c5219fb8": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_3e12fd4fd10e4fce90a6a450a2743a4f",
+            "max": 691455012,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_498f640d575f4be2b4f28e36f3496bf2",
+            "value": 691455012
+          }
+        },
+        "317bda85de40423c92713d730d0c1a34": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_c40d412efb10481ebbab0ebce8a2d5c1",
+            "placeholder": "​",
+            "style": "IPY_MODEL_cc48248f20ce4b71bb7954fd4bd09342",
+            "value": " 691456000/? [00:37&lt;00:00, 21086882.42it/s]"
+          }
+        },
+        "8b6ceadcc29e4c19b0f8b80900bbbccc": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "28b9dc4e8f54454cbeeaefabefb7b95b": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "a7ed5a6af9584f648458fed77457a9c0": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "3e12fd4fd10e4fce90a6a450a2743a4f": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "498f640d575f4be2b4f28e36f3496bf2": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "c40d412efb10481ebbab0ebce8a2d5c1": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "cc48248f20ce4b71bb7954fd4bd09342": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        }
+      }
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}
\ No newline at end of file