diff --git a/labml_nn/gan/dcgan.py b/labml_nn/gan/dcgan/__init__.py
similarity index 97%
rename from labml_nn/gan/dcgan.py
rename to labml_nn/gan/dcgan/__init__.py
index 2ca55d02..b2e4620f 100644
--- a/labml_nn/gan/dcgan.py
+++ b/labml_nn/gan/dcgan/__init__.py
@@ -17,7 +17,7 @@ import torch.nn as nn
 from labml import experiment
 from labml.configs import calculate
 from labml_helpers.module import Module
-from labml_nn.gan.simple_mnist_experiment import Configs
+from labml_nn.gan.original.experiment import Configs
 
 
 class Generator(Module):
@@ -107,7 +107,7 @@ calculate(Configs.discriminator, 'cnn', lambda c: Discriminator().to(c.device))
 
 def main():
     conf = Configs()
-    experiment.create(name='mnist_dcgan', comment='test')
+    experiment.create(name='mnist_dcgan')
     experiment.configs(conf,
                        {'discriminator': 'cnn',
                         'generator': 'cnn',
diff --git a/labml_nn/gan/dcgan/experiment.ipynb b/labml_nn/gan/dcgan/experiment.ipynb
new file mode 100644
index 00000000..47907e34
--- /dev/null
+++ b/labml_nn/gan/dcgan/experiment.ipynb
@@ -0,0 +1,286 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+  "colab": {
+   "name": "Cycle GAN",
+   "provenance": [],
+   "collapsed_sections": [],
+   "toc_visible": true
+  },
+  "kernelspec": {
+   "name": "python3",
+   "language": "python",
+   "display_name": "Python 3"
+  },
+  "accelerator": "GPU"
+ },
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "AYV_dMVDxyc2"
+   },
+   "source": [
+    "[![Github](https://img.shields.io/github/stars/lab-ml/nn?style=social)](https://github.com/lab-ml/nn)\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/lab-ml/nn/blob/master/labml_nn/gan/dcgan/experiment.ipynb)\n",
+    "\n",
+    "## DCGAN\n",
+    "\n",
+    "This is an experiment training DCGAN model."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "AahG_i2y5tY9"
+   },
+   "source": [
+    "Install the `labml-nn` package"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "ZCzmCrAIVg0L",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "outputId": "2fe2685f-731c-4c47-854e-a4f00e485281"
+   },
+   "source": [
+    "!pip install labml-nn"
+   ],
+   "execution_count": 1,
+   "outputs": [
+    {
+     "output_type": "stream",
+     "text": [
+      "Collecting labml-nn\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/9d/bb/a7a6f69ab6e21de2398b5f6b0b2bb47b430e4a20ae2c8710c489e02813be/labml_nn-0.4.81-py3-none-any.whl (118kB)\n",
+      "\r\u001B[K     |██▊                             | 10kB 22.6MB/s eta 0:00:01\r\u001B[K     |█████▌                          | 20kB 14.6MB/s eta 0:00:01\r\u001B[K     |████████▎                       | 30kB 12.9MB/s eta 0:00:01\r\u001B[K     |███████████                     | 40kB 12.1MB/s eta 0:00:01\r\u001B[K     |█████████████▉                  | 51kB 8.2MB/s eta 0:00:01\r\u001B[K     |████████████████▋               | 61kB 8.7MB/s eta 0:00:01\r\u001B[K     |███████████████████▍            | 71kB 8.9MB/s eta 0:00:01\r\u001B[K     |██████████████████████▏         | 81kB 9.9MB/s eta 0:00:01\r\u001B[K     |█████████████████████████       | 92kB 8.9MB/s eta 0:00:01\r\u001B[K     |███████████████████████████▊    | 102kB 8.0MB/s eta 0:00:01\r\u001B[K     |██████████████████████████████▌ | 112kB 8.0MB/s eta 0:00:01\r\u001B[K     |████████████████████████████████| 122kB 8.0MB/s \n",
+      "\u001B[?25hRequirement already satisfied: torch in /usr/local/lib/python3.6/dist-packages (from labml-nn) (1.7.0+cu101)\n",
+      "Collecting labml-helpers>=0.4.72\n",
+      "  Downloading https://files.pythonhosted.org/packages/ec/58/2b7dcfde4565134ad97cdfe96ad7070fef95c37be2cbc066b608c9ae5c1d/labml_helpers-0.4.72-py3-none-any.whl\n",
+      "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from labml-nn) (1.19.5)\n",
+      "Collecting labml>=0.4.94\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/99/b2/3a424548d74a88ce565b38f6b7e707e7c2f00bf8c7c575a1c251807e4896/labml-0.4.94-py3-none-any.whl (99kB)\n",
+      "\u001B[K     |████████████████████████████████| 102kB 8.2MB/s \n",
+      "\u001B[?25hCollecting einops\n",
+      "  Downloading https://files.pythonhosted.org/packages/5d/a0/9935e030634bf60ecd572c775f64ace82ceddf2f504a5fd3902438f07090/einops-0.3.0-py2.py3-none-any.whl\n",
+      "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.6/dist-packages (from torch->labml-nn) (3.7.4.3)\n",
+      "Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from torch->labml-nn) (0.16.0)\n",
+      "Requirement already satisfied: dataclasses in /usr/local/lib/python3.6/dist-packages (from torch->labml-nn) (0.8)\n",
+      "Collecting gitpython\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/d7/cb/ec98155c501b68dcb11314c7992cd3df6dce193fd763084338a117967d53/GitPython-3.1.12-py3-none-any.whl (159kB)\n",
+      "\u001B[K     |████████████████████████████████| 163kB 9.9MB/s \n",
+      "\u001B[?25hRequirement already satisfied: pyyaml in /usr/local/lib/python3.6/dist-packages (from labml>=0.4.94->labml-nn) (3.13)\n",
+      "Collecting gitdb<5,>=4.0.1\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/48/11/d1800bca0a3bae820b84b7d813ad1eff15a48a64caea9c823fc8c1b119e8/gitdb-4.0.5-py3-none-any.whl (63kB)\n",
+      "\u001B[K     |████████████████████████████████| 71kB 8.6MB/s \n",
+      "\u001B[?25hCollecting smmap<4,>=3.0.1\n",
+      "  Downloading https://files.pythonhosted.org/packages/d5/1e/6130925131f639b2acde0f7f18b73e33ce082ff2d90783c436b52040af5a/smmap-3.0.5-py2.py3-none-any.whl\n",
+      "Installing collected packages: smmap, gitdb, gitpython, labml, labml-helpers, einops, labml-nn\n",
+      "Successfully installed einops-0.3.0 gitdb-4.0.5 gitpython-3.1.12 labml-0.4.94 labml-helpers-0.4.72 labml-nn-0.4.81 smmap-3.0.5\n"
+     ],
+     "name": "stdout"
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "SE2VUQ6L5zxI"
+   },
+   "source": [
+    "Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "0hJXx_g0wS2C"
+   },
+   "source": [
+    "from labml import experiment\n",
+    "from labml_nn.gan.dcgan import Configs"
+   ],
+   "execution_count": 1,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Lpggo0wM6qb-"
+   },
+   "source": [
+    "Create an experiment"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "bFcr9k-l4cAg"
+   },
+   "source": [
+    "experiment.create(name=\"mnist_dcgan\")"
+   ],
+   "execution_count": 2,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "-OnHLi626tJt"
+   },
+   "source": [
+    "Initialize configurations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "Piz0c5f44hRo"
+   },
+   "source": [
+    "conf = Configs()"
+   ],
+   "execution_count": 3,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "wwMzCqpD6vkL"
+   },
+   "source": [
+    "Set experiment configurations and assign a configurations dictionary to override configurations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 17
+    },
+    "id": "e6hmQhTw4nks",
+    "outputId": "4be767af-0ebd-4c35-8da0-0e532495e037"
+   },
+   "source": [
+    "experiment.configs(conf,\n",
+    "                   {'discriminator': 'cnn',\n",
+    "                    'generator': 'cnn',\n",
+    "                    'label_smoothing': 0.01})"
+   ],
+   "execution_count": 4,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<IPython.core.display.HTML object>",
+      "text/html": "<pre style=\"overflow-x: scroll;\"></pre>"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "KJZRf8527GxL"
+   },
+   "source": [
+    "Start the experiment and run the training loop."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 649
+    },
+    "id": "aIAWo7Fw5DR8",
+    "outputId": "e3b02247-8ff9-47b5-8f52-49c9e3b8377f"
+   },
+   "source": [
+    "with experiment.start():\n",
+    "    conf.run()"
+   ],
+   "execution_count": 5,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<IPython.core.display.HTML object>",
+      "text/html": "<pre style=\"overflow-x: scroll;\"></pre>"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "<Figure size 576x720 with 6 Axes>",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeAAAAKGCAYAAACSkUhPAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAABxA0lEQVR4nO3dd3yUxfY/8DObHkghJECAQOhFOhGpioUOAgoIImLF3uv1eq96rVexoF4LKoINsSOKBRDEgkhApEhHIAHSKOl1M78/iN8fZz+LREkyoJ/36+VL5mR28+yzs89kd86eMdZaISIioprlcX0AREREf0ecgImIiBzgBExEROQAJ2AiIiIHOAETERE5wAmYiIjIAU7ARPSnGGOsMaal6+MgOlFxAib6GzLGXGSM+db1cRD9nXECJvqLMcYEuj4GIjo6TsBEVcwY080Y85MxJtcY864xZo4x5oGKnw03xqw2xhw0xnxvjOl02O12GGNuNcasMcZkV9wu9LCfH+22dxhj1ohIvjEm0BhzpzFmW8Vx/GKMGV3Rt52IvCAivYwxecaYgxXxEGPMVGPMLmNMujHmBWNM2GG/4zZjzF5jzB5jzCXVfR6J/uo4ARNVIWNMsIh8KCIzRSRGRGaLyG8TX1cRmSEiV4hIXRF5UUQ+NsaEHHYX40RksIg0E5FOInLRH7jtBBEZJiLR1toyEdkmIv1EJEpE7hORN4wx8dbaDSJypYgss9bWttZGV9z+ERFpLSJdRKSliDQSkX9X/P7BInKriAwQkVYictaxnCci4gRMVNV6ikigiDxtrS211n4gIj9W/GyKiLxorV1urfVaa2eJSHHFbX7ztLV2j7V2v4jMk0OT4R+5bYq1tlBExFr7bsV9lVtr54jIFhHp4e+gjTGm4nfcZK3db63NFZGHRGR8RZdxIvKqtXadtTZfRO79syeIiA7hWhFR1WooIrut3uUkpeL/TUVksjHmusN+Flxxm9+kHfbvgsN+Vpnbphz2bzHGXCgiN4tIYkWotojEHuG440QkXERWHpqLD92FiAQc9rhWHtZ/5xHuh4gqiRMwUdXaKyKNjDHmsEk4QQ59HJwiIg9aax/8E/dbmdv+36RvjGkqIi+JyJly6KNmrzFmtRyaVFXfClkiUigiJ1lrd/u5770Vj+M3Tf7Y4RORL34ETVS1lomIV0SurUiEGin//2Pfl0TkSmPMKeaQWsaYYcaYiErc7x+9bS05NMlmiogYYy4WkQ6H/TxdRBpXrFmLtba84nc8aYypV3GbRsaYQRX93xGRi4wx7Y0x4SJyT+VOBxEdCSdgoipkrS0RkXNE5FIROSgiF4jIJyJSbK1NFpHLReRZETkgIlulIsmqEvf7h25rrf1FRB6XQ38QpItIRxH57rAuX4nIehFJM8ZkVcTuqLjfH4wxOSKyUETaVNzfZyLyVMXttlb8n4iOgdFLVURU1Ywxy0XkBWvtq66PhYiOH3wHTFTFjDGnGWMaVHwEPVkOfZ3oc9fHRUTHFyZhEVW9NnJozbSWiGwXkTHW2r1uD4mIjjf8CJqIiMgBfgRNRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiBzgBExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkACdgIiIiB45pAjbGDDbGbDLGbDXG3FlVB0VERPRXZ6y1f+6GxgSIyGYRGSAiqSKyQkQmWGt/OdJtAkNr2ZCIGBXzBuk+nlI/vyu6DGNZgRDz1CtR7dKDwdAnom4BxAr3hKl2STQeQ0CBgVhUXB7EctJr6+OMwQdUVhAEsejIfNXO3x0OfUrqVO64ImL1feVl1II+to4XY7kBqu2J8HPe9+F598bgfUmevq/yMD3OyrIOiDc3Hw++GgSG1bLBPuOu3OcpMPhQxUTi4/LsC4AYPP487BMRg+OuIE0/x6X4NInHz3GFRhVBrDQjVN8urgT75ODroXYdfVyFe8OgT2mkn+MqxqcurI4+ruKsUOhjo/Gclufr8xVU289FIMPPuIvzM4bzdL/yYJ9xt++AePOqf9z5HXM+p9/4eZieKD9PuJ/XnKmrb+zNxmtKbX/Xur0+Y87vc4uxyJh8iOWl+wzYunjs3jw89uhon2tdqp9rXV0/x+XvGuxzrcvO8vMiivAzTgp9xlwtfDJsJp5Tb91KXOtCKj/m8OxUXg8R2Wqt3S4iYox5W0RGisgRJ+CQiBhpO/ImFctL0MdVaw/+QeAZlYX39UoMxMKv2a3aafOaQJ9+E1dCbO1/Oqv2rrPxGGKS8VQNuepbiC14vK8+zgvSoE/aTw0gNnLgD6qdfFcS9NkxBo8rehVeVM+4VN/Xt9NOgT4l5x6AWNm3+pyGnobnPXgW/hWQc34uxMw30aqd20FPCGn3PQO3qS7BETHSeqwed/mNdJ/QTHx9eM7YD7HwN6Iglj1B/yEW8A32OW3iCoiteribaqf1wmMIzcQPqdqP2ASx3dNaqnbEVanQJ2VBUzyuc1ap9roHOuHtBkNIIrbi66H9ORtVe9srbaBP2Ugcd0Ur9bir33cP9LFP14NY7pRsiJV+q6/cec31pJD24DS4TXUIjoiRNufqMZfrc/rDMvz8ETMwA+/szVi8/wvTVTv7s3jo0/P8nyD2y8P6+d19Fv662tvwD8gBE3+A2PeP99CBSZnQJ/vb+hAbdu4y1V55ezfos2MSXusiVuEfdIMv+l61P5/VG/qU9cNx4l2v//Jo0HMv9nkejz1ncg7E5Gt9TcxpU/kxdywfQTcSkZTD2qkVMcUYM8UYk2yMSS4rxL+iiKoDxx3VNI45+qOqPQnLWjvdWptkrU0KDPPz8QBRNeC4o5rGMUd/1LF8BL1bRBIOazeuiB2ZrfjvMKH7dDtuBX5cUD6+EGKB3++A2N6LolU7ZgOug32xpR3E7p/6rmrPPH8o9MlrVhtiQyJ/hljyO3o9Y1OfztCn1ce4NvNRE93vzifnQZ93Lh4IsRL8tFOGRuvj+uU9/OhmY//2eFzf6r/aU8Lxo6+ON+DHn7VvhQ8+pLiOXlMJLNTrKZk1s/x7iMXcglo+I7VeMn6MvrMvrgHF/4QfER44T19sYzfietK8FV0hds+DH6r2m5fhuCuJ9rPEMHkjxOZ+ql8jGweeBH1aLcF3ZQs76Y+Jp059A/o8ed1EiHlKcKGwzyXbVDv7bVyr3tgLj6vde3qpY1dxQ+jT6R8bIJZ5B36kHnRAX1AyT9Efb2f5WUesFhbzCsLT9O9usAzH3NaTIyDW5usUiO2bqNfqa+8phz5frsFzffdDc1V7ziWDoE9BQ7xetApLh9gvH61R7Y2ndoA+bb7Ex/h1b71cctkzn0Gf9y4ZADEbjPNAuzC9XLHmJbwmb4/DZZUWb+txkpKLY67dLXitC7utMcQCcvVSVcgB/ZF01u9c647lHfAKEWlljGlmjAkWkfEi8vEx3B8REdHfxp9+B2ytLTPGXCsiX4hIgIjMsNaur7IjIyIi+gs7lo+gxVo7X0TmV9GxEBER/W0c0wT8ZxifpYqHb3xFtfddh2ut/vzrkVEQ+2erT1X7iW7nQJ/Ir3Fd7/Xbeqn2I9/OgD45NgRiD+8aBrFN0xJU+8kz34I+j3xzAcRqf69XA97/dy/oc/+CVyAWavB7aRetmazaB6bhl/3u6/0hxKYtH6vaxS1wDe/gHQkQa/+/dRCbt9Tna1Sx+r68n+GaVbXyyT245cZ3VHt5bnO4ybAwXO994nZch3+g4weq/XjTcdAnZjUe0jvP9FftRz6dDn2KLL5E798xAmKbntFfQ3m473vQ5+mF50EsZJUedy/eeSb0uWPRaxDLKcd1wgd+0WvYeY/5GXf93ofYiwvGqHZBAo5pf+u9zZ/ANbqvFndRbdNE51t4F9fguPNZ+rv6qo9Ue9Nk/DpiZw8e37sP4dd0rm2yRLXfCcZxGbkO8wfef7SPaj/wxcvQZ08ZftVw2g4cF7se0mPu2bNmQp/7ll0Msf0bdc7E3CldoM/Ly/4HsS2lmPBy01r9Wst7GMfcvQPfhdj/NulrXUFnXF/OuQGfn9YvYP7F51/r/I7AJvprid6vjzzmWIqSiIjIAU7AREREDnACJiIicoATMBERkQN/ejOGPyMiqrHt2vd6FQvfpWtrbrocEwCazcWCGnkNMcFgX2ed9RC+F78AndcEF8SjW+ovUtc7D+volndqCbGALX76NddFKVLPwC/WN1iOyU3bx+rkMBuIx9n2hrUQK+2JBTWC1+3UgZho6JPdJQ5ioft0AYmUs/AcB+XgOW36EdaALWiuf2dYiv5C/g+bX5Hsgj01UhUhIhrHXfBBPaZSz8TKRQ2/wecpuxkm42W30u3aWDdBDvbCwhW+BeHbXL8G+hSdhUUEaq3GejfeBvp1s7cfJqzUSsMxle5TztcG4fWgzR047sq6tYZY0CZ9XDYeK+oXNcTXQ0iWToDZNRgTaaK2+3ndrjmIx1VXF6gI3Kfv+4etNTPuIiIb26RTrlWxYJ9j2TkiGm5XLxmLuOQkYiJeWZh+CMG5+Lzt6+5n4wCP7tfmOhxzxf07Qizsx20QK+nSTP++kzAxL+QAPm+l4/X1dn+Wn+Ijl2NBDXNSK4zt0UVcyhMxcaqgEW4wUutXfT3aPi4a+kRthpDErtgHsbI6uvhSQJ5+rf+w6eUjjjm+AyYiInKAEzAREZEDnICJiIgc4ARMRETkQI1WwvKGGMlurpONsjrrRA0bgIkD9p+4MXy0B/tlbNA7VeQm4rp35Fb8m2P6KL0DzL/Ch+B9J2GFrvhsTDLZeqM+pd48TKrY2wMTcup9oBOe7r0Pqw89HXUaxFJPx8SHFlt0otAvt8ZAn6D9fjYDb6urBkV8hklY46/7AmKvBuKOKkG6GIzsGqSTgooexU2/q0tZiJEDrfS4K6qnnydrMIkl/QZMwirYieckJFOPqeJoPIYmc/Dx3jbtddX+XwKOu7yG+BIN34zP+a+jdeJSuZ9kqoIe+HjqLNYJKtffghW05jzSA2K7hmBiS4t90fqYzsVx58F8SimK1+ev7ko89rbXY5n5H+ZjslDIAd3Oba5fC0WP18y484Ya2d9G/+7iuj7tGExQKr8Rr3VF38ZDLNhn07jiKHw9xy/Ba90/H5ip2s/FYwWtnKZYLTB8HT7f28bqsemJxGpSAQH4GMO/1LusvXHTs9DnwRZYTW7HCEzQTXxXX1+3nofJlKYMz40Zrx9jzCc45rrdsBpiny/H3e0ituoxldtMvz6LHjvymOM7YCIiIgc4ARMRETnACZiIiMgBTsBEREQOHFMlLGPMDhHJFRGviJRZa5N+r39k7Ub2lA5XqFjKAF0FpbAFZmmM65oMsblbMAGjJE1XJGnaLg36/KMZbl/8ZGedZFJ3ASYhXFZ/KcTaB+dCLNOr/6YZ/cMV0GdEK9y+7/yYH1T77g6nQ5+4hbiYPyYWz83JIXobvYPl+HfWBWsvgljBSp0cMemcRdDn2wldINZy1naIfTlfD4VIn0I6G+Y9KflZKTVTCctPVaIDrXQy1cGOmCzSocNOiG1Y3gxivlsdhrU5CF3uaPclxN48+STV9n6IFaCGNMCxcl4ExvZ49eMZs/Aa6NO0KVYse7Cl3krxgc6Y6NfnO7xdp7BdEOsZqvutKMYkxdfTe0Ns/dy2ql33rD3QJ/QfmFwz6vUlEHv6zZGqHb1NP6/rvnhK8vZV/7iLiGpsu/XR1deK6ujX78E2+LqMOBnPdV4hVl8LW6Cvm54RWKHpoubLIPbJKYmqHfclnopukfjcnuNnzKV59XGN//pK6NOhGVZte7m53pLyok7Doc+4ZZh0FxeYA7FTQvTj3lSKyWI3bcBtOAuW6kqA7Ufg1pZ5V8RCrO/s1RB7/QO9VWPtXfqCsHHuk5Kf6X/MVUUW9OnWWkzdIyIioiPiR9BEREQOHOsEbEXkS2PMSmPMFH8djDFTjDHJxpjk0tL8Y/x1RJXDcUc1TY25Eo45Orpj/Qi6r7V2tzGmnogsMMZstNaqxVJr7XQRmS4iEl4vwWZ21wUtavfWax5TElfALwk1WMwi4CfcQaNumv7sPTUWv7h9dcYFEJu6+l3Vvu3DSdAnvTv+vvfavAOxmybodZDyc3FNolGHgxDbUarXGy5YtRH6/OvLMRA75cxfIXZGmN5t5NIzJkCfA9fjuQkI1+fvrbfOhD4Ft2ERkeKDWCig0dd6LX/7eP23Xtni6t2FS427uASbnajXSMNGpat252hce2tfG9cid2/DNeDSWnp5p7wV/l07deMAiJ21RK87vbe8LfTJK8XCH5d1wLFx8zV6jVuGQhdpUAvX0F5M76/aI5fjrjf//Rbv7MpeSyDW22cN+NlzR0Of7WOiIeaN02Mhc3FD6BP9IOZzfJmFO4E1nafH/qab9dpx6bLqG3e+Yy6nib68Ro7V4+nyeNxlqqgc808+eOYMiAUW6scRGoy5M89tOBVio7/Rux99sBULSzQOPQixWA+Owwm3XqfaYS1w3I/piTkqa0t0rsP9q7C4z9ivr4LY7T0+h9hpPsd638SLoU/W+Vi4JiBGn7+fF+PuXk2ext3uVmUnQKzREl3gZttEvdZftvDIY+6Y3gFba3dX/D9DRD4UESyZQ0REROBPT8DGmFrGmIjf/i0iA0UEU+WIiIgIHMtH0PVF5ENjzG/385a1Fj8jICIiIvCnJ2Br7XYRwQUEIiIiOqoa3Q3JUyYSts8n4SJXJyn1DMMkEN8EJRGR6NMwKcPrU3BiSD0spPBQg28gNra1TnK49ydMrjotDO8r3GCCVcpAnfTx1bhH8Tj9rMk3DtT3dXbb/tDn9Z+fh1jzwAKI1fboRLcNt+H5a9AEv7rdu55O6EovxsIQWafjjifSCRMYdg3SX9KP8MkbyiiqkRocIiLi8YqE5OiCDGmZenemSU2Ww+2WHGgDsYP9cEehuBhdkGV/NhaNWNJ3OsQu7KiTm0YuWgV9bo1bAjF/L9tdI/XjWzjgKeizoywKYn1D9eM5pzsWRfjH4k8hNqr2FohFeXSyy/ax0dBHWmF2cI/GKaq9LrMB9IkYiQUdCvyMu8yePkmea/U48xTWzLjzeEVCD+jnJGWNTlbs1nwe3O7hHZjwlj8wD2Id43VCV7nFx/Vhu7cgNrHTMNVuOzcd+lxd93uIhZhwiLW+WRfLeKwRfgCaW44XO99r3cizJkKfd+fjta5pICbjhvlcg3fdhAV1TDEmqI3tu1K112Q3gj7eodkQ29+7HcR2D9AJauG/+oy54iOPOX4PmIiIyAFOwERERA5wAiYiInKAEzAREZEDx7Qb0h8V1iDBtrjgZhXL7aAXyBs11JVsRESeaDMHYhuLsfrS/H2dVPunrzCJJqAd7mC0rOdLqp1cXBv6RHgw+aZHCFatKbVe1U4tw6SlzHLc3eSljP6q/WzjJdBneTH+vsRATNBoEqiP32sxMeE/WbibVOtQndg2dRruIhK1AxMh9rfD4wrN0uMq6kJdVWbFlW9Kzqb0GsmICa+XYFudp8fdwQ5lqh0Zj+Piqta4A9YnGZ0gdlLUXtX+7A3c8SevCT4HK895QrW/KcJkOX9V4AaGY8x33K0vKYM+O8pwd6JnduoExLltMQHx66JoiDUIwKpa3UN0Mkp2OY79f+zFXb525euqbLvfw2pjtdK8ENvfDncHC/ephhc7Qe/s88MVs2tk3IU1SLDNL9RjLq+tvtad3Bar2A2P/Rli24rrYyxf7+azei5WBSuJwmv7t5Omqvbn+U2hT6gHx9e42piQ5Dvm8sqxSt6mUrzWPZSiE8Feb/Eh9Mny4vMd4udZa1yJa12v1XgdG5WgK4K9ORur/tVbhclbB1pjRTDj8yvjx+xQ7WVT3pbsI4w5vgMmIiJygBMwERGRA5yAiYiIHKjRQhxB+eVSf6VeF5p48beq/ck9uPNH6VRc65l9Mn4hOuN8vebb/9LV0Oe5Rt9BbPD5V6v2nTNegz4JAX52AfKzfH52Y70fRUB0NPQpmIMFEZZ0+Ei1z5x0JfR5fsbTEIvy4LnxXQcZ2qgb9Amog7shzblJ754yZgoWLfn6P7i+2XjWJohln95StQ/MbqzaZftxLaW6eEpFau/Va0qlZ+qCEPWm4lrVrmdwzdQ7AtfcF07opdrFZ2KfDX1fgdjgS29Q7f8+/xz0KbK4vp7hxWIWk5r0Ve3AJo2hT+50fLkv7ajX30674nro899pWBQh1OAaXUG5XjMb17gX9AlsGgexXeP0DjMXX4kFHV5/fjDEEp/dADFvG31fWbaJatfUuAsstBK7Vp8P21tf+w7egTvrpL+4A2I/9o7GfpN8rn8DcY12wymvQ+zUm25R7ccf+R/0aRPk71qH4/DshJ6qHRCHr5d287Hgz8et9PM76JwroM8zc3DMRXjw/SJc6xJOhj5x8fh6eeMiveZ7/oSvoM/8X/tDrOE7WyFW0E2vo++bodtl+4485vgOmIiIyAFOwERERA5wAiYiInKAEzAREZEDR03CMsbMEJHhIpJhre1QEYsRkTkikigiO0RknLX2wFF/W7mVgDydmDAx6ifVPutxvcOGiP+Ej7yz8IvnDRboggin37wR+gxL7AkxT6k+hjPD8Pd9V4S7gYR7MFnB9vbZofEX3EVpVKPVEBvc7BTVDixeCX1aB+EuO7vKMOFHfI4r9zx8zJFbsfDEhaN0IsJ3Z2Mhk9qZ6/B2q36B2KyxOtlmyx161xLvQvzCfHXxlJZLeKreNeqFbi+r9o6ZmJTmrwjGZ5MxYaT+Mp0AM/ya1dBndGdMIgrer3c/8lfYZVspPr8hBhPvAlo114FSLMRxSVNMQBzSUifVhRaugD49X8Tft7kUn78C3yIIPbFoSXoHHMMjzteJmAsuwPEan4Kv5YHfYiGLLyboohXeET7FFBbja7s6GK+VoBw9fuZ1f1G197yO1xSvn/dEHw4fALH4ufqx97naT1GPVn0hVrtIP789n8Lndm8ZPrd4pCLlvXUxH08eFq4YEb0QYkOa+zy/xWuhj79r3a9+XgvikxxbOKI7dPEGYw2Mq87XO3x9PhgLE0Xtx+M6a/leiC0crYuBpEzUSbZl3xz5WleZd8AzRcT36nGniCyy1rYSkUUVbSIiIqqko07A1tqlIuJbH3KkiMyq+PcsERlVtYdFRET01/Zn14DrW2t/ey+eJiJYrLSCMWaKMSbZGJNcWoabxxNVBzXuSvF7gERVjWOO/qhjTsKyh3ZzOOKODtba6dbaJGttUlCgv5UEoqqnxp2f9SSiqsYxR3/Un62ElW6MibfW7jXGxItIRmVu5A0NkINtI1TsilPPV+3dI7CCT1E/TBiy43Gnld7/3qHaZ4SnQp+ZXYZDbMhMXfFpUMMu0Ef8VJzq/RMew+QZ81R7fxnurDQhEpOWvmijExMuf28+9PF3XCYEKzh5PtcVae58ACt73bthBMRe36SreDUXrK6TdlFniM1Kwr/jbIlOCmn9oE+1mL01l4RVHuyR3Gb6gnh7v7GqvWekrpgkIpLd1k/CTjuMxYzS4/PcKEyg+67j1RDr95RO6PD7/AZhFZ3UOa0g1ueN7aodFoAJZN1Cd0HsnYZ9VHvcvGXQx+9xBeKlw7OgnmqfPWMx9HnyU3z9fThXJws1z9kDfbJPx8e84ExMWjNF+pw2+KfeNW3HbrhJtSgP9kh+gk48vLb3ONXOGIg7ER3ogO9lvGfhmOtxu64wNTryJ+izpMtVELtghk4+8vfcesLxjVLY5/gHxUWv6GtdakkM9EkIxF2zvF11cucVs3A3pMq+FvLm6fniwkc+gT6PrzkLYu+m6uqAtSNwLKWdjdeEhf3wGGxJumq3fkxfk/enHfH96Z9+B/yxiEyu+PdkEZn7J++HiIjob+moE7AxZraILBORNsaYVGPMpSLyiIgMMMZsEZGzKtpERERUSUf9CNpaO+EIP8IdjImIiKhSWAmLiIjIgRrdjtBYkcAivSC9a4xeRI/ehgkH9vsIiI26+GuIpRVHqnb/F2+DPt2mYQLUeyk+C/KBmKwSUL8exH6YHA2xsz54Q7VP9pP4sseLCV3lT+oqL8/uPB36hARiBolp0wxipffq5I+Or2GO3JjE1RA7o7Y+N9f3vxb65PTCxLP6yzGZxJOvK9RsukwnaBQ9XqNDT4xPHsSu8TrBIiwDEyUC8/Dv0+Y98Pncm6PH3bnv3AR9Aq7CKj6vrdXVz1rX2gx9TCImJSbchwlsXWfr42obghV7pmeeBrENd+mEvUX7cZtP8WAijad1c4iZS3UlpJMW4HhN6o1bVzYKPaja3/x6CvTJTcRqRkF5mCQTsq9ItTdP0glFRY/ia69aGBHrM3x2TUxU7Vq78Xn0RmEFs3YtMCltY7b+5ufoT26FPiG3Y3HCWam68lmgx881pVEDiBVdgq+Pjgv1bbuFpEAfr+Dzln6HHidTt2Glr0jPDohJJ0zEi/J5XbVdhOfq1MRtEOsfrSurTTt5HPTJTcTHXK8NbiFpvLrftrE68bZo2pHHHN8BExEROcAJmIiIyAFOwERERA7U7Bqw10pQvl73CDmo/wbYPRLXQMZ2Xg6x+SknQazeNXp98t4Fb0KfYD87K00fdrJq37k5GfokBuIaXnxAGMSyy/Ua1IVnTII+Qz7CQg3/SNSFNx7tijuZ/G/bEoiVCq6FNwsMVe1ii0/zkqt6QeztnjqxfcgN30Ofn67GQhxXz/4AYretGqPaUYv1WlA6biRVbUyZldB9ujBFUbT+Qn1WN1zvadw2HWLZxaEQa3SXHlMnvfED9Fl7sCHEPOfoMXXLGrxdXACWNGzu51Vb6rMT0QWn4pcXes3F9dfnT31dtZ/uhuuvD23D4hzRHhx38QH6nBZbfC1vfRV32Frts5TbaBKuS9a5Kwpil77xMcTu/GK8vt06fX3J0C/PamPKrIQc0I+/OEoXe8jqguujvdrheuWPOxIh1vo+vS5/77zZ0OenAszNWDdErx3fsHkN9In0/AixTsF43fRdwT6vz3nQp8fH+Hhe6qwLA93bGb9Q89j2byEW5WfMxQXoohdei6/jux7tALGFQ3Suw7BrV0GfDXfg7SbM/Bxi//lRF5eJWKWfVw9uEvX/f3bkHxEREVF14QRMRETkACdgIiIiBzgBExEROVCjSVg20EhxtP5Sck5L3eelfjPhdvu8uKPQ+xt7Qiw2Wu/e89qe3tAnPBBXxF9bo5M5xky5Efr869kZEGsSiIkJfWbqL8TX64Bftt9bggkluV6d3PPa+s+gz7B/YmGRmf95HGJBRp/jU+7HghrSCUP5jfWxJt/SHfrk/BN3prr1/ckQa/GWLgKw9U79t57385rcDclIThOdILS/lx4HN/dYCLeLCMCiIw98eg7EAtvoxI+sEhyv29NjIfbaKj3ubvz3NdDn3ntfhdhJQXhcnT7SO9807oTJKFmlmNx0w+xLVPuDNU9An6tuuAFiN099C2KJ4ToxqMvreDtpiSHfbB7v47i9+O5bMXvqjiVYPKHNa3rP8c3X6Ofd+/mRd6apSjbASHG0vrwe7Kcfw8M9MHlxfSEWXlmejolr+W10AZUXdmKRlSYR+yF2x/dfqPZ9l18KfR5++QWIhRicKlp+MUW1G56CffK8uCPdt/n68bywDnd+G3cXFhZ58L6XINbY5xrc/T+4A5SNg5BImR4H6+7FC2LmNbh//X1LRkGs5Zs6wXPrxfraUv5h1e+GRERERMeAEzAREZEDnICJiIgc4ARMRETkwFGTsIwxM0RkuIhkWGs7VMTuFZHLRSSzottd1lpcSfdhRaTc5zeWxukF7CA/lar2l2FSS6ceWGGloJtOuOheB3euuTsWK7+MOFsnEwx8dSn06RiMO8KUWqyK5G2hE2RmT34W+vhLP4r16GMfe+pE6DPl0w8h1jAQq+l4faoiBY7Igj71amFlr961dNLG9y0SoU/98/xUKeqEFcH2nKF3PwrzKf7lKai5v/2MFQkq9EmEKNO/v2EQ7hyzKLs9xCJbYb/QLjpZI70Qd+9a1e9FiI3rPFS3v/4S+iSFYCJNueC4E5+H98CT06FLXQ8mbz10sa52dm67gdCny+KfINY5OA2PQfTOQwYLYUmtzvh4Gkbq11ZK+2jo02z8rxCzHXF3nL199bkP3aJ/borx9VJTgrfq10lBUgj02ZCLOxEldsIdflIaRqt20wC8bj6XgOPpvJ7nqvakhfOgT+dgCEm57wATkcgYXaXt5UdfgT7RHrzaxfhUrxrd6Wzok/Q5jjl/12CRWqq1vzsOuoFd1kGse8RO1Z4ahTsytZiEY87btTXE0pP0uA/eo8+VKTnymKvMVXCmiAz2E3/SWtul4r+jTr5ERET0/x11ArbWLhUR/LOViIiI/rRj+RzwWmPMGmPMDGNMnSN1MsZMMcYkG2OSy4qxsDxRdTh83JUWcdxR9VNjjtc6qgRj/eweAZ2MSRSRTw5bA64vIllyaOXpfhGJt9ZecuR7OCSsQYJtccHNKpbfRK8RnNFrLdxuRAyuB6SVRUMsz6eYxTNLz4I+XTvg5/rTm32k2qlluDRe4udvlR4hQRArKNdfws4qx8IfSwoSIfZBui56MaflJ9Bna6mfRTU/TgrWa02lFteH+q8dC7ErEvXa97QnsU9ECh5DXsOj13MJPCdTtddfP1PyN++tkQW58HoJtvWYm1SswGdzItsGL5jPdMcdZtYVJUBsVY7ezufnD3Dt2NPXzxpz95dVe1MprqXHeLAARbvgcIjl+ezC9XMJLuRtLMYdmd5I1bsfzWmLBTZ2lOF9fZnbEWJ3x25U7W2lmGcw4OvrIXZ6682qvfItLIpQew+O4ZwmARALy9LXs+jJKaq9/Mq3JGdTerWPu/B6CbbNuXrMFcbpX1vcFtfkL+iIOxH5WxduVmufan//H9zFKv/igxBb1FUXdvmlFPMJQv0s3ncPwTHgm2uyrQwfz34v3v/bB/SxPlQfd11L9+J1M8DPs9YkUOcHFdtS6NNv9fkQm9xM7zz2ytPDoU/0VjyG7OZ4Hjw+pytwbIZqr7tu1hGvdX/qHbC1Nt1a67XWlovISyLS48/cDxER0d/Vn5qAjTHxhzVHiwimmREREdERVeZrSLNFpL+IxBpjUkXkHhHpb4zpIoc+gt4hIldU3yESERH99Rx1ArbWTvATxi98ERERUaXV6G5IgQVWYtcUq1iHc7er9k8vYQJG/9s2QuyDLpgMk365TmSaeNk30Oe+uJ8hdublN6r2Oy8+BX38fVbvtZgEMjpBJxgENsXj7DF3K8Q+aqV3Kel523XQ58OHp0IswoNPoW9yxPDGSdAnulExxJ44R+8u8/Qdz0Gfu27DDzvqvfcLxAp66S+s572vtySxB2pu6AWUWIlI1Uk8LS/QhVy2v4pfsN/TGZP7F/bG3WpSpuikqwZDUqDP523nQmzYqCtV+/F3/RTPCMAkSX9Jdecm9FLtwIbx0OfgK5gQs7Tje6o9+DzckenkZ1ZB7KKYZRDLK9evh6sT+0GfNp0xqWx9hw6qPfxWfN0u+m8fiDV+bRPESjo2Ve3Md/Xrr+yAnyoT1SCgxELCoh2mC0k0ehST7lY+0ARi5WdjguAn1+id3hpfi0WHlrT9GGIDLtZJcO+8Mg36BAjmC5X6udb5Xlf8jbn28/ZC7Kn4ZNU+8wLcwWjWTDyuaD/XOt+kV9/rr4hIbEQ6HsNdOulq2OUroM/KB3A3uPpvr4eYt32iah+cXU932H/kax1LURIRETnACZiIiMgBTsBEREQOcAImIiJyoEaTsEy5laA8Xank5aY6+Sj1X1gBKtOLyQoHzhsHsfgv9WJ7p+sxMWFY814QCynVSSb1AmpBn1/9VPWJ8mCCjOmiE3Jsagb0aReGOwoNbqaTB6JKMSkg/jHcFWpDSQHEEgJ1YkJA25bQpyg+EmK3XTNHtf97Bu5SErl/A8RGLfeTVHZufdXeM1knAJV/5W9PqOphvFaCs/W4m9pEJ0Xl/wv/Ft1ZhklYGeNOglj8Mv0ctB2POwUNb9UXYrZQf33et4KZiEhqGY67AosVemzvzjqwBytvDWmIyXIj2vVXbU8uJineX281xF7PbQaxQeE6oTIwEROKimLwMba+Rh/Xiiu7Qp86mzDh6uQl+Nr6caJO9iu9Xid92S8xga06GK+VoHydhPV+Z/3lkS0zj1jBV3ngjIshlviWTvTret5O6DO8NSbBBRXqqoKxfq51B7x4TfFXYap4sE8S1kZ8PoZF4Xga3FTXbQr0roY+jQPxWre+BCttNfOZwQL87OBW2KIuxNr10hURt5xdD/pEFG2BWMJCPA/bb9bXjuzh+jXr/ebI1zq+AyYiInKAEzAREZEDnICJiIgc4ARMRETkQI0mYZUHeyQvQSdhjOk8WLV3XdYWbpffCpNOzBkYG3yLrpg1IAyrsLzU4xyIjZ/+mWoPatgFf18QVtA5OBeTTP717vuq7bX4N84ZYfsh9sJpeuu/l156CvoMaoiJPGKwao1ZpLedu+2TD6DPZUswseOpLWeqdr2ibOizbyQmIX3UC4/BlqSqdvP/6qSdjLSjb4NZVbzBHslLCFGxK0/W42DvGExUy22OyRPlXTDW+mKdAHNZLFZyurPpJIhNmasTEP2Ou0B8iQ5cjeNn6psvqPZX+fg6Glkb90xZVmuMal+zMhn6DG3UDWLiwcpI//u4v2oHP4/b2mWtwNfRzu0tVLvN7kzos29oG4glDw6BmOTpBMf4x5qrdkpajeyAKeVBHimM1Y/12tP0tnh7hmNVtTIsViZFvfG1Mux+fa2bEIVbtk5pjxWmzpiht+HzN+Y8oXgQA5Ixwerx5/6n2htLsBJWh+BcvP+WulrZjfM+gj7+jsvfta7hMp2sNWQuVm176qczIBado5NQGwRjZcDU8Yl4CKN3QCwoVycfNr9Pn4f0PUzCIiIiOq5wAiYiInKAEzAREZEDldkPOEFEXhOR+nJo/9/p1tppxpgYEZkjIolyaE/gcdZa/Pb/YaxHpCxMz/mpk/VaVeRO/Ly8KA4P86KBSyC2OluvqfSdcyv0KbkKv2T+fprPGpcHd8/wJOJ6Ta2pURBr9IpeN43w4Be393hxLSP0H3tUe24u7grlbz3Q26cjxIIm6HWwVitwLbdf+80QuzX+S9W+fOBN0CfzLFwriVnTEGKFDfXazK7Bes2w+DFcQ6xO1ueUp07Ua76h+3Gdzc8GMNKzK543j9G3PfcdPG/1nsQxdes3uphMm8DV0Me0x7XphaMx/2HIAr2+2zEUd2TaWYbFV3b+TxcpuHkFFrhpGYLFVzwJ+JzXu1Lv2pP06Q7os75/DsROr6uLbLzZZxj02dcJXzPh6Y0gFnxQj8+tE/V6ZnFKzbznsEakLFQf887x+hpSOxWvdQXt8HE26oK5LO/v6qLab88fAH1yb8Jr3bZPz1LtFoFY8Mc0xrXcBecnQmz0vDWq3S0Ex9ymUiy8kvZf/Rxc8+NE6NPcsxZigfViIZYxWp+v0ctxt6KQ7ngNTgzSeQb/7nMp9DF+lm4LT8JxH1Coi7tsH61zE4oeP7bdkMpE5BZrbXsR6Ski1xhj2ovInSKyyFrbSkQWVbSJiIioEo46AVtr91prV1X8O1dENohIIxEZKSKzKrrNEpFR1XSMREREfzl/6PMYY0yiiHQVkeUiUt9a+9tnI2ly6CNqf7eZYoxJNsYklxXhxtJE1UGNu2KOO6p+HHP0R1V6AjbG1BaR90XkRmutWsix1lo5tD4MrLXTrbVJ1tqkwFAs/E1UHdS4C+G4o+rHMUd/VKUKcRhjguTQ5Pumtfa3qg7pxph4a+1eY0y8iOA3tX3vp1wksEjP077f007rh/N4wxb4xfzXN/SAWMs7Dqp2g5dToc/Yhish9vFpegej4WuzoM+FUd9CLEgwS6dU9Mr9+GGXQ58WL2+H2MSGy1X7ja5YeGDsWrzdoFpLIFY/QCc+pPvZAGb9q1hQ4yKPjnW+Ggs37L0Ki49svDEcj6G+zseLmq93G8nAXK5q4ym1UmuvTsTwhugiCQcG4k4rbeJxSP+wpTnEWj2nk6JaPIK7cA2uj8khX16gC1B0XIGFK26s+zLEAvwUJMgt16+bx86bAH02XYEJMeOSdBLOmr44cXT6AZ+sG+u+DrFQo/+eX1uK4+KzJ06F2MyAVqrd6rqN0CfqGkwMSr0HQqDe+/pcZeLmUtXCWJGAEv2cRPgkmKb7KbDhicFzfeAzTPxpuEgXY7FP4W5IJ4Xiu/B9V+iLQePvsJjJPfH43PpLmfS5lMutfcZAnz3PYeLfVa2XqvZH/dpBn5hvIyD2VAIWFIrw6NdxKr6E5LnnRkHM6/Owe1+PhUxSx8VBbNODuLNSaJh+/Ud+5XP9xZzJ/3PUd8DGGCMir4jIBmvtE4f96GMRmVzx78kiMtf3tkRERORfZd4B9xGRSSKy1hizuiJ2l4g8IiLvGGMuFZGdIoLfXyAiIiK/jjoBW2u/FZEjFVA98whxIiIi+h2shEVERORAje6GJCJivHrlvqCB/hvg/D7fw21K/ZQk+jkYq+CI0Q9newpWTnnnkcEQaztfJ8jMu6w/9ImbiRV8RtfGJJ2Ba3VVl8BGtaHPp6uwytX2aXqHkMaLd0OfD4Zg4tmnr2ElrNkt5qt2v09vhj7hsfihRoPlOgEkfTJ+s2zneVj9KzgVk0min9OJCMUP6ccT8AVWp6ku3hAj2c11skau3pxJHkz6EG73bU5riG0KwHMSkK+zLLZmYKLGxw/hh0XNPtEVoNZc3B769LmxO8R+PPNpiA3/Ue98UzcRE6DivsO/t398/2TVjv9yK/RZNyoGf9+zl0Dsq66zVPvqF6+GPuVYUE4id+jkpANX4DnedAUm5QRswsfT8m1d9W3fg/t0h2V+snSqgTUi5YH6NZbWTz/OO/p/Crd7KwVf4xm98JjNF/q+Uuc3hT7FazH7J+lrnYS65mq8ftw3bRDEpjVaDLHrfh2q2kVtMFGu6CdM8np91gjV7vnlj9Dnl6H1IHbh7LEQ+7C1Tj0a9O110CfaN1tMRIJ9LucpE/HYf72wAcS8ufhcNHlAZ/alP+qTxPvZkccc3wETERE5wAmYiIjIAU7AREREDtT4GrCvIJ8vxkcF4g4eH6R0gVjON7hOFP6M/uy9ayQWRDj72Z8h9talei3jYBssWDCk1h6IFZTj2kLxO/q4rn3ybeizpiAB7+t1vUa58gFc+9tzPa7bfp04FWI7y3S/xLl4nPtwuVFSp+h12eCVuA6TOPd3N7z6P3tPraPa3i/1Gl5ZdlCl7qcqeMpEwvbpNbOSKJ1XsLkI14Byy0IhVl6IL5m0h3Xbm405C72n4jrX4of6qPb+kfj38Ef9n4DYfj+7tIQv0LkGne7AwgK1ArDIQ75PRYKfnugCfYqG4XG92uFJiPmOu6jtWAFmfzs8NxkD9LjLScQ159azMAfDU4BrnDtH6ryPwIX65+W57i55tX/Vv3vNyXgdyC7EMefdgXkkW+7W59FbWgR9ksZsgdjP1+j8k72nYuGVFxp8AbFUPzu47ZilC6ic/zTeblMBXqc7jNXX0o+vPgP6ZI3Ba/Bbzfxd6/S1rdHbeF3J7ILHXthIr8sW1sf13obf4esl6CCe55RhumCHWaJ/bn9nzPEdMBERkQOcgImIiBzgBExEROQAJ2AiIiIHzKGdBGtGWHyCbXaRLgpRrnOPpDQCj+eqobi4//EeLGbhfV4v+BfG4N8XwXl4/33u0DsR/ZqPhRQO3ItfdJ8363mIrSvVC/7/HnMR9Ml9EHfeKZmjj73dFNw9p6QcF/PT/4O783w+Qx/XhhLM2rmr5wiIbXxMV0mI/Qq/RG/8JABZP3/GhWfqJIedY/QN0+59Vop/TT1SidMqFVY/wbacqMddbjN9PCH78UFMOncRxL7d1wJi9kZdnCSnDRYrKYjF+598jS6YsjATd4XZ/wKOu48fexxic/P0cb17Phb+KH0sF2L5r+qddqIuwR3Edu6rA7EGMzFZ6MMXp6n2N0VYCOfFAWdBbOMN+hiiN+KwKA/wE/OTxxe9XY+7fRfrHYF+vXW6FG7dU+3jLiw+wSZeosdcSZS+9njD8Fp02in4ul+VhtVLombqpMbScBxf3iB8mKHnp+nblePtQp7FJLgPX5gGsRSvvu0dZ18EfYKeOQixtBm6Ck7rKzZAn5/2YqGl6LcxGe2TJ3Qy4M4yTPL7Z3/cpemXf+iky9jleDvfHZNEREoj8JzGbNBjLmOyvr7vvP1FKdq22++Y4ztgIiIiBzgBExEROcAJmIiIyAFOwERERA4cNQnLGJMgIq+JSH0RsSIy3Vo7zRhzr4hcLiKZFV3vstbO938vh0RGNLInd7tGxZo/vlG1d17TEm6XegbuhBK7BnfT2TVc/z1RexsurHcftxZiGefrpKs7Fn4Efa6YhTu7lLTCZKpmL+u19szOfirbYEgSh/yq2vbiYOhzwwI8vXc/cBnECkfqHWESbsfqLcVNMLGmJFIneRXWxb/P/CVh1dmE58FToqsg5Sfo3Xl+XjRN8g6k1EgSVkRkY5t0yrUq1ugBXSUo7VZMZts5FKvx1FuJJyB1gH4N1dqByXJth2+GWOFknVQy+XPcceahZyZCzDNgH8RiH9GDqqQOjp+8hnhcDSbuUG07CV8zkxd9A7En750Asazhepy18pNsuL8rjruyMD0MSmvhsAjOwetUnY1YNc+U6ecnr6ked2sXTJO8/dU/7iKiGttufa5XMc+t6aodcA8mO+0+FXexCk/Hx37gJB0LPoiv1fqn4o5q4Zfr29311UfQ58rnroVYYL/9EGvwL93ePQAfj5/ia5I0SVcj3DMSk6tu+24BxK6eeSXEQk/Wr4XoZ3GuKI7CMV0Wqs9XXgIOiajt+FqP2ogV2cRnDs1tGanaaxYdecxVpi5bmYjcYq1dZYyJEJGVxpjfzs6T1lqsD0ZERES/66gTsLV2r4jsrfh3rjFmg4j42YyXiIiIKusPrQEbYxJFpKuI/PbF2WuNMWuMMTOMMfjZ0qHbTDHGJBtjkktK8/11Iapyh4+7Uo47qgFqzJVwzNHRVXoCNsbUFpH3ReRGa22OiDwvIi1EpIsceoeM1QFExFo73VqbZK1NCg7CnTeIqsPh4y6I445qgBpzwRxzdHSV2pvLGBMkhybfN621H4iIWGvTD/v5SyLyydHupzzQSHGMLl9zYex3qj3neV1VRERkYCgmncy/tj/Ems7T7W4ProA+q2/vCrGQ/BTVTgrGbc46D9wIsZsbYoWu+27TFabis7GqVr3nUiC2faqughSZtx369A7FSkZRk7By0bPNP1Dte3OGQZ/iOnEQC7lyr2qnbsUtulrOxuS3S2bMhdjjj4xX7ZzB+h1B2U9+srmqixEpD9J/a15Wf6lqv/o4JrqMjNwBsQ8WDYRYnZ91wtM5V38Ffb66tS/Ewor1tmyDwtOgz7PD90LsPy3xfD+6+XTVDmiAz2+rf+O42/BYB9WOLMJx5++4npyUCbH7m+vH/VrWydCnLBQTdQ6erpO1vLlY4qrlW3hdOH/GZxCb9qyuenSwu84CKv2xZir/lQcaKYzVyT//SvxStedM7QG3OydqG8Q+uHwAxILyddJd/zu/hT4/3pyEB2b189YqCBPlksZgouoFcd9D7Il9g1S74VeY7BT8FF671z7dUbVjLI65zsF5ELv4PLzedgvboY9pwxDoU9gXK4kFTtQJccVrcdvE4GzcTvO8txdC7PEZeswVd9PHXrbqyNe6o74DNsYYEXlFRDZYa584LH54La/RIrLuaPdFREREh1TmHXAfEZkkImuNMasrYneJyARjTBc59NWkHSJyRTUcHxER0V9SZbKgvxURf99h+t3v/BIREdGR1ehuSOFxCbbtOTfpWIb+nN33C9IiIkV1cP73hmCszla9PpkXj39f1PsG165y2+t12vC9uC4SmHYQYr/8ux7EAkL1WlWDD3BLDX+7NDX4Un9pPq8Drr+GZuBxBWRjbMNNuM7mq953uF7jK+anAxArTMAvupf52YkldJ9+Lva30+dh87tPSkFGzRTiCK+XYNucq8ddrXQ97krD8DHkJWCsDOskSN11+r7y4vHcxi/GQgZ5rfWuSWFpWDAlMBtjG6+Ohpgp0aeywff4ui6OxMcTt1w/xzntcCen8AzMiQjIx1yAzdfq59gE4tpX3Gd+tpjxGQUxyzOgS0ErzKXw+rlWBOXp5yKniV5P3vjhk1KQWf3jLjwuwbYdrcdccK5+TgJK8TkqivZz/avr51q3RV9nCmNwzMUt9zPmWurnNzgH19aD9uM1ZdPlkRCT2vq28fNx7d6L9WAk5kd9DS5ogder4Gw/Y67Az5i7RY+ncj/5A3F+djoyPqe+7nKcF0ri8TH75jCJiISl6zyDzC76IrFlzhNHvNaxFCUREZEDnICJiIgc4ARMRETkACdgIiIiB2o0CcsYkykiO0UkVkSyauwXVy0ee9Voaq3FahHVgOPOuePp2Gtk3HHMOXc8HfsRx1yNTsD/90uNSbbW+inTcvzjsZ+4TuTHz2M/MZ3Ij53HXv34ETQREZEDnICJiIgccDUBT3f0e6sCj/3EdSI/fh77ielEfuw89mrmZA2YiIjo744fQRMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHAh0fQBERH81sbGxNjEx0fVh0HFg5cqVWdbaOH8/4wRMRFTFEhMTJTk52fVh0HHAGLPzSD/jR9BEREQOcAImIiJygBMwEVEVMMZMMcYkG2OSMzMzXR8OnQA4ARMRVQFr7XRrbZK1Nikuzm/ODZHCCZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMgBTsBEREQOcAImIqoCxpgpxphkY0xyZmam68OhEwAnYCKiKmCtnW6tTbLWJsXFxbk+HDoBcAImIiJygBMwERGRA5yAiYiIHOAETERE5AAnYCIiIgc4ARMRETnACZiIiMiBY5qAjTGDjTGbjDFbjTF3VtVBERER/dUF/tkbGmMCROR/IjJARFJFZIUx5mNr7S9H/GVhtWxwRIyKlQfrPp4SvJ0nuhRidl8Qdowp031y8OFFxeZBLHdvbdUujbR4DEUGYhExBRDLzwhX7ZC4IuhTkBsKsZioXNXO2RMBffweVzEeV1RMvr6vzFrQJyAGz2lJkT6nIaH4ZJRnBmOsrhdiNi9A9wnWx16274B48/Lx4KtBpcYdng6xEfi4PAcCIOaNLtd9cvDv2pC6OA5K00N0OwqPwd/zGxpVDLGSLH1fHj/Pb2k+vmZqRxaqdvFeHJslkXgMAYUQkrBYHSzKDIM+ZZHlEDPF+nx5wv2c9yw87+WxfsZdrs+4C/Uz7nJrZtwRHc2fnoBFpIeIbLXWbhcRMca8LSIjReSIE3BwRIy0OfcmFcttpvvU3oG3Cx+VDrGy1+tBrPz8fapd+hlWoxl22TcQW/xgb9XecxZeJCI248Xr1PErIbbimW6q3eKKjdBn5ZK2EBs/fKlqf3VvX+iTOhAn4Igt+BQOumCZvq8XekKfyLF7ILZzUwPVbtEO+xS80BBjF2RDrOQHPeEVNNF/HKU9NA1uU12CI2Kk9Rg97vKa6j7he/GabM84ALHwd3CW3DdCTzwRi8OhT4sLN0Ms7bEWqp0yHJ/f2ltw3LUZgfe1c0Yr1a41YS/+vmX43PUb/LNqb/lPe+iTMgAnvzrr8Xy1v2S9am96/iTos38wztwBW/T5CuuyH/rUnonnPe8iHHfepXrc5bbRf4ikPfA03IbIlWP5CLqRiKQc1k6tiCmH10ctK8z3/TFRteC4I6LjXbUnYR1eHzUwDD8KJaoOHHdEdLw7lo+gd4tIwmHtxhWxIzMi3mD90VXkNv2xW+xqXKNNGYBrSQkbcyGWWqwX9uJX4xrt/F34EdvtD7yj2jMuPhv6FMXhR25jYlZAbOsc3V7WuzP0abYY11Z/6Kk/i3/w8RehzwMTJ0OsNAo/thwVrT8aX/daCPTZ2As/Hmzzij73v57TGPoMuiMZYpuuxo/UTXmOah9op9e0s2pwGc6UiwT6fPIZuVW3Y1fhx5k7++HLo1Ey7nLjnaj/jo3YhrdbtbwVxG546DPV/nRyP+gjFsdws/H7IJY/R/fbclIn6NPiM3xtLayvx8E9j38EfV69dRTEQjPwo+STI3eqduaHODYPtukAscSP9LnfnR8DfZrehitbqffjOQ1N0/eVdTBSHxOXf+k4cizvgFeISCtjTDNjTLCIjBeRj6vmsIiIiP7a/vQ7YGttmTHmWhH5QkQCRGSGtXb9UW5GREREcmwfQYu1dr6IzK+iYyEiIvrbOKYJ+A8rFwks0OtC1972vmpvLaoPNxsbgutuD94wFGKXtPxetee2Ph36BHyI68mvzT9Ztacux/XXUIPfOXwxC9fsNk/toto39PsC+sz5ejDE9s1rotqPzB4IfZ798TmIpXkxwej+HSNUe9PzDaDP3T0/hdiLX49W7bJauIa39cJmEGvzGn7V6tOl3XWgnv4ebNk3+FWv6mR8ft3Ft3yi2suz8XG1Dcb117l3dIHYpQnfqva8hjjuQjNw7fHzoXqd9l+LX4M+pRZfos/uOQNimx9oqdp3DMHVoFd+HgmxYJ+X1ruDToE+9331MsTWF8MXHuSzDL2+u/HRBOhz86n49/qs7fq1XNId16ozbm0KsS7P/ASxhe/2UO3Srvq+yr+q2XFH9HtYipKIiMgBTsBEREQOcAImIiJygBMwERGRA8ZaTLSpLrXrNLZd+t+gYmHpOjkn9Qy9MYKISKPFWEowpwUmU+3roBNdQvdj4ktBJywgEBWpk23qnbMN+kjXdhAKSMmAmK2jv/iffmos9Ak9gOc893xdQCA3A89Dm+vW4O/r2gaPa1OKanvbYDJMXgKev8hN+hh2jsSCCNbPn2zNZmOt7tJ6uvBGYJ4uPvLDxpcku2BPjVRFiIhqbLv1uV7FQvbpcbdzGG5+0Xihn802GuFmBblN9UkJxJtJUV2MlUbohKBWd6+GPsV9sWBK2LpUiJW0jFftrC5Yj7rORtzEYcfZOsnLBuHYbHv7BogV9sPiK+E/btf31RgTKg+2i4RY7VR9XKln4Nj0d04bLzgIsbLauhhPQJGuQf7D+hclJ7/6x11SUpJNTsaiNfT3Y4xZaa1N8vczvgMmIiJygBMwERGRA5yAiYiIHOAETERE5ECNVsIqDzKSF683907rWcunD1aq2XEDJoaUHsR+oWn64ZRhHoqErcMEj9ev1BWmbo8bDX22D8Ekneav4Q46my7X2TblEWXQp1+HTRBbNVdXEfr66kehz5XhIyC2NwmTteoX643Xfx2J1bKCcjEPJX20TjBq8D5W/xrzH6zs9YIHq5J59D7oUlJH33fRE7jJe3Xxhhg52FxvbF/QR4+VAMxPkm2X4TEGpeB5C9YbP/lNVAtLxzF838TZqj3rmVOhz4HWuJNVaAqOxazOerBnt8HnLmQojtfwpfX0MV3yBvR5pcFZEMtpgpeO4AN696y9fXHclUbgeUjvqR9jFL48pNX5GExObAmxiK36Octroq8TxY/X3LgjOhq+AyYiInKAEzAREZEDnICJiIgcOKY1YGPMDhHJFRGviJQd6cvGREREpFVFEtbp1tqsynQMKLJSZ7OuiBRYqCvXZJ2MSRrt47Hi1CZTD2JF5TrRp3nrNOhzVzPchu/Wtnr7uJGr1kKfk8Nwe7d2UyAkBVZnH53y9bXQJzIQM37mXPm4al/RFrcjvOrn5RBrFYSPJ+FO/cFGphcTwYb+eBXEwpbr5J5T7/4W+nxxfi+I3TnnPYg99MG5qh21SScvpelCVNUqsMhK3Q36FwYV6MSfrO6YtFS//kGIZeyPO/ovbI2V2y5pvwxir3bS1dXiFmOSVIfQFIhdeDve1+4yXWHq8Z2DjnqYIiL/u+Ip1b6705nQp8mivRCLL8fX5D0NP1ftX0qw/NfNq8dCrO6netzlDsmFPrnXYlWtwS/9DLGlKd1UO26l/nkGPjVEzvAjaCIiIgeOdQK2IvKlMWalMcbP+0ERY8wUY0yyMSa5tJR/flLNOHzclZRw3BHR8edYP4Lua63dbYypJyILjDEbrbVLD+9grZ0uItNFRCIiG9fczg/0t3b4uIvkuCOi49AxTcDW2t0V/88wxnwoIj1EZOmR+ntDjGS30Gu+sRN2qfbkBrjjT4NAXBt7+PWJEAvJ0dfZqA6489H8g50hNnKVXmeb+hOuv96XhGvAnYJxHWzCxCtUO/As3D3nrFPWQ+zFLF2E4e51uP56wYIrIHbfaR9CrHmEXrO7+uyLoY9nKBZzyG+q10E/n94H+jR++leIvZ7aE2It3j6g2ptv1wVQvF9iIZXq4g0xkt1Mr/nmDclT7eHNNsLtyv1U1FixGnMPgnP1Y0ltFAx9XlqL5/KGlYtV++mfT4c+bRriTlP1Y/Hc3XiBfj2knoVVaFqdvh1i09J0kY0OX+P663uru0NsZOfVEIsw+nw9NWEc9Cm8HF8P3ua6HT0Pi8tsvAbzGALy60As/jv9mt95jR7T3u9qbtwRHc2f/gjaGFPLGBPx279FZKCIrKuqAyMiIvorO5Z3wPVF5ENjzG/385a19vPfvwkRERGJHMMEbK3dLiL4eS4REREdFb+GRERE5ECN7oYkIoe+uHSY7Rn6y/pdEnfCTRbmdoBYyBhMTukeq5OpggwWV3ikwQqInd22v2p/sPZ56NMyEP9WCTKYbFP/YZ2k9GYCFsoIMXhfI8L1ljpnJ+EOQ89+8zrEBobhV2w8ond8CXl6P/R5tBEmby3La6XaW7th0YmD/fMgFtCjPcR+PVcnAQVt0z83xTX4t1+5SECJHnh2g0706dYRx90nmZ0glnkyJvHUTtDPXbgXH9t73V+C2C1dh6l2vdk50OeBph9BLNwEQWzntfq4ruuI465bGCbQdQjWRWEmdB8JfS5dgAmBF0Yn43F5dKLbtrGYTCVl+JqM6qbr+GTVwgIebW/AxMWSzq0gltZPJ/uF+dSuMfl8z0HHD45GIiIiBzgBExFVgcOLv2RmZro+HDoBcAImIqoC1trp1toka21SXFwlaobT3x4nYCIiIgdqNAnLBooUxuldcQIDdfLIx9l6NxMRkQnRuAtQh7BUiO0siVXtF+fijjC/9sMEj4836q8vry8x0KfYYiWecMEkrDcSl6h2djn+jZNdjokoY7bo5Jf5yR9Bnx+L8biyy3FbodiAWqr9fsvPoM+5W4dA7LrGC1V73kysvBV4MVZ1LI3A4wpP0/26X6QrnM19C6uUVRfrESkL1cdYXE8/B/ctxeSjm/t8CbHdLaMg1ipaf9y45WlMShu+62aIff3zVNWen98a+vxY1AxiXUL2QGxF3xdVe0MJjs0Vhc0hdsHXuhLW9yumQZ/lxQ0gtt+LiWBNAnXs5/PxvjouxjEVHKCfi9BMfM0U924HscwuIRCru07vRlZ+g07wCpinf07kEt8BExEROcAJmIiIyAFOwERERA7U6BpwQJGVuhv0WmrtgbpIxNLHcGedrvdgkYSZJ7WAWNbFJ6v2VTfi2ueNdXZAbPCIC1X7jY+mQ59wD66peS0WZRjaWO8cExAdDX2af1kAsQXt5un7Of086DNz4SyIRfg5rqMdk4iIJxwLalx7q16fe/n6Z6HPv6ZcDrHQ1Tsglt9LPz+rXtFFLQqyFvk91urgKbMSnqnXGUsa6F1/6r6ARSNWdWoCsToXHIDYxuEnqXbmabjGv3kEFncZMvF61b7+pbehT5NA/H1ZXsxHmNhU76YVWB+zcOu8j/kCWwfqAiGDfI5JROTal96BWEwArqUW++weNTrhFOjTtsFeiO24WK9N9xi5Fvr8fBCL8TR5G68L3vgY1c6eVV+17T5cuyZyhe+AiYiIHOAETERE5AAnYCIiIgc4ARMRETlw1CQsY8wMERkuIhnW2g4VsRgRmSMiiSKyQ0TGWWsxW8SHp6RcwlN1AtLsVu+rdvL9mAwTF4A7/mRdPB5i9T/bpdrRt2Cy05CWvSFmC39Rbd9CFiIiu8owaal+ABYCKDtdFxLxLN8IfU6P2gCxwU2S9DGVbYU+9fwcV4YXz01to4tg7L8IE9uit2AhjLvPn6PaD/UbDn2Cs9ZB7NK1+HheGa2LoqRdoM9V+QJMYKsuHq9IcI5OXJrT5RXV3vRMPbhdhAfP0T+HYBJa7Pd6Z67TbsBdh3x33BIRCSzUxUnOroXjdWkRjrFwg4VPPO19dgbKxvFaK7AYYsNb9VXtgKKfoc+oWnhfK4sx+S/Ko89xyUBM/jtYD5Og6p6mE7N234wFQ+qvxXE3dPkOiM2bpJPRCsZlq3b5D5ggR+RKZd4BzxSRwT6xO0VkkbW2lYgsqmgTERFRJR11ArbWLhUR3w1lR4rIb9+JmSUio6r2sIiIiP7a/uwacH1r7W+fG6WJSP0jdTx8i67SMvyIjag6HD7uSkrwY3oiIteOOQnLWmtFBCv0//+f/98WXUGB4cf664gq5fBxFxyMa+dERK792UpY6caYeGvtXmNMvIhkVOZG5SEBktdUXwzPP3m0vuOhuPvLvlOw8k9Af6zqc94NOuFpaC1Mhnl5yGiIPfSY3klmUMMu0Ec8ARC6aTMmhjz6iq54lFseCn06B2NSy4unnKPv540Xoc+ghlhZyARhMszNG35S7XfufQz6XLDhQoitL2ikAx78+yz1Rkysebmrn2FkU1Qz8cmWqp2u85aqlfWIlNbWx3jr6RNUe/dwn8cuInmJmCgW3AzPiXe8vu9hUZjItK7ZOIiNePs71fY37kwIJmGlvNUSYmPeXK3a4Z4S6DM8Yg3EbjlpimpPfB2rx/k9Lj/jrt5SPdbj/70N+vy4rA3Eyvfq6lVtM3xXvEQyzsNKWPPPwD/oPUV6l7SG9+rndRduJEXkzJ99B/yxiEyu+PdkEZlbNYdDRET093DUCdgYM1tElolIG2NMqjHmUhF5REQGGGO2iMhZFW0iIiKqpKN+BG2tnXCEH51ZxcdCRET0t8FKWERERA7U6HaE1iNSGq7n/E23Jqp2/HeY+BKShofZY8AmiOV5dRJIz49vhj4D7sBElCdSBumAwZyygJaJEJs2BhNK3pr3smoX2Rzok+8nZzz6vzpp6coNE6FPlMGkloAGWMFp2mkDVPuNH96DPgPjsULXabV1bN6EvtCnuA4efPlJWLkoMP2gam+crJ+b4oewmlN1sR4j3mD9+7Ze0lC16/2EFZIKGuLfp2E9siAW4NFj9uapV0CfnDswaXDqMj3u2oZiUp9plgCxpndhRaten2LlNF9f5beF2KYrdZLXPYvPgT5tQ/E1U96pFcSyLtOJX7d//C4eRC8MdY7UiVOvjR0AfayfK1VeUlOIBWfrbRK3TtSVt4oe5HsOOn5wNBIRETnACZiIiMgBTsBEREQO1OgacECJlYgUvX5VFKvXBjPH58Lt/tPlY4i9k34yxFacpnfgeWrF69Bnewmume46Xf8d8syOb6FPhPkGYjF+dkPy+ixWXdDjbOjz6LIPIXZXo/mq/Y+Bp0OfF3fiMYT62RmnridMtcsFj3PZJV0hNutCvZPMQ5fOxj7nDoLY6HeXQuzh74aqduQ6fV4yimpuDdh4rQTl63XaiJ36OU8dhmvADRrieu/BPCz+0OwePaYDn8cCMOt2NIRY+7v12ueZyZh70DAIcx3OCk+FWJHVa/NXnIY5BM3eSYPYP3rrcfdRL1zb/ecv30NMBGMdgvV5KLeYL7DtBT/r0OE61mwCnj/vtVEQq/MiVnP54afWqh27XD/PWfk1N+6IjobvgImIiBzgBExEROQAJ2AiIiIHOAETERE5UKNJWN4gI/nxeheVnPb6i/Ozk2bC7cI9pRBbuRF3TWrTShc7+C4vG/q8tw6Tjz775VnVvubCa6HPU7Oeg1i9ANwhqf07V6t205Pw2LeUxkHshZTTVPvljXOgzyXnXQOxR9+ajscVov+uavn5ZdAnuifuZhOeoM/XtHvPgz61p+2G2MNfD4dYi7f1Dla7rtQ7QNm5WHCluniDjeQ21kN9Xx9dNGJaX0w4SymtC7En5w+DWEGiTiTcm4Y7YInF5J+xi1ep9sybRkKfsx9bBLEIDyZr9fhIj9kGp/hJzis7ALGHl+jnbtYqHE//vA4Li5z9XzyupBCdMNb1+RugT9EpmOwWkK/Ha+hzWGCj4MGDENvyAxbCafGhvgbs0C9HKVtcc+OO6Gj4DpiIiMgBTsBEREQOcAImIiJyoDL7Ac8wxmQYY9YdFrvXGLPbGLO64r+hv3cfREREpFUmCWumiDwrIq/5xJ+01k79I7/MiIjxLY7jkxPhMZgk8UMh7rYzoutqiK1/OF61t+XFQp+NZ7wMsZHthqj2pB/nQZ9mgZhw5U95hE4yeXPGNOgT4cHTPqyNrvY1qsc46HP3N7Mg1jLIz9ZKvuCki9xwHe6Q1DxYJ/e81wSrjW05NQhirTvVgdiBNrVUO+AXn8Skwpr78MVTLhKcp89BULpOQsssi4Tb7SrGJKw6bfdDrLSDTjirU46PbXbPmRC7prtOujp7CSY2XRi1FmIimEBnQ/S4u//BV/3cDk0d/plqX9QVK7e1/wyPYVDt9RAr9Uk087eDUXzLTIg1jdDJYT+EtYY+bSbsglj99vgLsrpEqHZYsj4mTwE/9KPjx1FHo7V2qYjgVYeIiIj+tGP5c/BaY8yaio+o8S1QBWPMFGNMsjEmubQo/xh+HVHlcdwR0fHuz07Az4tICxHpIiJ7ReTxI3W01k631iZZa5OCQmsdqRtRleK4I6Lj3Z8qxGGt/b9tSIwxL4nIJ5W5nTdIJDfBZ8736LWrOftPgdudUycZYvUCcyDWrfZO1f7vW2OgT7+e0RBb+Msbqr29DLrIhlL8W6V7CMY2DtUFOzaV4in2Cv6CW1N0HttHftah15RgEYNML95XbZ/D2jrwJehz2lo8N3e3/FS1l87CNeBaw3GN/mBLPA/BPk9P/b57VHvPW1igpLqUB4gUxuhjDCjQfR5YjGufF/b5DmKn1N8JsUKvXhdf91xH6HPG6ViUYvaPuujFrrIY6LOwoDHExkdgQY3Vg59R7c/ycfelTUXxELtuSzfV/nzVC9Dnm0IsjPFVPu5qdF0dfW6+uewx6NPjw5sh1rWXLu4Sl4zjKW8wntO8hpiXEZyt1/ojBuodoAI+rrlxR3Q0f+odsDHm8FfyaBFZd6S+REREhI76DtgYM1tE+otIrDEmVUTuEZH+xpguImJFZIeIYK06IiIiOqKjTsDW2gl+wq9Uw7EQERH9bfBLcUREVeDwzPvMTPy+M5GvGt0NKajASv1kvVtJ13O2qvY3z2AS1vn3/ACxF9q3h1jalUmqfeqkn6DPi42XQez0S65T7denPwl9ov0Uz/BaTEg6u3EP1Q6IjoY+fb/eA7G3m32l2v0vvxL6vPE8Hldl9nYZ2rg7xCLr4k5RVz8xUbVn3IgJOf++BXdWavr8JojlnKmLKWR/pJOCvAexoEd1CSixErVTJ9+EjtBfba/1aBTcbk/3aIjtHoTjIHO0HosFIzFBcHNP3zo2IgOm6Od41KMLoE+3sB0Qyy4vhNi4hN6qHdC6BfTJmYaj5ZfeOgHxzEmYLHbX9JkQaxWcBrFin3ovE5v0hT5t6/0Kse/G6PHZ7eo10Gfj4ydBrOH72yFW0lInmh14r75qlx+ovnFnrZ0uItNFRJKSkipRIYf+7vgOmIiIyAFOwERERA5wAiYiInKAEzAREZEDNZqEZcrKJWifLkH0TMIXqp39n/lwu/1eTJzIOacbxBp9qpObhl3/M/QZ3AyTvIJLdKWtxoG1oU+GF+sJe/xUtPJNfjHZudDHnyGt+qh2SOEq6OPvuFLL8iCWV64T3QJaJEIfb2wExC7p8r1qPzpoJPQJT8FzOuwnTCr79Oxo1S5+Sj+H5gs/5caqifFaCcrTv+/V9npnqZ0v425IJRYrLd1xweUQi1+8T7XrX4HnY+RJZ0AsJFuPuxtf2gF91pdgwlWAGIjJKT6Vorbuhi6XJeKuRkM76uMKysbn98wwrMD2YzEeQkG5TnTzdGwDfTJOwbLxJ038RbX3XNkE+kTtxoSrPotwh6QFt+nKYQdP168F78LKpC0S1Qy+AyYiInKAEzAREZEDnICJiIgc4ARMRETkQI0mYXnDAiS7fbSKTeiot+HLHIXbnGX1wy3EYifth1i9m3QyTL/QLOjzQgvcWu3OT95R7UENu0AfE4inauBqPIbrP9XbCHr81Ko6JRQrJX2beJFq3zfvLegzqCFWtBIPJgqdvKpEte9fMAf6TFp5CcRyvaGqbfIKoM+ea/AYPu0dCjFbkq7adR5spdoBe2vubz9vsEdyG4eo2LV9x6t22tAEuF1xNCY7lTTCAkflz+hEuPNif4Q+TzcaBbGJP6xXbX/jzhMeDjHzaTTEWjyzWd9O8DhPC8NEpnfq9lPt65Z/D338HZe/cbftDZ0I9u93cJfS++eOhdiyH/Vrvk0hvm4PDMDKXt8NweTMsIJtqt1yXyPVzkpngSo6fvAdMBERkQOcgImIiBzgBExEROTAUdeAjTEJIvKaiNQXESsi062104wxMSIyR0QSRWSHiIyz1h74vfuyHpHScL2utvvCdqodlI9rNIEZuNZzW98vIDYjVe++kvTuzXhfE3Bd799bR6l2iCcF+nia49rxohGNIHbpN3pdL7scixjsx5BsvL2Wak/dPQj6mCBcO/ZEYUGNlRfEqfb1n+FuUhe3xV2h2oTsVe1Fw3tBH+vnTzabiOfBGn2et50XptrFKTX3t5+xIh6fuh97ztbFHsqD8Xb5zbBYSP8uGyCWWaQLpNw57VK8r3/ievq0LboIRr1QLCxhGtbH2EV4XMMWrVbtRgG429VrB3tAbPsDeo35xg8uhj4tglbiMbRpDrFmL+rnvM9rO6DPgDNwh7KeEXpHtOeSx0CfwlgcL6EdcdwFZev8hy2T9dp/8YN8z0HHj8qMxjIRucVa215EeorINcaY9iJyp4gssta2EpFFFW0iIiKqhKNOwNbavdbaVRX/zhWRDSLSSERGishv9fxmicioajpGIiKiv5w/9HmMMSZRRLqKyHIRqW+t/e0zyzQ59BG1v9tMMcYkG2OSywqxnjJRdTh83JUWc9wR0fGn0hOwMaa2iLwvIjdaa9VipLXWivj54uGhn0231iZZa5MCw2r560JU5Q4fd0EhHHdEdPypVCEOY0yQHJp837TWflARTjfGxFtr9xpj4kUk42j34ymxUnu3LqqR1Vlnvxw4We9eIiIyqA0mvty3djjEEm/WSUq9Zm+EPpfVXwqx/56kk1Mmb8CCBWfXwqSlAIMJXdnluvDG5MtvhD79H8ViBy/11bvzPJ50KvQZ+BMWKLggajHEwo0ukpBShsc5+38DIeYN0f16XI474+y+AD/oSH8Ch9GBfTo5LHKV/lsvwM9uOtXFlFsJztWZb6W19GPN6oyJTeF1MXFq6fcnQazVbP0Ou+QOTJYbkrgJYlvP0Ilpjb7G4hb3xL8OMX+2l+lEsNsmXQF9Uq7H7L/W9TNVu+yaNOhTezEm+t3R6DWIRXj0azvNi0VEVk/tgjHRscCL8VISfzfe15678fHk74hS7frf6J9n5fnZSYrIkaO+AzbGGBF5RUQ2WGufOOxHH4vI5Ip/TxaRuVV/eERERH9NlXkH3EdEJonIWmPM6orYXSLyiIi8Y4y5VER2isi4ajlCIiKiv6CjTsDW2m9F/O0ALiIiZ1bt4RAREf098FvpREREDtTobkgiItaj30yXROrk6Ud7vA+38fp5A/55fnu872BdMWvl59gnYwFWtGr6ta7E89rw06HPune3QOxfcasg1nPxdardogATRd5+vz/EPt+qk64GLvkG+iwc3QVi38/AikSvNZuv2ue+hBXBog/gLk25TfR53jMKk2+2Xo9JWEHL8Plp87HeKSpnqi6S5pmPO1xVl/IAI0V1dIJTdkvd58peS+B2P+c0htjywsSj/r7wz/C8rUvpDLHY+b+qduoUrOw09pHJEPu84xsQu3WD3mUoIgQTugJXYSJT4TJ9CQiYgwlQB+6Mg9iYi66G2KpBT6v2oIVToE+0n4pWtffq10gtPwlX28bhOfVmYyZf08/1fRXd4LNj2XJMtiNyhe+AiYiIHOAETERE5AAnYCIiIgdqdA3YBhgpq6Xn/HKfjY5KLa5dvbG3J95XPh56yqOh+r4KsZDCBed/CrEZN43W93MVHsMrMVh4oMjPsTacqx/Q2S98jn2CcNOougF5qn3XP3H9LHsM/r30RVM8rjyr12Tr/oLr0Hv74Lqtp7E+hs11m0GfxHmFEAvMweIpO0fFqHawz2kvz8YdrqqLsSIBJTrXICxDn8udRXXhdlsO4NqnSQ+B2KbL9Fg0xbi+3uPKdRBb84heF06fiM/v622ehViWF5/PsBfqqHa3x1ZAH39Kx+oxvP7mjtAnu2UoxOac+TTElhfrY2j8Cb4+cppASPb21mMxug6u9zb/AMuJGi8W39vbVx9rwNx6qm0P1njaC9ER8R0wERGRA5yAiYiIHOAETERE5AAnYCIiIgfMoZ0Ea0ZYfIJtPlkXhSiuo3+/x099hn+d9w7EPs3qBLHNM9qqtm+C16GYn52Bbpmq2vftxp2WdjzXGmJf/RcTUVK9+gFcdcn10MdzFxY7yH5NF33oeNVa6LMrvw7Eiv7XEGKfPT1NtRcWxkKflwacAbEtj0Srdv05YdCnLAzPX15D/Duu7np9HvZM1kUTUv/xghRt210jW9OE10+wLcfrcVfQUI+7gCI8lEFn/wix1fuwOId5XJ/f8mA8H7mNMSHp5ItXq/bugmjok/NUAsTeePoJiM3N1bs0zbusP/TZclEwxOIX6+MyF+HYzNgfCbFGb+KL643nn1TtZ/b1hT5rx2Ji3/ZJ8artb6esqG2Y2Lb/JHzO4n7S/dLG+oy7u56T4u3VP+6SkpJscnJydf8aOgEYY1Zaa5P8/YzvgImIiBzgBExEROQAJ2AiIiIHjjoBG2MSjDGLjTG/GGPWG2NuqIjfa4zZbYxZXfHf0Oo/XCIior+GypSFKRORW6y1q4wxESKy0hizoOJnT1prp/7ObZWgnHJptDhXxRKe3a7au25oAbe7O/4ciDX6HP92OHiuT5WmPVjBZ9KAryF2y9CLVPvx+TOhz6h2t0DstNUXQKzuvTrRxUZDF0ldiok10ePTVTttTBT0uXHJAojd1eQSiA1YO1G1Y67ByklFLbDyU+Qifew5iZirErUdd5NpsByzZjzFul/9d/QON2n7a+7Dl4AiKzGbSlSs+didqp1/u04EEhFZlN8DYuEZmLSYNUTHIrb72fFnaBrEUsfpSlsDPl0DfV5thklLpy26AWKtXtbPcU5zHPsRm/C40oboKmZtbsVErWFvLYPYu01xK/CBL92u2k0+yfbz+3Bch2XqdhluhiTeEByLTT/Jg5jx6iSseh/WVu30g/zQj44fR52ArbV7RWRvxb9zjTEbRAT3TSMiIqJK+0N/DhpjEkWkq4gsrwhda4xZY4yZYYzB78gcus0UY0yyMSa5tAzruRJVBzXuSjjuiOj4U+kJ2BhTW0TeF5EbrbU5IvK8iLQQkS5y6B3y4/5uZ62dbq1NstYmBQXWOvYjJqoENe6COe6I6PhTqQnYGBMkhybfN621H4iIWGvTrbVea225iLwkIrhgRkRERH4ddQ3YGGNE5BUR2WCtfeKweHzF+rCIyGgRwf3WfNhAI8Uxeju3YTE/q/ZPLx6E210Yigkss2aOgFiTmfrhjJ/2MfR5/Z94u4hMnQjWAIsWySlnrofYrfFfQuzOlLNVO2w/ZpRcPe0niM2+f4hq25xfoE/n4CyIRQzGc/NQ6w9U+78Fg6BPSRQ+9VHn7Vbt7VsbQJ/YnzGh69KXP4LYI89OUO2c7jpRq3RlzVVgswFGiurox3tpw29U+9XHsGrT4Fr7ILbqtm5+foFOXBp66xLosuT23nizfJ0IdnHUBujz5dntIfbvRt9CbMbd+vgjpR706XkzvkSXvnSyansK9kOfKXVWQeyNM06G2PmtdeWnZW+0gT7BuVhVq+wc/TsLsvE1E7sGx+tpL2Olsvf/pyu85fbXW5KWJWNFLSJXKpMF3UdEJonIWmPM6orYXSIywRjTRUSsiOwQkSuq4fiIiE4IxpgpIjJFRKRJEz8bHxP5qEwW9Lci4q926vyqPxwiohOTtXa6iEwXOVQL2vHh0AmAX4ojIiJyoEZ3QwqPS7Btz7lJxWrv1gUb/O1WlNMU36gXxeJxN1iu7ys7EXdsiV+C63p5LXVxgPDdBdAnYD9+6f+XO+IgFlFf96s1BwsP+HuMdVfo9d2iRrhWFpRTArGA7EKIbbgt2qcTnquYH7DgQqDPXdVdngl9Cpvht82Ko3DRPDxdH2tmZ10YYutbT0hhekrN7IZUL8G2Gqd3Qwrbp9cCPV48R0VR+PdpaQQecp3Neuenkkg8H9FrD0CsoIl+jgMLcX09aD+OxU2X4ZiyYfrx+CtUU1gXY/W/1s+xv+c3MB+LrwTk4VjcfLEueiGReLv6X+JrstRnh6245XiuihrVxlgMXhdC9+vfebClHudb5jwhBRnVP+64GxL9hrshERERHWc4ARMRETnACZiIiMgBTsBEREQO1GgSljEmU0R2ikisiGBViRMDj71qNLXWYhZbNeC4c+54OvYaGXdMwqLf/F4SVmUKcVSZ3wa+MSb5SAd0vOOxn3g47tw6kY+dqDrxI2giIiIHOAETERE54GoCnu7o91YFHvuJ60R+/Dx2or+YGk3CIiL6O2ASFv2GlbCIiIiOM5yAiYiIHKjxCdgYM9gYs8kYs9UYc2dN//4/whgzwxiTYYxZd1gsxhizwBizpeL/WL3+OGCMSTDGLDbG/GKMWW+MuaEifkIcf1U6kcacyIk77jjmiP6YGp2AjTEBIvI/ERkiIu1FZIIxpn1NHsMfNFNEBvvE7hSRRdbaViKyqKJ9PCoTkVuste1FpKeIXFNxrk+U468SJ+CYEzlxxx3HHNEfUNPvgHuIyFZr7XZrbYmIvC0iI2v4GCrNWrtURPb7hEeKyKyKf88SkVE1eUyVZa3da61dVfHvXBHZICKN5AQ5/ip0Qo05kRN33HHMEf0xNT0BNxKRlMPaqRWxE0l9a+3ein+niUh9lwdTGcaYRBHpKiLL5QQ8/mP0VxhzIifY8/Y3H3NElcIkrGNgD32H67j+HpcxpraIvC8iN1prcw7/2Ylw/ISO9+eNY46ocmp6At4tIgmHtRtXxE4k6caYeBGRiv9nOD6eIzLGBMmhC+Gb1toPKsInzPFXkb/CmBM5QZ43jjmiyqvpCXiFiLQyxjQzxgSLyHgR+biGj+FYfSwikyv+PVlE5jo8liMyxhgReUVENlhrnzjsRyfE8Vehv8KYEzkBnjeOOaI/pqZ3QyozxlwrIl+ISICIzLDWrq/JY/gjjDGzRaS/iMQaY1JF5B4ReURE3jHGXCqHtrgb5+4If1cfEZkkImuNMasrYnfJiXP8VeJEG3MiJ/S445gj+gNYipKIqIqxFCX9hqUoiYiIjjOcgImIiBzgBExEROQAJ2AiIiIHOAETERE5wAmYiIjIAU7AREREDnACJiIicoATMBERkQOcgImIiBzgBExEROQAJ2AiIiIHOAETERE5wAmYiIjIAU7AREREDnACJiIicoATMBERkQOcgImIiBzgBExEROQAJ2AioipgjJlijEk2xiRnZma6Phw6AXACJiKqAtba6dbaJGttUlxcnOvDoRMAJ2AiIiIHOAETERE5wAmYiIjIAU7AREREDnACJiIicoATMBERkQOcgImIiBzgBExEROQAJ2AiIiIHOAETERE5wAmYiIjIAU7AREREDnACJiIicoATMBERkQOcgImIiBzgBExEROQAJ2AiIiIHOAETERE5wAmYiIjIAU7AREREDhhrretjICL6SzHGZIrIThGJFZEsx4fzZ/HYq0ZTa22cvx9wAiYiqibGmGRrbZLr4/gzeOzVjx9BExEROcAJmIiIyAFOwERE1We66wM4Bjz2asY1YCIiIgf4DpiIiMgBTsBEREQOcAImIqoGxpjBxphNxpitxpg7XR/P7zHGzDDGZBhj1h0WizHGLDDGbKn4fx2Xx3gkxpgEY8xiY8wvxpj1xpgbKuLH/fFzAiYiqmLGmAAR+Z+IDBGR9iIywRjT3u1R/a6ZIjLYJ3aniCyy1rYSkUUV7eNRmYjcYq1tLyI9ReSainN93B8/J2AioqrXQ0S2Wmu3W2tLRORtERnp+JiOyFq7VET2+4RHisisin/PEpFRNXlMlWWt3WutXVXx71wR2SAijeQEOH5OwEREVa+RiKQc1k6tiJ1I6ltr91b8O01E6rs8mMowxiSKSFcRWS4nwPFzAiYiot9lD31f9bj+zqoxpraIvC8iN1prcw7/2fF6/JyAiYiq3m4RSTis3bgidiJJN8bEi4hU/D/D8fEckTEmSA5Nvm9aaz+oCB/3x88JmIio6q0QkVbGmGbGmGARGS8iHzs+pj/qYxGZXPHvySIy1+GxHJExxojIKyKywVr7xGE/Ou6Pn5WwiIiqgTFmqIg8JSIBIjLDWvug2yM6MmPMbBHpL4e28UsXkXtE5CMReUdEmsihrRXHWWt9E7WcM8b0FZFvRGStiJRXhO+SQ+vAx/XxcwImIiJygB9BExEROcAJmIiIyAFOwERERA5wAiYiInKAEzAREZEDnICJiIgc4ARMRETkwP8DDiuqm6BZzukAAAAASUVORK5CYII=\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "<Figure size 576x720 with 6 Axes>",
+      "image/png": "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\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "<Figure size 576x720 with 6 Axes>",
+      "image/png": "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\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
+      "\u001B[0;32m<ipython-input-5-0592df1e05e4>\u001B[0m in \u001B[0;36m<module>\u001B[0;34m\u001B[0m\n\u001B[1;32m      1\u001B[0m \u001B[0;32mwith\u001B[0m \u001B[0mexperiment\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstart\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m----> 2\u001B[0;31m     \u001B[0mconf\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mrun\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m      3\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36mrun\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    246\u001B[0m         \u001B[0m_\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtrainer\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    247\u001B[0m         \u001B[0;32mfor\u001B[0m \u001B[0m_\u001B[0m \u001B[0;32min\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtraining_loop\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 248\u001B[0;31m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mrun_step\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    249\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    250\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0msample\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36mrun_step\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    234\u001B[0m             \u001B[0;32mwith\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mmode\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mupdate\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mis_train\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;32mTrue\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    235\u001B[0m                 \u001B[0;32mwith\u001B[0m \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnamespace\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'train'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 236\u001B[0;31m                     \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtrainer\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    237\u001B[0m             \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mvalidator\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    238\u001B[0m                 \u001B[0;32mwith\u001B[0m \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnamespace\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'valid'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36m__call__\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    136\u001B[0m                 \u001B[0msm\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mon_epoch_start\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    137\u001B[0m         \u001B[0;32mwith\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mset_grad_enabled\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mmode\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mis_train\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 138\u001B[0;31m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__iterate\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    139\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    140\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_batch_index\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mcompleted\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36m__iterate\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    149\u001B[0m                 \u001B[0mbatch\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mnext\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__iterable\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    150\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 151\u001B[0;31m                 \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstep\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mbatch\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_batch_index\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    152\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    153\u001B[0m                 \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_batch_index\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstep\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_nn/gan/original/experiment.py\u001B[0m in \u001B[0;36mstep\u001B[0;34m(self, batch, batch_idx)\u001B[0m\n\u001B[1;32m    149\u001B[0m             \u001B[0;31m# Log stuff\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    150\u001B[0m             \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0madd\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'generated'\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mgenerated_images\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0;36m0\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;36m5\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 151\u001B[0;31m             \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0madd\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m\"loss.generator.\"\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mloss\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    152\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    153\u001B[0m             \u001B[0;31m# Train\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml/tracker.py\u001B[0m in \u001B[0;36madd\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m    131\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0;32mnot\u001B[0m \u001B[0misinstance\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0margs\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0;36m0\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mstr\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    132\u001B[0m             \u001B[0;32mraise\u001B[0m \u001B[0mTypeError\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'tracker.add should be called as add(name, value), add(dictionary) or add(k=v,k2=v2...)'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 133\u001B[0;31m         \u001B[0m_internal\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstore\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0margs\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0;36m0\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0margs\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0;36m1\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    134\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    135\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml/internal/tracker/__init__.py\u001B[0m in \u001B[0;36mstore\u001B[0;34m(self, key, value)\u001B[0m\n\u001B[1;32m    165\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    166\u001B[0m         \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_create_indicator\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mkey\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mvalue\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 167\u001B[0;31m         \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mindicators\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0mkey\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mcollect_value\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mvalue\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    168\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    169\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0mnew_line\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml/internal/tracker/indicators/numeric.py\u001B[0m in \u001B[0;36mcollect_value\u001B[0;34m(self, value)\u001B[0m\n\u001B[1;32m     79\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     80\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0mcollect_value\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mvalue\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 81\u001B[0;31m         \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_values\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mappend\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mto_numpy\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mvalue\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mravel\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     82\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     83\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0mclear\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml/internal/util/values.py\u001B[0m in \u001B[0;36mto_numpy\u001B[0;34m(value)\u001B[0m\n\u001B[1;32m     20\u001B[0m             \u001B[0;32mreturn\u001B[0m \u001B[0mvalue\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdata\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mcpu\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnumpy\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     21\u001B[0m         \u001B[0;32melif\u001B[0m \u001B[0misinstance\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mvalue\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mTensor\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 22\u001B[0;31m             \u001B[0;32mreturn\u001B[0m \u001B[0mvalue\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdata\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mcpu\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnumpy\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     23\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     24\u001B[0m     \u001B[0;32mraise\u001B[0m \u001B[0mValueError\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34mf\"Unknown type {type(value)}\"\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/training_loop.py\u001B[0m in \u001B[0;36m__handler\u001B[0;34m(self, sig, frame)\u001B[0m\n\u001B[1;32m    162\u001B[0m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__finish\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    163\u001B[0m             \u001B[0mlogger\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mlog\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'Killing loop...'\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mText\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdanger\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 164\u001B[0;31m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mold_handler\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0msig\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mframe\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    165\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    166\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0m__str__\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m: "
+     ]
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "oBXXlP2b7XZO"
+   },
+   "source": [
+    ""
+   ],
+   "execution_count": null,
+   "outputs": []
+  }
+ ]
+}
\ No newline at end of file
diff --git a/labml_nn/gan/original/experiment.ipynb b/labml_nn/gan/original/experiment.ipynb
new file mode 100644
index 00000000..424b4d23
--- /dev/null
+++ b/labml_nn/gan/original/experiment.ipynb
@@ -0,0 +1,264 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+  "colab": {
+   "name": "Cycle GAN",
+   "provenance": [],
+   "collapsed_sections": [],
+   "toc_visible": true
+  },
+  "kernelspec": {
+   "name": "python3",
+   "language": "python",
+   "display_name": "Python 3"
+  },
+  "accelerator": "GPU"
+ },
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "AYV_dMVDxyc2"
+   },
+   "source": [
+    "[![Github](https://img.shields.io/github/stars/lab-ml/nn?style=social)](https://github.com/lab-ml/nn)\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/lab-ml/nn/blob/master/labml_nn/gan/original/experiment.ipynb)\n",
+    "\n",
+    "## DCGAN\n",
+    "\n",
+    "This is an experiment training DCGAN model."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "AahG_i2y5tY9"
+   },
+   "source": [
+    "Install the `labml-nn` package"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "ZCzmCrAIVg0L",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "outputId": "2fe2685f-731c-4c47-854e-a4f00e485281"
+   },
+   "source": [
+    "!pip install labml-nn"
+   ],
+   "execution_count": 1,
+   "outputs": [
+    {
+     "output_type": "stream",
+     "text": [
+      "Collecting labml-nn\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/9d/bb/a7a6f69ab6e21de2398b5f6b0b2bb47b430e4a20ae2c8710c489e02813be/labml_nn-0.4.81-py3-none-any.whl (118kB)\n",
+      "\r\u001B[K     |██▊                             | 10kB 22.6MB/s eta 0:00:01\r\u001B[K     |█████▌                          | 20kB 14.6MB/s eta 0:00:01\r\u001B[K     |████████▎                       | 30kB 12.9MB/s eta 0:00:01\r\u001B[K     |███████████                     | 40kB 12.1MB/s eta 0:00:01\r\u001B[K     |█████████████▉                  | 51kB 8.2MB/s eta 0:00:01\r\u001B[K     |████████████████▋               | 61kB 8.7MB/s eta 0:00:01\r\u001B[K     |███████████████████▍            | 71kB 8.9MB/s eta 0:00:01\r\u001B[K     |██████████████████████▏         | 81kB 9.9MB/s eta 0:00:01\r\u001B[K     |█████████████████████████       | 92kB 8.9MB/s eta 0:00:01\r\u001B[K     |███████████████████████████▊    | 102kB 8.0MB/s eta 0:00:01\r\u001B[K     |██████████████████████████████▌ | 112kB 8.0MB/s eta 0:00:01\r\u001B[K     |████████████████████████████████| 122kB 8.0MB/s \n",
+      "\u001B[?25hRequirement already satisfied: torch in /usr/local/lib/python3.6/dist-packages (from labml-nn) (1.7.0+cu101)\n",
+      "Collecting labml-helpers>=0.4.72\n",
+      "  Downloading https://files.pythonhosted.org/packages/ec/58/2b7dcfde4565134ad97cdfe96ad7070fef95c37be2cbc066b608c9ae5c1d/labml_helpers-0.4.72-py3-none-any.whl\n",
+      "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from labml-nn) (1.19.5)\n",
+      "Collecting labml>=0.4.94\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/99/b2/3a424548d74a88ce565b38f6b7e707e7c2f00bf8c7c575a1c251807e4896/labml-0.4.94-py3-none-any.whl (99kB)\n",
+      "\u001B[K     |████████████████████████████████| 102kB 8.2MB/s \n",
+      "\u001B[?25hCollecting einops\n",
+      "  Downloading https://files.pythonhosted.org/packages/5d/a0/9935e030634bf60ecd572c775f64ace82ceddf2f504a5fd3902438f07090/einops-0.3.0-py2.py3-none-any.whl\n",
+      "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.6/dist-packages (from torch->labml-nn) (3.7.4.3)\n",
+      "Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from torch->labml-nn) (0.16.0)\n",
+      "Requirement already satisfied: dataclasses in /usr/local/lib/python3.6/dist-packages (from torch->labml-nn) (0.8)\n",
+      "Collecting gitpython\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/d7/cb/ec98155c501b68dcb11314c7992cd3df6dce193fd763084338a117967d53/GitPython-3.1.12-py3-none-any.whl (159kB)\n",
+      "\u001B[K     |████████████████████████████████| 163kB 9.9MB/s \n",
+      "\u001B[?25hRequirement already satisfied: pyyaml in /usr/local/lib/python3.6/dist-packages (from labml>=0.4.94->labml-nn) (3.13)\n",
+      "Collecting gitdb<5,>=4.0.1\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/48/11/d1800bca0a3bae820b84b7d813ad1eff15a48a64caea9c823fc8c1b119e8/gitdb-4.0.5-py3-none-any.whl (63kB)\n",
+      "\u001B[K     |████████████████████████████████| 71kB 8.6MB/s \n",
+      "\u001B[?25hCollecting smmap<4,>=3.0.1\n",
+      "  Downloading https://files.pythonhosted.org/packages/d5/1e/6130925131f639b2acde0f7f18b73e33ce082ff2d90783c436b52040af5a/smmap-3.0.5-py2.py3-none-any.whl\n",
+      "Installing collected packages: smmap, gitdb, gitpython, labml, labml-helpers, einops, labml-nn\n",
+      "Successfully installed einops-0.3.0 gitdb-4.0.5 gitpython-3.1.12 labml-0.4.94 labml-helpers-0.4.72 labml-nn-0.4.81 smmap-3.0.5\n"
+     ],
+     "name": "stdout"
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "SE2VUQ6L5zxI"
+   },
+   "source": [
+    "Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "0hJXx_g0wS2C"
+   },
+   "source": [
+    "\n",
+    "from labml import experiment\n",
+    "from labml_nn.gan.original.experiment import Configs"
+   ],
+   "execution_count": 1,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Lpggo0wM6qb-"
+   },
+   "source": [
+    "Create an experiment"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "bFcr9k-l4cAg"
+   },
+   "source": [
+    "experiment.create(name=\"mnist_gan\")"
+   ],
+   "execution_count": 2,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "-OnHLi626tJt"
+   },
+   "source": [
+    "Initialize configurations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "Piz0c5f44hRo"
+   },
+   "source": [
+    "conf = Configs()"
+   ],
+   "execution_count": 3,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "wwMzCqpD6vkL"
+   },
+   "source": [
+    "Set experiment configurations and assign a configurations dictionary to override configurations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 17
+    },
+    "id": "e6hmQhTw4nks",
+    "outputId": "4be767af-0ebd-4c35-8da0-0e532495e037"
+   },
+   "source": [
+    "experiment.configs(conf,\n",
+    "                   {'label_smoothing': 0.01})"
+   ],
+   "execution_count": 4,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<IPython.core.display.HTML object>",
+      "text/html": "<pre style=\"overflow-x: scroll;\"></pre>"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "KJZRf8527GxL"
+   },
+   "source": [
+    "Start the experiment and run the training loop."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 649
+    },
+    "id": "aIAWo7Fw5DR8",
+    "outputId": "e3b02247-8ff9-47b5-8f52-49c9e3b8377f"
+   },
+   "source": [
+    "with experiment.start():\n",
+    "    conf.run()"
+   ],
+   "execution_count": 5,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<IPython.core.display.HTML object>",
+      "text/html": "<pre style=\"overflow-x: scroll;\"></pre>"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "<Figure size 576x720 with 6 Axes>",
+      "image/png": "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\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
+      "\u001B[0;32m<ipython-input-5-0592df1e05e4>\u001B[0m in \u001B[0;36m<module>\u001B[0;34m\u001B[0m\n\u001B[1;32m      1\u001B[0m \u001B[0;32mwith\u001B[0m \u001B[0mexperiment\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstart\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m----> 2\u001B[0;31m     \u001B[0mconf\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mrun\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m      3\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36mrun\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    246\u001B[0m         \u001B[0m_\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtrainer\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    247\u001B[0m         \u001B[0;32mfor\u001B[0m \u001B[0m_\u001B[0m \u001B[0;32min\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtraining_loop\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 248\u001B[0;31m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mrun_step\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    249\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    250\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0msample\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36mrun_step\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    234\u001B[0m             \u001B[0;32mwith\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mmode\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mupdate\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mis_train\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;32mTrue\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    235\u001B[0m                 \u001B[0;32mwith\u001B[0m \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnamespace\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'train'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 236\u001B[0;31m                     \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtrainer\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    237\u001B[0m             \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mvalidator\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    238\u001B[0m                 \u001B[0;32mwith\u001B[0m \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnamespace\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'valid'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36m__call__\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    136\u001B[0m                 \u001B[0msm\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mon_epoch_start\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    137\u001B[0m         \u001B[0;32mwith\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mset_grad_enabled\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mmode\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mis_train\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 138\u001B[0;31m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__iterate\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    139\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    140\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_batch_index\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mcompleted\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36m__iterate\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    149\u001B[0m                 \u001B[0mbatch\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mnext\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__iterable\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    150\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 151\u001B[0;31m                 \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstep\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mbatch\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_batch_index\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    152\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    153\u001B[0m                 \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_batch_index\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstep\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_nn/gan/original/experiment.py\u001B[0m in \u001B[0;36mstep\u001B[0;34m(self, batch, batch_idx)\u001B[0m\n\u001B[1;32m    157\u001B[0m                 \u001B[0;32mif\u001B[0m \u001B[0mbatch_idx\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mis_last\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    158\u001B[0m                     \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0madd\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'generator'\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mgenerator\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 159\u001B[0;31m                 \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mgenerator_optimizer\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstep\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    160\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    161\u001B[0m         \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0msave\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/autograd/grad_mode.py\u001B[0m in \u001B[0;36mdecorate_context\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m     24\u001B[0m         \u001B[0;32mdef\u001B[0m \u001B[0mdecorate_context\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m*\u001B[0m\u001B[0margs\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m**\u001B[0m\u001B[0mkwargs\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     25\u001B[0m             \u001B[0;32mwith\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__class__\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 26\u001B[0;31m                 \u001B[0;32mreturn\u001B[0m \u001B[0mfunc\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m*\u001B[0m\u001B[0margs\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m**\u001B[0m\u001B[0mkwargs\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     27\u001B[0m         \u001B[0;32mreturn\u001B[0m \u001B[0mcast\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mF\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdecorate_context\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     28\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/optim/adam.py\u001B[0m in \u001B[0;36mstep\u001B[0;34m(self, closure)\u001B[0m\n\u001B[1;32m    106\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    107\u001B[0m             \u001B[0mbeta1\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mbeta2\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mgroup\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0;34m'betas'\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 108\u001B[0;31m             F.adam(params_with_grad,\n\u001B[0m\u001B[1;32m    109\u001B[0m                    \u001B[0mgrads\u001B[0m\u001B[0;34m,\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    110\u001B[0m                    \u001B[0mexp_avgs\u001B[0m\u001B[0;34m,\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/optim/functional.py\u001B[0m in \u001B[0;36madam\u001B[0;34m(params, grads, exp_avgs, exp_avg_sqs, max_exp_avg_sqs, state_steps, amsgrad, beta1, beta2, lr, weight_decay, eps)\u001B[0m\n\u001B[1;32m     92\u001B[0m             \u001B[0mdenom\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0;34m(\u001B[0m\u001B[0mmax_exp_avg_sq\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0msqrt\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m \u001B[0;34m/\u001B[0m \u001B[0mmath\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0msqrt\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mbias_correction2\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0madd_\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0meps\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     93\u001B[0m         \u001B[0;32melse\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 94\u001B[0;31m             \u001B[0mdenom\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0;34m(\u001B[0m\u001B[0mexp_avg_sq\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0msqrt\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m \u001B[0;34m/\u001B[0m \u001B[0mmath\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0msqrt\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mbias_correction2\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0madd_\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0meps\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     95\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     96\u001B[0m         \u001B[0mstep_size\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mlr\u001B[0m \u001B[0;34m/\u001B[0m \u001B[0mbias_correction1\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/training_loop.py\u001B[0m in \u001B[0;36m__handler\u001B[0;34m(self, sig, frame)\u001B[0m\n\u001B[1;32m    162\u001B[0m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__finish\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    163\u001B[0m             \u001B[0mlogger\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mlog\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'Killing loop...'\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mText\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdanger\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 164\u001B[0;31m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mold_handler\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0msig\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mframe\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    165\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    166\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0m__str__\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m: "
+     ]
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "oBXXlP2b7XZO"
+   },
+   "source": [
+    ""
+   ],
+   "execution_count": null,
+   "outputs": []
+  }
+ ]
+}
\ No newline at end of file
diff --git a/labml_nn/gan/simple_mnist_experiment.py b/labml_nn/gan/original/experiment.py
similarity index 98%
rename from labml_nn/gan/simple_mnist_experiment.py
rename to labml_nn/gan/original/experiment.py
index 4dabbc72..c522b777 100644
--- a/labml_nn/gan/simple_mnist_experiment.py
+++ b/labml_nn/gan/original/experiment.py
@@ -85,6 +85,7 @@ class Discriminator(Module):
 
 class Configs(MNISTConfigs, TrainValidConfigs):
     device: torch.device = DeviceConfigs()
+    dataset_transforms = 'mnist_gan_transforms'
     epochs: int = 10
 
     is_save_models = True
@@ -146,7 +147,7 @@ class Configs(MNISTConfigs, TrainValidConfigs):
             loss = self.generator_loss(logits)
 
             # Log stuff
-            tracker.add('generated', generated_images[0:5])
+            tracker.add('generated', generated_images[0:6])
             tracker.add("loss.generator.", loss)
 
             # Train
@@ -161,7 +162,7 @@ class Configs(MNISTConfigs, TrainValidConfigs):
 
 
 @option(Configs.dataset_transforms)
-def mnist_transforms():
+def mnist_gan_transforms():
     return transforms.Compose([
         transforms.ToTensor(),
         transforms.Normalize((0.5,), (0.5,))
diff --git a/labml_nn/gan/wasserstein/experiment.ipynb b/labml_nn/gan/wasserstein/experiment.ipynb
new file mode 100644
index 00000000..462905b2
--- /dev/null
+++ b/labml_nn/gan/wasserstein/experiment.ipynb
@@ -0,0 +1,288 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+  "colab": {
+   "name": "Cycle GAN",
+   "provenance": [],
+   "collapsed_sections": [],
+   "toc_visible": true
+  },
+  "kernelspec": {
+   "name": "python3",
+   "language": "python",
+   "display_name": "Python 3"
+  },
+  "accelerator": "GPU"
+ },
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "AYV_dMVDxyc2"
+   },
+   "source": [
+    "[![Github](https://img.shields.io/github/stars/lab-ml/nn?style=social)](https://github.com/lab-ml/nn)\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/lab-ml/nn/blob/master/labml_nn/gan/wasserstein/experiment.ipynb)\n",
+    "\n",
+    "## DCGAN\n",
+    "\n",
+    "This is an experiment training DCGAN model."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "AahG_i2y5tY9"
+   },
+   "source": [
+    "Install the `labml-nn` package"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "ZCzmCrAIVg0L",
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "outputId": "2fe2685f-731c-4c47-854e-a4f00e485281"
+   },
+   "source": [
+    "!pip install labml-nn"
+   ],
+   "execution_count": 1,
+   "outputs": [
+    {
+     "output_type": "stream",
+     "text": [
+      "Collecting labml-nn\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/9d/bb/a7a6f69ab6e21de2398b5f6b0b2bb47b430e4a20ae2c8710c489e02813be/labml_nn-0.4.81-py3-none-any.whl (118kB)\n",
+      "\r\u001B[K     |██▊                             | 10kB 22.6MB/s eta 0:00:01\r\u001B[K     |█████▌                          | 20kB 14.6MB/s eta 0:00:01\r\u001B[K     |████████▎                       | 30kB 12.9MB/s eta 0:00:01\r\u001B[K     |███████████                     | 40kB 12.1MB/s eta 0:00:01\r\u001B[K     |█████████████▉                  | 51kB 8.2MB/s eta 0:00:01\r\u001B[K     |████████████████▋               | 61kB 8.7MB/s eta 0:00:01\r\u001B[K     |███████████████████▍            | 71kB 8.9MB/s eta 0:00:01\r\u001B[K     |██████████████████████▏         | 81kB 9.9MB/s eta 0:00:01\r\u001B[K     |█████████████████████████       | 92kB 8.9MB/s eta 0:00:01\r\u001B[K     |███████████████████████████▊    | 102kB 8.0MB/s eta 0:00:01\r\u001B[K     |██████████████████████████████▌ | 112kB 8.0MB/s eta 0:00:01\r\u001B[K     |████████████████████████████████| 122kB 8.0MB/s \n",
+      "\u001B[?25hRequirement already satisfied: torch in /usr/local/lib/python3.6/dist-packages (from labml-nn) (1.7.0+cu101)\n",
+      "Collecting labml-helpers>=0.4.72\n",
+      "  Downloading https://files.pythonhosted.org/packages/ec/58/2b7dcfde4565134ad97cdfe96ad7070fef95c37be2cbc066b608c9ae5c1d/labml_helpers-0.4.72-py3-none-any.whl\n",
+      "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from labml-nn) (1.19.5)\n",
+      "Collecting labml>=0.4.94\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/99/b2/3a424548d74a88ce565b38f6b7e707e7c2f00bf8c7c575a1c251807e4896/labml-0.4.94-py3-none-any.whl (99kB)\n",
+      "\u001B[K     |████████████████████████████████| 102kB 8.2MB/s \n",
+      "\u001B[?25hCollecting einops\n",
+      "  Downloading https://files.pythonhosted.org/packages/5d/a0/9935e030634bf60ecd572c775f64ace82ceddf2f504a5fd3902438f07090/einops-0.3.0-py2.py3-none-any.whl\n",
+      "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.6/dist-packages (from torch->labml-nn) (3.7.4.3)\n",
+      "Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from torch->labml-nn) (0.16.0)\n",
+      "Requirement already satisfied: dataclasses in /usr/local/lib/python3.6/dist-packages (from torch->labml-nn) (0.8)\n",
+      "Collecting gitpython\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/d7/cb/ec98155c501b68dcb11314c7992cd3df6dce193fd763084338a117967d53/GitPython-3.1.12-py3-none-any.whl (159kB)\n",
+      "\u001B[K     |████████████████████████████████| 163kB 9.9MB/s \n",
+      "\u001B[?25hRequirement already satisfied: pyyaml in /usr/local/lib/python3.6/dist-packages (from labml>=0.4.94->labml-nn) (3.13)\n",
+      "Collecting gitdb<5,>=4.0.1\n",
+      "\u001B[?25l  Downloading https://files.pythonhosted.org/packages/48/11/d1800bca0a3bae820b84b7d813ad1eff15a48a64caea9c823fc8c1b119e8/gitdb-4.0.5-py3-none-any.whl (63kB)\n",
+      "\u001B[K     |████████████████████████████████| 71kB 8.6MB/s \n",
+      "\u001B[?25hCollecting smmap<4,>=3.0.1\n",
+      "  Downloading https://files.pythonhosted.org/packages/d5/1e/6130925131f639b2acde0f7f18b73e33ce082ff2d90783c436b52040af5a/smmap-3.0.5-py2.py3-none-any.whl\n",
+      "Installing collected packages: smmap, gitdb, gitpython, labml, labml-helpers, einops, labml-nn\n",
+      "Successfully installed einops-0.3.0 gitdb-4.0.5 gitpython-3.1.12 labml-0.4.94 labml-helpers-0.4.72 labml-nn-0.4.81 smmap-3.0.5\n"
+     ],
+     "name": "stdout"
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "SE2VUQ6L5zxI"
+   },
+   "source": [
+    "Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "0hJXx_g0wS2C"
+   },
+   "source": [
+    "\n",
+    "from labml import experiment\n",
+    "from labml_nn.gan.wasserstein.experiment import Configs"
+   ],
+   "execution_count": 14,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Lpggo0wM6qb-"
+   },
+   "source": [
+    "Create an experiment"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "bFcr9k-l4cAg"
+   },
+   "source": [
+    "experiment.create(name=\"mnist_wgan\")"
+   ],
+   "execution_count": 15,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "-OnHLi626tJt"
+   },
+   "source": [
+    "Initialize configurations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "Piz0c5f44hRo"
+   },
+   "source": [
+    "conf = Configs()"
+   ],
+   "execution_count": 16,
+   "outputs": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "wwMzCqpD6vkL"
+   },
+   "source": [
+    "Set experiment configurations and assign a configurations dictionary to override configurations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 17
+    },
+    "id": "e6hmQhTw4nks",
+    "outputId": "4be767af-0ebd-4c35-8da0-0e532495e037"
+   },
+   "source": [
+    "experiment.configs(conf,\n",
+    "                   {\n",
+    "                       'discriminator': 'cnn',\n",
+    "                       'generator': 'cnn',\n",
+    "                       'label_smoothing': 0.01,\n",
+    "                       'generator_loss': 'wasserstein',\n",
+    "                       'discriminator_loss': 'wasserstein',\n",
+    "                   })"
+   ],
+   "execution_count": 17,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<IPython.core.display.HTML object>",
+      "text/html": "<pre style=\"overflow-x: scroll;\"></pre>"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "KJZRf8527GxL"
+   },
+   "source": [
+    "Start the experiment and run the training loop."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 649
+    },
+    "id": "aIAWo7Fw5DR8",
+    "outputId": "e3b02247-8ff9-47b5-8f52-49c9e3b8377f"
+   },
+   "source": [
+    "with experiment.start():\n",
+    "    conf.run()"
+   ],
+   "execution_count": 18,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "<IPython.core.display.HTML object>",
+      "text/html": "<pre style=\"overflow-x: scroll;\"></pre>"
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "<Figure size 576x720 with 6 Axes>",
+      "image/png": "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\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": "<Figure size 576x720 with 6 Axes>",
+      "image/png": "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\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
+      "\u001B[0;32m<ipython-input-18-0592df1e05e4>\u001B[0m in \u001B[0;36m<module>\u001B[0;34m\u001B[0m\n\u001B[1;32m      1\u001B[0m \u001B[0;32mwith\u001B[0m \u001B[0mexperiment\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstart\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m----> 2\u001B[0;31m     \u001B[0mconf\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mrun\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m      3\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36mrun\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    246\u001B[0m         \u001B[0m_\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtrainer\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    247\u001B[0m         \u001B[0;32mfor\u001B[0m \u001B[0m_\u001B[0m \u001B[0;32min\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtraining_loop\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 248\u001B[0;31m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mrun_step\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    249\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    250\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0msample\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36mrun_step\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    234\u001B[0m             \u001B[0;32mwith\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mmode\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mupdate\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mis_train\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;32mTrue\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    235\u001B[0m                 \u001B[0;32mwith\u001B[0m \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnamespace\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'train'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 236\u001B[0;31m                     \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtrainer\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    237\u001B[0m             \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mvalidator\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    238\u001B[0m                 \u001B[0;32mwith\u001B[0m \u001B[0mtracker\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnamespace\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'valid'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36m__call__\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    136\u001B[0m                 \u001B[0msm\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mon_epoch_start\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    137\u001B[0m         \u001B[0;32mwith\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mset_grad_enabled\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mmode\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mis_train\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 138\u001B[0;31m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__iterate\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    139\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    140\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_batch_index\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mcompleted\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/train_valid.py\u001B[0m in \u001B[0;36m__iterate\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    147\u001B[0m                 \u001B[0mmonit\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mprogress\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;36m0\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    148\u001B[0m             \u001B[0;32mwhile\u001B[0m \u001B[0;32mnot\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_batch_index\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0miteration_completed\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 149\u001B[0;31m                 \u001B[0mbatch\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mnext\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__iterable\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    150\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    151\u001B[0m                 \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstep\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mbatch\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_batch_index\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/utils/data/dataloader.py\u001B[0m in \u001B[0;36m__next__\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    433\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_sampler_iter\u001B[0m \u001B[0;32mis\u001B[0m \u001B[0;32mNone\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    434\u001B[0m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_reset\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 435\u001B[0;31m         \u001B[0mdata\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_next_data\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    436\u001B[0m         \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_num_yielded\u001B[0m \u001B[0;34m+=\u001B[0m \u001B[0;36m1\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    437\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_dataset_kind\u001B[0m \u001B[0;34m==\u001B[0m \u001B[0m_DatasetKind\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mIterable\u001B[0m \u001B[0;32mand\u001B[0m\u001B[0;31m \u001B[0m\u001B[0;31m\\\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/utils/data/dataloader.py\u001B[0m in \u001B[0;36m_next_data\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m    473\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0m_next_data\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    474\u001B[0m         \u001B[0mindex\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_next_index\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m  \u001B[0;31m# may raise StopIteration\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 475\u001B[0;31m         \u001B[0mdata\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_dataset_fetcher\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mfetch\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mindex\u001B[0m\u001B[0;34m)\u001B[0m  \u001B[0;31m# may raise StopIteration\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    476\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_pin_memory\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    477\u001B[0m             \u001B[0mdata\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0m_utils\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mpin_memory\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mpin_memory\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mdata\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py\u001B[0m in \u001B[0;36mfetch\u001B[0;34m(self, possibly_batched_index)\u001B[0m\n\u001B[1;32m     42\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0mfetch\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mpossibly_batched_index\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     43\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mauto_collation\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 44\u001B[0;31m             \u001B[0mdata\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0;34m[\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdataset\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0midx\u001B[0m\u001B[0;34m]\u001B[0m \u001B[0;32mfor\u001B[0m \u001B[0midx\u001B[0m \u001B[0;32min\u001B[0m \u001B[0mpossibly_batched_index\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     45\u001B[0m         \u001B[0;32melse\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     46\u001B[0m             \u001B[0mdata\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdataset\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0mpossibly_batched_index\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py\u001B[0m in \u001B[0;36m<listcomp>\u001B[0;34m(.0)\u001B[0m\n\u001B[1;32m     42\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0mfetch\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mpossibly_batched_index\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     43\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mauto_collation\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 44\u001B[0;31m             \u001B[0mdata\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0;34m[\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdataset\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0midx\u001B[0m\u001B[0;34m]\u001B[0m \u001B[0;32mfor\u001B[0m \u001B[0midx\u001B[0m \u001B[0;32min\u001B[0m \u001B[0mpossibly_batched_index\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     45\u001B[0m         \u001B[0;32melse\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     46\u001B[0m             \u001B[0mdata\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdataset\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0mpossibly_batched_index\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torchvision/datasets/mnist.py\u001B[0m in \u001B[0;36m__getitem__\u001B[0;34m(self, index)\u001B[0m\n\u001B[1;32m    104\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    105\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtransform\u001B[0m \u001B[0;32mis\u001B[0m \u001B[0;32mnot\u001B[0m \u001B[0;32mNone\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 106\u001B[0;31m             \u001B[0mimg\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtransform\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mimg\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    107\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    108\u001B[0m         \u001B[0;32mif\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtarget_transform\u001B[0m \u001B[0;32mis\u001B[0m \u001B[0;32mnot\u001B[0m \u001B[0;32mNone\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torchvision/transforms/transforms.py\u001B[0m in \u001B[0;36m__call__\u001B[0;34m(self, img)\u001B[0m\n\u001B[1;32m     65\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0m__call__\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mimg\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     66\u001B[0m         \u001B[0;32mfor\u001B[0m \u001B[0mt\u001B[0m \u001B[0;32min\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mtransforms\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 67\u001B[0;31m             \u001B[0mimg\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mt\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mimg\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     68\u001B[0m         \u001B[0;32mreturn\u001B[0m \u001B[0mimg\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     69\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/nn/modules/module.py\u001B[0m in \u001B[0;36m_call_impl\u001B[0;34m(self, *input, **kwargs)\u001B[0m\n\u001B[1;32m    725\u001B[0m             \u001B[0mresult\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m_slow_forward\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m*\u001B[0m\u001B[0minput\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m**\u001B[0m\u001B[0mkwargs\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    726\u001B[0m         \u001B[0;32melse\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 727\u001B[0;31m             \u001B[0mresult\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mforward\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m*\u001B[0m\u001B[0minput\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m**\u001B[0m\u001B[0mkwargs\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    728\u001B[0m         for hook in itertools.chain(\n\u001B[1;32m    729\u001B[0m                 \u001B[0m_global_forward_hooks\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mvalues\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m,\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torchvision/transforms/transforms.py\u001B[0m in \u001B[0;36mforward\u001B[0;34m(self, tensor)\u001B[0m\n\u001B[1;32m    224\u001B[0m             \u001B[0mTensor\u001B[0m\u001B[0;34m:\u001B[0m \u001B[0mNormalized\u001B[0m \u001B[0mTensor\u001B[0m \u001B[0mimage\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    225\u001B[0m         \"\"\"\n\u001B[0;32m--> 226\u001B[0;31m         \u001B[0;32mreturn\u001B[0m \u001B[0mF\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mnormalize\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mtensor\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mmean\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mstd\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0minplace\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    227\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    228\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0m__repr__\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torchvision/transforms/functional.py\u001B[0m in \u001B[0;36mnormalize\u001B[0;34m(tensor, mean, std, inplace)\u001B[0m\n\u001B[1;32m    276\u001B[0m     \u001B[0mmean\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mas_tensor\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mmean\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdtype\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0mdtype\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdevice\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0mtensor\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdevice\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    277\u001B[0m     \u001B[0mstd\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mas_tensor\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mstd\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdtype\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0mdtype\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdevice\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0mtensor\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdevice\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 278\u001B[0;31m     \u001B[0;32mif\u001B[0m \u001B[0;34m(\u001B[0m\u001B[0mstd\u001B[0m \u001B[0;34m==\u001B[0m \u001B[0;36m0\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0many\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    279\u001B[0m         \u001B[0;32mraise\u001B[0m \u001B[0mValueError\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'std evaluated to zero after conversion to {}, leading to division by zero.'\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mformat\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mdtype\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    280\u001B[0m     \u001B[0;32mif\u001B[0m \u001B[0mmean\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mndim\u001B[0m \u001B[0;34m==\u001B[0m \u001B[0;36m1\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/tensor.py\u001B[0m in \u001B[0;36mwrapped\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m     22\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0mwrapped\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m*\u001B[0m\u001B[0margs\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m**\u001B[0m\u001B[0mkwargs\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     23\u001B[0m         \u001B[0;32mfrom\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0moverrides\u001B[0m \u001B[0;32mimport\u001B[0m \u001B[0mhas_torch_function\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mhandle_torch_function\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 24\u001B[0;31m         \u001B[0;32mif\u001B[0m \u001B[0;32mnot\u001B[0m \u001B[0mall\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mtype\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mt\u001B[0m\u001B[0;34m)\u001B[0m \u001B[0;32mis\u001B[0m \u001B[0mTensor\u001B[0m \u001B[0;32mfor\u001B[0m \u001B[0mt\u001B[0m \u001B[0;32min\u001B[0m \u001B[0margs\u001B[0m\u001B[0;34m)\u001B[0m \u001B[0;32mand\u001B[0m \u001B[0mhas_torch_function\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0margs\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     25\u001B[0m             \u001B[0;32mreturn\u001B[0m \u001B[0mhandle_torch_function\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mwrapped\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0margs\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m*\u001B[0m\u001B[0margs\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m**\u001B[0m\u001B[0mkwargs\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     26\u001B[0m         \u001B[0;32mtry\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/overrides.py\u001B[0m in \u001B[0;36mhas_torch_function\u001B[0;34m(relevant_args)\u001B[0m\n\u001B[1;32m   1081\u001B[0m     \u001B[0mimplementations\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;32mFalse\u001B[0m \u001B[0motherwise\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m   1082\u001B[0m     \"\"\"\n\u001B[0;32m-> 1083\u001B[0;31m     return _is_torch_function_enabled() and any(\n\u001B[0m\u001B[1;32m   1084\u001B[0m         \u001B[0mtype\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0ma\u001B[0m\u001B[0;34m)\u001B[0m \u001B[0;32mis\u001B[0m \u001B[0;32mnot\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mTensor\u001B[0m \u001B[0;32mand\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m   1085\u001B[0m         \u001B[0mgetattr\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0ma\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m'__torch_function__'\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0m_disabled_torch_function_impl\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/miniconda/envs/torch/lib/python3.8/site-packages/torch/overrides.py\u001B[0m in \u001B[0;36m<genexpr>\u001B[0;34m(.0)\u001B[0m\n\u001B[1;32m   1081\u001B[0m     \u001B[0mimplementations\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;32mFalse\u001B[0m \u001B[0motherwise\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m   1082\u001B[0m     \"\"\"\n\u001B[0;32m-> 1083\u001B[0;31m     return _is_torch_function_enabled() and any(\n\u001B[0m\u001B[1;32m   1084\u001B[0m         \u001B[0mtype\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0ma\u001B[0m\u001B[0;34m)\u001B[0m \u001B[0;32mis\u001B[0m \u001B[0;32mnot\u001B[0m \u001B[0mtorch\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mTensor\u001B[0m \u001B[0;32mand\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m   1085\u001B[0m         \u001B[0mgetattr\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0ma\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m'__torch_function__'\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0m_disabled_torch_function_impl\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/ml/lab-ml/nn/labml_helpers/training_loop.py\u001B[0m in \u001B[0;36m__handler\u001B[0;34m(self, sig, frame)\u001B[0m\n\u001B[1;32m    162\u001B[0m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0m__finish\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    163\u001B[0m             \u001B[0mlogger\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mlog\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34m'Killing loop...'\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mText\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mdanger\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 164\u001B[0;31m             \u001B[0mself\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mold_handler\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0msig\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mframe\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    165\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    166\u001B[0m     \u001B[0;32mdef\u001B[0m \u001B[0m__str__\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mself\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m: "
+     ]
+    }
+   ]
+  },
+  {
+   "cell_type": "code",
+   "metadata": {
+    "id": "oBXXlP2b7XZO"
+   },
+   "source": [
+    ""
+   ],
+   "execution_count": null,
+   "outputs": []
+  }
+ ]
+}
\ No newline at end of file
diff --git a/labml_nn/gan/wasserstein/experiment.py b/labml_nn/gan/wasserstein/experiment.py
index bafa8f4b..3eb6f795 100644
--- a/labml_nn/gan/wasserstein/experiment.py
+++ b/labml_nn/gan/wasserstein/experiment.py
@@ -1,5 +1,5 @@
-# We import the [simple gan experiment]((simple_mnist_experiment.html) and change the
-# generator and discriminator networks
+# We import the [DCGAN experiment]((../dcgan.html) and change the
+# loss functions
 from labml import experiment
 
 from labml.configs import calculate