Medetec_Classifier.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Medetec_Classifier.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "collapsed_sections": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/paulgureghian/Google_Colab_PyTorch_Notebooks/blob/master/Medetec_Classifier.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "metadata": {
        "id": "fqQih7hWMmaK",
        "colab_type": "code",
        "outputId": "39eda806-e6b0-494a-a51d-910049cc47ac",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 122
        }
      },
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive') "
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3Aietf%3Awg%3Aoauth%3A2.0%3Aoob&scope=email%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdocs.test%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdrive%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdrive.photos.readonly%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fpeopleapi.readonly&response_type=code\n",
            "\n",
            "Enter your authorization code:\n",
            "··········\n",
            "Mounted at /content/drive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "iPik8jr9KgKS",
        "colab_type": "code",
        "outputId": "aae334ad-beba-4691-9155-79651d2510bd",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 85
        }
      },
      "cell_type": "code",
      "source": [
        "###  Install 'Ludwig'\n",
        "!pip -q install ludwig"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\u001b[?25l\r\u001b[K    8% |██▊                             | 10kB 20.5MB/s eta 0:00:01\r\u001b[K    16% |█████▍                          | 20kB 2.2MB/s eta 0:00:01\r\u001b[K    25% |████████▏                       | 30kB 3.2MB/s eta 0:00:01\r\u001b[K    33% |██████████▉                     | 40kB 2.1MB/s eta 0:00:01\r\u001b[K    42% |█████████████▌                  | 51kB 2.6MB/s eta 0:00:01\r\u001b[K    50% |████████████████▎               | 61kB 3.1MB/s eta 0:00:01\r\u001b[K    59% |███████████████████             | 71kB 3.6MB/s eta 0:00:01\r\u001b[K    67% |█████████████████████▋          | 81kB 4.0MB/s eta 0:00:01\r\u001b[K    76% |████████████████████████▍       | 92kB 4.5MB/s eta 0:00:01\r\u001b[K    84% |███████████████████████████     | 102kB 3.5MB/s eta 0:00:01\r\u001b[K    93% |█████████████████████████████▊  | 112kB 3.5MB/s eta 0:00:01\r\u001b[K    100% |████████████████████████████████| 122kB 4.6MB/s \n",
            "\u001b[?25h  Building wheel for ludwig (setup.py) ... \u001b[?25ldone\n",
            "\u001b[?25h  Building wheel for wrapt (setup.py) ... \u001b[?25ldone\n",
            "\u001b[31mspacy 2.0.18 has requirement numpy>=1.15.0, but you'll have numpy 1.14.6 which is incompatible.\u001b[0m\n",
            "\u001b[?25h"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "fIULCisFOsAU",
        "colab_type": "code",
        "outputId": "0ef63806-7c01-4cef-ac2b-033ad9f8fb8e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 102
        }
      },
      "cell_type": "code",
      "source": [
        "!pip -q install spacy"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\u001b[K    100% |████████████████████████████████| 17.3MB 2.6MB/s \n",
            "\u001b[31mtorchvision 0.2.1 has requirement pillow>=4.1.1, but you'll have pillow 4.0.0 which is incompatible.\u001b[0m\n",
            "\u001b[31mpymc3 3.6 has requirement joblib<0.13.0, but you'll have joblib 0.13.2 which is incompatible.\u001b[0m\n",
            "\u001b[31mfeaturetools 0.4.1 has requirement pandas>=0.23.0, but you'll have pandas 0.22.0 which is incompatible.\u001b[0m\n",
            "\u001b[31malbumentations 0.1.12 has requirement imgaug<0.2.7,>=0.2.5, but you'll have imgaug 0.2.8 which is incompatible.\u001b[0m\n",
            "\u001b[?25h"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "Lwomz8yNOD5M",
        "colab_type": "code",
        "outputId": "c5d52e7c-56b2-416d-8372-a1da98a916f7",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1064
        }
      },
      "cell_type": "code",
      "source": [
        "import torch\n",
        "from ludwig import LudwigModel\n",
        "from torch import nn, optim\n",
        "from collections import OrderedDict\n",
        "from torch.optim import lr_scheduler \n",
        "from torchvision import  models, datasets, transforms"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "error",
          "ename": "ImportError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mImportError\u001b[0m                               Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-4-aa0384f6614e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mLudwigModel\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;32mfrom\u001b[0m \u001b[0mtorch\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mnn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptim\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mcollections\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mOrderedDict\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptim\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mlr_scheduler\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/ludwig/__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     15\u001b[0m \u001b[0;31m# ==============================================================================\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     16\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapi\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mLudwigModel\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 17\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcli\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mCLI\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     18\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mglobals\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mLUDWIG_VERSION\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0m__version__\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/ludwig/cli.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     22\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mpredict\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[0mludwig\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mtrain\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 24\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mvisualize\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;34m\u001b[0m\u001b[0m\n\u001b[1;32m     26\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/ludwig/visualize.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     30\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     31\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconstants\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 32\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mvisualization_utils\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     33\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata_utils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mload_json\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mload_from_file\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     34\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mludwig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprint_utils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mlogging_level_registry\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/ludwig/utils/visualization_utils.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     26\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlines\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mLine2D\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     27\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 28\u001b[0;31m \u001b[0mmpl\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'TkAgg'\u001b[0m\u001b[0;34m)\u001b[0m  \u001b[0;31m# make matplotlib run on mac os\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     29\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpatches\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpatches\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     30\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpath\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/matplotlib/__init__.py\u001b[0m in \u001b[0;36muse\u001b[0;34m(arg, warn, force)\u001b[0m\n\u001b[1;32m   1389\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mforce\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1390\u001b[0m             \u001b[0;32mfrom\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpyplot\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mswitch_backend\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1391\u001b[0;31m             \u001b[0mswitch_backend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\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   1392\u001b[0m     \u001b[0;31m# Finally if pyplot is not imported update both rcParams and\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1393\u001b[0m     \u001b[0;31m# rcDefaults so restoring the defaults later with rcdefaults\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/matplotlib/pyplot.py\u001b[0m in \u001b[0;36mswitch_backend\u001b[0;34m(newbackend)\u001b[0m\n\u001b[1;32m    220\u001b[0m                 \u001b[0;34m\"Cannot load backend {!r} which requires the {!r} interactive \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    221\u001b[0m                 \"framework, as {!r} is currently running\".format(\n\u001b[0;32m--> 222\u001b[0;31m                     newbackend, required_framework, current_framework))\n\u001b[0m\u001b[1;32m    223\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    224\u001b[0m     \u001b[0mrcParams\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'backend'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrcParamsDefault\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'backend'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnewbackend\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mImportError\u001b[0m: Cannot load backend 'TkAgg' which requires the 'tk' interactive framework, as 'headless' is currently running",
            "",
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0;32m\nNOTE: If your import is failing due to a missing package, you can\nmanually install dependencies using either !pip or !apt.\n\nTo view examples of installing some common dependencies, click the\n\"Open Examples\" button below.\n\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n"
          ]
        }
      ]
    },
    {
      "metadata": {
        "id": "WpJdybPMOgfo",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "data_dir = '/content/drive/My Drive/Medetec/medetec_combined_split'\n",
        "train_dir = data_dir + '/train'\n",
        "valid_dir = data_dir + '/valid'\n",
        "test_dir = data_dir + '/test'"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "RPI0h2et6UWk",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "training_transforms= transforms.Compose([transforms.Resize(256),\n",
        "                                         transforms.RandomRotation(45),\n",
        "                                         transforms.RandomHorizontalFlip(),\n",
        "                                         transforms.RandomCrop(224),\n",
        "                                         transforms.RandomResizedCrop(224),\n",
        "                                         transforms.ToTensor(),\n",
        "                                         transforms.Normalize((0.485,0.456,0.406),\n",
        "                                                              (0.229,0.224,0.255))])\n",
        "\n",
        "validation_transforms = transforms.Compose([transforms.Resize(256),\n",
        "                                            transforms.CenterCrop(224),\n",
        "                                            transforms.ToTensor(),\n",
        "                                            transforms.Normalize((0.485,0.456,0.406),\n",
        "                                                                 (0.229,0.224,0.255))])\n",
        "\n",
        "testing_transforms = transforms.Compose([transforms.Resize(256),\n",
        "                                         transforms.CenterCrop(224),\n",
        "                                         transforms.ToTensor(),\n",
        "                                         transforms.Normalize((0.485,0.456,0.406),\n",
        "                                                              (0.229,0.224,0.255))])\n",
        "\n",
        "training_dataset = datasets.ImageFolder(train_dir, transform=training_transforms)\n",
        "validation_dataset = datasets.ImageFolder(valid_dir, transform=validation_transforms)\n",
        "testing_dataset = datasets.ImageFolder(test_dir, transform=testing_transforms)\n",
        "\n",
        "training_dataloader = torch.utils.data.DataLoader(training_dataset, batch_size=32, shuffle=True)\n",
        "validation_dataloader = torch.utils.data.DataLoader(validation_dataset, batch_size=32)\n",
        "testing_dataloader = torch.utils.data.DataLoader(testing_dataset, batch_size=32) "
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "msdlit-I_Qm9",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "device = torch.device(\"cuda\" if torch.cuda.is_available() else 'cpu')\n",
        "\n",
        "model = models.vgg16(pretrained=True)\n",
        "\n",
        "\n",
        "for param in model.parameters():\n",
        "    param.requires_grad_(False) \n",
        "    \n",
        "model.classifier = nn.Sequential(OrderedDict([\n",
        "                                ('fc1', nn.Linear(25088, 4096)),\n",
        "                                ('relu1', nn.ReLU()),\n",
        "                                ('fc2', nn.Linear(4096, 19)), \n",
        "                                ('output', nn.Softmax(dim=1))\n",
        "                                ])) \n",
        "\n",
        "model.to(device) \n",
        "epochs = 50\n",
        "criterion = nn.CrossEntropyLoss()\n",
        "optimizer = optim.SGD(model.classifier.parameters(), lr=0.01)  \n",
        "scheduler = lr_scheduler.ReduceLROnPlateau(optimizer) "
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "_e2ZWlc7TKTC",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "for epoch in range(epochs):\n",
        "    #scheduler.step()\n",
        "    train_loss = 0\n",
        "    \n",
        "    model.train()\n",
        "    for inputs, labels in training_dataloader:\n",
        "        inputs, labels = inputs.to(device), labels.to(device)\n",
        "        \n",
        "        optimizer.zero_grad()\n",
        "        \n",
        "        logps = model.forward(inputs)\n",
        "        \n",
        "        loss = criterion(logps, labels)\n",
        "        \n",
        "        loss.backward()\n",
        "        \n",
        "        optimizer.step()\n",
        "        \n",
        "        train_loss += loss.item()\n",
        "        \n",
        "    model.eval()\n",
        "    accuracy = 0\n",
        "    valid_loss = 0\n",
        "    \n",
        "    for inputs, labels in validation_dataloader:\n",
        "        inputs, labels = inputs.to(device), labels.to(device)\n",
        "        \n",
        "        output = model.forward(inputs)\n",
        "        \n",
        "        loss = criterion(output, labels)\n",
        "        \n",
        "        valid_loss += loss.item()\n",
        "        \n",
        "        ps = torch.exp(output)\n",
        "        top_ps, top_class = ps.topk(1, dim=1) \n",
        "        equals = top_class == labels.view(*top_class.shape)\n",
        "        accuracy += torch.mean(equals.type(torch.FloatTensor)).item()\n",
        "        \n",
        "    print('Epoch {}/{}.. '.format(epoch+1, epochs),\n",
        "          'Training loss: {:.3f}.. '.format(train_loss / len(training_dataloader)),\n",
        "          'Validation loss: {:.3f}.. '.format(valid_loss / len(validation_dataloader)),\n",
        "          'Validation accuracy: {:.3f}.. '.format(accuracy / len(validation_dataloader)))\n",
        "          \n",
        "    model.train()      "
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "s3qYsKr6NkzJ",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "!pip freeze"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}