06_pytorch_transfer_learning.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "39355618-53c2-4f68-b6b2-076e0caa727e",
      "metadata": {
        "id": "39355618-53c2-4f68-b6b2-076e0caa727e"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/mrdbourke/pytorch-deep-learning/blob/main/06_pytorch_transfer_learning.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
        "\n",
        "[View Source Code](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/06_pytorch_transfer_learning.ipynb) | [View Slides](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/slides/06_pytorch_transfer_learning.pdf)"
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "muTD2LO-QbAx"
      },
      "id": "muTD2LO-QbAx",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "id": "a283a60e-4ee4-4a02-a998-ca942a4d3e0d",
      "metadata": {
        "id": "a283a60e-4ee4-4a02-a998-ca942a4d3e0d"
      },
      "source": [
        "# 06. PyTorch Transfer Learning\n",
        "\n",
        "> **Note:** This notebook uses `torchvision`'s new [multi-weight support API (available in `torchvision` v0.13+)](https://pytorch.org/blog/introducing-torchvision-new-multi-weight-support-api/).\n",
        "\n",
        "We've built a few models by hand so far.\n",
        "\n",
        "But their performance has been poor.\n",
        "\n",
        "You might be thinking, **is there a well-performing model that already exists for our problem?**\n",
        "\n",
        "And in the world of deep learning, the answer is often *yes*.\n",
        "\n",
        "We'll see how by using a powerful technique called [**transfer learning**](https://developers.google.com/machine-learning/glossary#transfer-learning)."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "bce1d5c7-8cb9-4f7f-8402-58f419ae9176",
      "metadata": {
        "id": "bce1d5c7-8cb9-4f7f-8402-58f419ae9176"
      },
      "source": [
        "## What is transfer learning?\n",
        "\n",
        "**Transfer learning** allows us to take the patterns (also called weights) another model has learned from another problem and use them for our own problem.\n",
        "\n",
        "For example, we can take the patterns a computer vision model has learned from datasets such as [ImageNet](https://www.image-net.org/) (millions of images of different objects) and use them to power our FoodVision Mini model.\n",
        "\n",
        "Or we could take the patterns from a [language model](https://developers.google.com/machine-learning/glossary#masked-language-model) (a model that's been through large amounts of text to learn a representation of language) and use them as the basis of a model to classify different text samples.\n",
        "\n",
        "The premise remains: find a well-performing existing model and apply it to your own problem.\n",
        "\n",
        "<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/06-transfer-learning-example-overview.png\" alt=\"transfer learning overview on different problems\" width=900/>\n",
        "\n",
        "*Example of transfer learning being applied to computer vision and natural language processing (NLP). In the case of computer vision, a computer vision model might learn patterns on millions of images in ImageNet and then use those patterns to infer on another problem. And for NLP, a language model may learn the structure of language by reading all of Wikipedia (and perhaps more) and then apply that knowledge to a different problem.*"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "08cee0cd-4e6a-4faa-8027-c06e2dee4c7d",
      "metadata": {
        "id": "08cee0cd-4e6a-4faa-8027-c06e2dee4c7d"
      },
      "source": [
        "## Why use transfer learning?\n",
        "\n",
        "There are two main benefits to using transfer learning:\n",
        "\n",
        "1. Can leverage an existing model (usually a neural network architecture) proven to work on problems similar to our own.\n",
        "2. Can leverage a working model which has **already learned** patterns on similar data to our own. This often results in achieving **great results with less custom data**.\n",
        "\n",
        "<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/06-transfer-learning-for-foodvision-mini%20.png\" alt=\"transfer learning applied to FoodVision Mini\" width=900/>\n",
        "\n",
        "*We'll be putting these to the test for our FoodVision Mini problem, we'll take a computer vision model pretrained on ImageNet and try to leverage its underlying learned representations for classifying images of pizza, steak and sushi.*\n",
        "\n",
        "Both research and practice support the use of transfer learning too.\n",
        "\n",
        "A finding from a recent machine learning research paper recommended practioner's use transfer learning wherever possible.\n",
        "\n",
        "<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/06-how-to-train-your-vit-section-6-transfer-learning-highlight.png\" width=900 alt=\"how to train your vision transformer paper section 6, advising to use transfer learning if you can\"/>\n",
        "\n",
        "*A study into the effects of whether training from scratch or using transfer learning was better from a practioner's point of view, found transfer learning to be far more beneficial in terms of cost and time. **Source:** [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://arxiv.org/abs/2106.10270) paper section 6 (conclusion).*\n",
        "\n",
        "And Jeremy Howard (founder of [fastai](https://www.fast.ai/)) is a big proponent of transfer learning.\n",
        "\n",
        "> The things that really make a difference (transfer learning), if we can do better at transfer learning, it’s this world changing thing. Suddenly lots more people can do world-class work with less resources and less data. — [Jeremy Howard on the Lex Fridman Podcast](https://youtu.be/Bi7f1JSSlh8?t=72)\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "4ef09280-6222-4b64-bfe1-90fe6840c6ff",
      "metadata": {
        "id": "4ef09280-6222-4b64-bfe1-90fe6840c6ff"
      },
      "source": [
        "## Where to find pretrained models\n",
        "\n",
        "The world of deep learning is an amazing place.\n",
        "\n",
        "So amazing that many people around the world share their work.\n",
        "\n",
        "Often, code and pretrained models for the latest state-of-the-art research is released within a few days of publishing.\n",
        "\n",
        "And there are several places you can find pretrained models to use for your own problems.\n",
        "\n",
        "| **Location** | **What's there?** | **Link(s)** |\n",
        "| ----- | ----- | ----- |\n",
        "| **PyTorch domain libraries** | Each of the PyTorch domain libraries (`torchvision`, `torchtext`) come with pretrained models of some form. The models there work right within PyTorch. | [`torchvision.models`](https://pytorch.org/vision/stable/models.html), [`torchtext.models`](https://pytorch.org/text/main/models.html), [`torchaudio.models`](https://pytorch.org/audio/stable/models.html), [`torchrec.models`](https://pytorch.org/torchrec/torchrec.models.html) |\n",
        "| **HuggingFace Hub** | A series of pretrained models on many different domains (vision, text, audio and more) from organizations around the world. There's plenty of different datasets too. | https://huggingface.co/models, https://huggingface.co/datasets |\n",
        "| **`timm` (PyTorch Image Models) library** | Almost all of the latest and greatest computer vision models in PyTorch code as well as plenty of other helpful computer vision features. | https://github.com/rwightman/pytorch-image-models|\n",
        "| **Paperswithcode** | A collection of the latest state-of-the-art machine learning papers with code implementations attached. You can also find benchmarks here of model performance on different tasks. | https://paperswithcode.com/ |\n",
        "\n",
        "<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/06-transfer-learning-where-to-find-pretrained-models.png\" alt=\"different locations to find pretrained neural network models\" width=900/>\n",
        "\n",
        "*With access to such high-quality resources as above, it should be common practice at the start of every deep learning problem you take on to ask, \"Does a pretrained model exist for my problem?\"*\n",
        "\n",
        "> **Exercise:** Spend 5-minutes going through [`torchvision.models`](https://pytorch.org/vision/stable/models.html) as well as the [HuggingFace Hub Models page](https://huggingface.co/models), what do you find? (there's no right answers here, it's just to practice exploring)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "047709a9-e17e-471d-ab4e-b01fd7bfdc40",
      "metadata": {
        "id": "047709a9-e17e-471d-ab4e-b01fd7bfdc40"
      },
      "source": [
        "## What we're going to cover\n",
        "\n",
        "We're going to take a pretrained model from `torchvision.models` and customise it to work on (and hopefully improve) our FoodVision Mini problem.\n",
        "\n",
        "| **Topic** | **Contents** |\n",
        "| ----- | ----- |\n",
        "| **0. Getting setup** | We've written a fair bit of useful code over the past few sections, let's download it and make sure we can use it again. |\n",
        "| **1. Get data** | Let's get the pizza, steak and sushi image classification dataset we've been using to try and improve our model's results. |\n",
        "| **2. Create Datasets and DataLoaders** | We'll use the `data_setup.py` script we wrote in chapter 05. PyTorch Going Modular to setup our DataLoaders. |\n",
        "| **3. Get and customise a pretrained model** | Here we'll download a pretrained model from `torchvision.models` and customise it to our own problem. |\n",
        "| **4. Train model** | Let's see how the new pretrained model goes on our pizza, steak, sushi dataset. We'll use the training functions we created in the previous chapter. |\n",
        "| **5. Evaluate the model by plotting loss curves** | How did our first transfer learning model go? Did it overfit or underfit?  |\n",
        "| **6. Make predictions on images from the test set** | It's one thing to check out a model's evaluation metrics but it's another thing to view its predictions on test samples, let's *visualize, visualize, visualize*! |"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "41430fb1-466a-4b38-bfef-0479ca85baf1",
      "metadata": {
        "id": "41430fb1-466a-4b38-bfef-0479ca85baf1"
      },
      "source": [
        "## Where can you get help?\n",
        "\n",
        "All of the materials for this course [are available on GitHub](https://github.com/mrdbourke/pytorch-deep-learning).\n",
        "\n",
        "If you run into trouble, you can ask a question on the course [GitHub Discussions page](https://github.com/mrdbourke/pytorch-deep-learning/discussions).\n",
        "\n",
        "And of course, there's the [PyTorch documentation](https://pytorch.org/docs/stable/index.html) and [PyTorch developer forums](https://discuss.pytorch.org/), a very helpful place for all things PyTorch."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "590369df-00b6-491e-8feb-cb540ad257ec",
      "metadata": {
        "id": "590369df-00b6-491e-8feb-cb540ad257ec"
      },
      "source": [
        "## 0. Getting setup\n",
        "\n",
        "Let's get started by importing/downloading the required modules for this section.\n",
        "\n",
        "To save us writing extra code, we're going to be leveraging some of the Python scripts (such as `data_setup.py` and `engine.py`) we created in the previous section, [05. PyTorch Going Modular](https://www.learnpytorch.io/05_pytorch_going_modular/).\n",
        "\n",
        "Specifically, we're going to download the [`going_modular`](https://github.com/mrdbourke/pytorch-deep-learning/tree/main/going_modular) directory from the `pytorch-deep-learning` repository (if we don't already have it).\n",
        "\n",
        "We'll also get the [`torchinfo`](https://github.com/TylerYep/torchinfo) package if it's not available.\n",
        "\n",
        "`torchinfo` will help later on to give us a visual representation of our model.\n",
        "\n",
        "> **Note:** As of June 2022, this notebook uses the nightly versions of `torch` and `torchvision` as `torchvision` v0.13+ is required for using the updated multi-weights API. You can install these using the command below."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "8ed820be",
      "metadata": {
        "id": "8ed820be",
        "outputId": "47e59d67-d797-4d9b-d75e-f9dff62343f0"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "torch version: 1.13.0.dev20220620+cu113\n",
            "torchvision version: 0.14.0.dev20220620+cu113\n"
          ]
        }
      ],
      "source": [
        "# For this notebook to run with updated APIs, we need torch 1.12+ and torchvision 0.13+\n",
        "try:\n",
        "    import torch\n",
        "    import torchvision\n",
        "    assert int(torch.__version__.split(\".\")[1]) >= 12, \"torch version should be 1.12+\"\n",
        "    assert int(torchvision.__version__.split(\".\")[1]) >= 13, \"torchvision version should be 0.13+\"\n",
        "    print(f\"torch version: {torch.__version__}\")\n",
        "    print(f\"torchvision version: {torchvision.__version__}\")\n",
        "except:\n",
        "    print(f\"[INFO] torch/torchvision versions not as required, installing nightly versions.\")\n",
        "    !pip3 install -U torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113\n",
        "    import torch\n",
        "    import torchvision\n",
        "    print(f\"torch version: {torch.__version__}\")\n",
        "    print(f\"torchvision version: {torchvision.__version__}\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "0797a4ff-512e-4c46-a82a-e913e0db10a8",
      "metadata": {
        "id": "0797a4ff-512e-4c46-a82a-e913e0db10a8"
      },
      "outputs": [],
      "source": [
        "# Continue with regular imports\n",
        "import matplotlib.pyplot as plt\n",
        "import torch\n",
        "import torchvision\n",
        "\n",
        "from torch import nn\n",
        "from torchvision import transforms\n",
        "\n",
        "# Try to get torchinfo, install it if it doesn't work\n",
        "try:\n",
        "    from torchinfo import summary\n",
        "except:\n",
        "    print(\"[INFO] Couldn't find torchinfo... installing it.\")\n",
        "    !pip install -q torchinfo\n",
        "    from torchinfo import summary\n",
        "\n",
        "# Try to import the going_modular directory, download it from GitHub if it doesn't work\n",
        "try:\n",
        "    from going_modular.going_modular import data_setup, engine\n",
        "except:\n",
        "    # Get the going_modular scripts\n",
        "    print(\"[INFO] Couldn't find going_modular scripts... downloading them from GitHub.\")\n",
        "    !git clone https://github.com/mrdbourke/pytorch-deep-learning\n",
        "    !mv pytorch-deep-learning/going_modular .\n",
        "    !rm -rf pytorch-deep-learning\n",
        "    from going_modular.going_modular import data_setup, engine"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "208107cc-a0d7-4d84-ad27-4b5120d6be02",
      "metadata": {
        "id": "208107cc-a0d7-4d84-ad27-4b5120d6be02"
      },
      "source": [
        "Now let's setup device agnostic code.\n",
        "\n",
        "> **Note:** If you're using Google Colab, and you don't have a GPU turned on yet, it's now time to turn one on via `Runtime -> Change runtime type -> Hardware accelerator -> GPU`."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "b93a75c4-6e40-4575-8d60-d1d43be9220f",
      "metadata": {
        "id": "b93a75c4-6e40-4575-8d60-d1d43be9220f",
        "outputId": "4dfd266d-478f-44e4-ee30-818a012a3800"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "'cuda'"
            ]
          },
          "execution_count": 3,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Setup device agnostic code\n",
        "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
        "device"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "afbfa2ba-bae1-406b-bed6-4d17250e5b97",
      "metadata": {
        "id": "afbfa2ba-bae1-406b-bed6-4d17250e5b97"
      },
      "source": [
        "## 1. Get data\n",
        "\n",
        "Before we can start to use **transfer learning**, we'll need a dataset.\n",
        "\n",
        "To see how transfer learning compares to our previous attempts at model building, we'll download the same dataset we've been using for FoodVision Mini.\n",
        "\n",
        "Let's write some code to download the [`pizza_steak_sushi.zip`](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/data/pizza_steak_sushi.zip) dataset from the course GitHub and then unzip it.\n",
        "\n",
        "We can also make sure if we've already got the data, it doesn't redownload."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "8dfd6e3f-3f0d-4fca-9835-6a45a7c797c3",
      "metadata": {
        "id": "8dfd6e3f-3f0d-4fca-9835-6a45a7c797c3",
        "outputId": "7e044516-910c-429b-f034-769653daa6de"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "data/pizza_steak_sushi directory exists.\n"
          ]
        }
      ],
      "source": [
        "import os\n",
        "import zipfile\n",
        "\n",
        "from pathlib import Path\n",
        "\n",
        "import requests\n",
        "\n",
        "# Setup path to data folder\n",
        "data_path = Path(\"data/\")\n",
        "image_path = data_path / \"pizza_steak_sushi\"\n",
        "\n",
        "# If the image folder doesn't exist, download it and prepare it...\n",
        "if image_path.is_dir():\n",
        "    print(f\"{image_path} directory exists.\")\n",
        "else:\n",
        "    print(f\"Did not find {image_path} directory, creating one...\")\n",
        "    image_path.mkdir(parents=True, exist_ok=True)\n",
        "\n",
        "    # Download pizza, steak, sushi data\n",
        "    with open(data_path / \"pizza_steak_sushi.zip\", \"wb\") as f:\n",
        "        request = requests.get(\"https://github.com/mrdbourke/pytorch-deep-learning/raw/main/data/pizza_steak_sushi.zip\")\n",
        "        print(\"Downloading pizza, steak, sushi data...\")\n",
        "        f.write(request.content)\n",
        "\n",
        "    # Unzip pizza, steak, sushi data\n",
        "    with zipfile.ZipFile(data_path / \"pizza_steak_sushi.zip\", \"r\") as zip_ref:\n",
        "        print(\"Unzipping pizza, steak, sushi data...\")\n",
        "        zip_ref.extractall(image_path)\n",
        "\n",
        "    # Remove .zip file\n",
        "    os.remove(data_path / \"pizza_steak_sushi.zip\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "173ed0e2-bd8d-4b7e-8c17-2d2a64a2b886",
      "metadata": {
        "id": "173ed0e2-bd8d-4b7e-8c17-2d2a64a2b886"
      },
      "source": [
        "Excellent!\n",
        "\n",
        "Now we've got the same dataset we've been using previously, a series of images of pizza, steak and sushi in standard image classification format.\n",
        "\n",
        "Let's now create paths to our training and test directories."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "e3e04e57-44e8-4c13-97db-ba9a21a1924c",
      "metadata": {
        "id": "e3e04e57-44e8-4c13-97db-ba9a21a1924c"
      },
      "outputs": [],
      "source": [
        "# Setup Dirs\n",
        "train_dir = image_path / \"train\"\n",
        "test_dir = image_path / \"test\""
      ]
    },
    {
      "cell_type": "markdown",
      "id": "80dde33f-ab14-41b7-a9f8-2cc0b8a512c0",
      "metadata": {
        "id": "80dde33f-ab14-41b7-a9f8-2cc0b8a512c0"
      },
      "source": [
        "## 2. Create Datasets and DataLoaders\n",
        "\n",
        "Since we've downloaded the `going_modular` directory, we can use the [`data_setup.py`](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/going_modular/going_modular/data_setup.py) script we created in section [05. PyTorch Going Modular](https://www.learnpytorch.io/05_pytorch_going_modular/#2-create-datasets-and-dataloaders-data_setuppy) to prepare and setup our DataLoaders.\n",
        "\n",
        "But since we'll be using a pretrained model from [`torchvision.models`](https://pytorch.org/vision/stable/models.html), there's a specific transform we need to prepare our images first."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "0db9c008-5432-4ad2-bad4-881ebe212a6c",
      "metadata": {
        "tags": [],
        "id": "0db9c008-5432-4ad2-bad4-881ebe212a6c"
      },
      "source": [
        "### 2.1 Creating a transform for `torchvision.models` (manual creation)\n",
        "\n",
        "> **Note:** As of `torchvision` v0.13+, there's an update to how data transforms can be created using `torchvision.models`. I've called the previous method \"manual creation\" and the new method \"auto creation\". This notebook showcases both.\n",
        "\n",
        "When using a pretrained model, it's important that **your custom data going into the model is prepared in the same way as the original training data that went into the model**.\n",
        "\n",
        "Prior to `torchvision` v0.13+, to create a transform for a pretrained model in `torchvision.models`, the documentation stated:\n",
        "\n",
        "> All pre-trained models expect input images normalized in the same way, i.e. mini-batches of 3-channel RGB images of shape (3 x H x W), where H and W are expected to be at least 224.\n",
        ">\n",
        "> The images have to be loaded in to a range of `[0, 1]` and then normalized using `mean = [0.485, 0.456, 0.406]` and `std = [0.229, 0.224, 0.225]`.\n",
        ">\n",
        "> You can use the following transform to normalize:\n",
        ">\n",
        "> ```\n",
        "> normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],\n",
        ">                                  std=[0.229, 0.224, 0.225])\n",
        "> ```\n",
        "\n",
        "The good news is, we can achieve the above transformations with a combination of:\n",
        "\n",
        "| **Transform number** | **Transform required** | **Code to perform transform** |\n",
        "| ----- | ----- | ----- |\n",
        "| 1 | Mini-batches of size `[batch_size, 3, height, width]` where height and width are at least 224x224^. | `torchvision.transforms.Resize()` to resize images into `[3, 224, 224]`^ and `torch.utils.data.DataLoader()` to create batches of images. |\n",
        "| 2 | Values between 0 & 1. | `torchvision.transforms.ToTensor()` |\n",
        "| 3 | A mean of `[0.485, 0.456, 0.406]` (values across each colour channel). | `torchvision.transforms.Normalize(mean=...)` to adjust the mean of our images.  |\n",
        "| 4 | A standard deviation of `[0.229, 0.224, 0.225]` (values across each colour channel). | `torchvision.transforms.Normalize(std=...)` to adjust the standard deviation of our images.  |\n",
        "\n",
        "> **Note:** ^some pretrained models from `torchvision.models` in different sizes to `[3, 224, 224]`, for example, some might take them in `[3, 240, 240]`. For specific input image sizes, see the documentation.\n",
        "\n",
        "> **Question:** *Where did the mean and standard deviation values come from? Why do we need to do this?*\n",
        ">\n",
        "> These were calculated from the data. Specifically, the ImageNet dataset by taking the means and standard deviations across a subset of images.\n",
        ">\n",
        "> We also don't *need* to do this. Neural networks are usually quite capable of figuring out appropriate data distributions (they'll calculate where the mean and standard deviations need to be on their own) but setting them at the start can help our networks achieve better performance quicker.\n",
        "\n",
        "Let's compose a series of `torchvision.transforms` to perform the above steps."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "4e095ac1-af8e-4215-8028-de97cfb65c39",
      "metadata": {
        "id": "4e095ac1-af8e-4215-8028-de97cfb65c39"
      },
      "outputs": [],
      "source": [
        "# Create a transforms pipeline manually (required for torchvision < 0.13)\n",
        "manual_transforms = transforms.Compose([\n",
        "    transforms.Resize((224, 224)), # 1. Reshape all images to 224x224 (though some models may require different sizes)\n",
        "    transforms.ToTensor(), # 2. Turn image values to between 0 & 1\n",
        "    transforms.Normalize(mean=[0.485, 0.456, 0.406], # 3. A mean of [0.485, 0.456, 0.406] (across each colour channel)\n",
        "                         std=[0.229, 0.224, 0.225]) # 4. A standard deviation of [0.229, 0.224, 0.225] (across each colour channel),\n",
        "])"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "cd676c4f-6f81-4bfb-a578-8f3d5cd2bd4a",
      "metadata": {
        "id": "cd676c4f-6f81-4bfb-a578-8f3d5cd2bd4a"
      },
      "source": [
        "Wonderful!\n",
        "\n",
        "Now we've got a **manually created series of transforms** ready to prepare our images, let's create training and testing DataLoaders.\n",
        "\n",
        "We can create these using the `create_dataloaders` function from the [`data_setup.py`](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/going_modular/going_modular/data_setup.py) script we created in [05. PyTorch Going Modular Part 2](https://www.learnpytorch.io/05_pytorch_going_modular/#2-create-datasets-and-dataloaders-data_setuppy).\n",
        "\n",
        "We'll set `batch_size=32` so our model see's mini-batches of 32 samples at a time.\n",
        "\n",
        "And we can transform our images using the transform pipeline we created above by setting `transform=manual_transforms`.\n",
        "\n",
        "> **Note:** I've included this manual creation of transforms in this notebook because you may come across resources that use this style. It's also important to note that because these transforms are manually created, they're also infinitely customizable. So if you wanted to included data augmentation techniques in your transforms pipeline, you could."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "f7d97a6f-50f8-4212-a777-3d2cfac2a4fe",
      "metadata": {
        "id": "f7d97a6f-50f8-4212-a777-3d2cfac2a4fe",
        "outputId": "fdae4d88-a3b6-4996-9115-423f73ecc1f5"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(<torch.utils.data.dataloader.DataLoader at 0x7fa9429a3a60>,\n",
              " <torch.utils.data.dataloader.DataLoader at 0x7fa9429a37c0>,\n",
              " ['pizza', 'steak', 'sushi'])"
            ]
          },
          "execution_count": 7,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Create training and testing DataLoaders as well as get a list of class names\n",
        "train_dataloader, test_dataloader, class_names = data_setup.create_dataloaders(train_dir=train_dir,\n",
        "                                                                               test_dir=test_dir,\n",
        "                                                                               transform=manual_transforms, # resize, convert images to between 0 & 1 and normalize them\n",
        "                                                                               batch_size=32) # set mini-batch size to 32\n",
        "\n",
        "train_dataloader, test_dataloader, class_names"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "7cbd7821-21c0-44e7-a3a0-0682e241ea27",
      "metadata": {
        "id": "7cbd7821-21c0-44e7-a3a0-0682e241ea27"
      },
      "source": [
        "### 2.2 Creating a transform for `torchvision.models` (auto creation)\n",
        "\n",
        "As previously stated, when using a pretrained model, it's important that **your custom data going into the model is prepared in the same way as the original training data that went into the model**.\n",
        "\n",
        "Above we saw how to manually create a transform for a pretrained model.\n",
        "\n",
        "But as of `torchvision` v0.13+, an automatic transform creation feature has been added.\n",
        "\n",
        "When you setup a model from `torchvision.models` and select the pretrained model weights you'd like to use, for example, say we'd like to use:\n",
        "    \n",
        "```python\n",
        "weights = torchvision.models.EfficientNet_B0_Weights.DEFAULT\n",
        "```\n",
        "\n",
        "Where,\n",
        "* `EfficientNet_B0_Weights` is the model architecture weights we'd like to use (there are many differnt model architecture options in `torchvision.models`).\n",
        "* `DEFAULT` means the *best available* weights (the best performance in ImageNet).\n",
        "    * **Note:** Depending on the model architecture you choose, you may also see other options such as `IMAGENET_V1` and `IMAGENET_V2` where generally the higher version number the better. Though if you want the best available, `DEFAULT` is the easiest option. See the [`torchvision.models` documentation](https://pytorch.org/vision/main/models.html) for more.\n",
        "    \n",
        "Let's try it out."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "d3f4bd4c-7b7a-41fb-8d1c-ae96ee88f024",
      "metadata": {
        "id": "d3f4bd4c-7b7a-41fb-8d1c-ae96ee88f024",
        "outputId": "99f91cf8-8bfe-49f0-dd45-06803e6d4ece"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "EfficientNet_B0_Weights.IMAGENET1K_V1"
            ]
          },
          "execution_count": 8,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Get a set of pretrained model weights\n",
        "weights = torchvision.models.EfficientNet_B0_Weights.DEFAULT # .DEFAULT = best available weights from pretraining on ImageNet\n",
        "weights"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "cebcdf20-4ab7-40ba-8691-9d9af8962dab",
      "metadata": {
        "id": "cebcdf20-4ab7-40ba-8691-9d9af8962dab"
      },
      "source": [
        "And now to access the transforms assosciated with our `weights`, we can use the `transforms()` method.\n",
        "\n",
        "This is essentially saying \"get the data transforms that were used to train the `EfficientNet_B0_Weights` on ImageNet\"."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "29924062-a233-4926-a77a-9052d1956938",
      "metadata": {
        "id": "29924062-a233-4926-a77a-9052d1956938",
        "outputId": "4c38d4a1-dea8-4596-fa76-1e473acf7809"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "ImageClassification(\n",
              "    crop_size=[224]\n",
              "    resize_size=[256]\n",
              "    mean=[0.485, 0.456, 0.406]\n",
              "    std=[0.229, 0.224, 0.225]\n",
              "    interpolation=InterpolationMode.BICUBIC\n",
              ")"
            ]
          },
          "execution_count": 9,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Get the transforms used to create our pretrained weights\n",
        "auto_transforms = weights.transforms()\n",
        "auto_transforms"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "243ecdc5-e2c7-46d5-9bb5-6a07606ce93e",
      "metadata": {
        "id": "243ecdc5-e2c7-46d5-9bb5-6a07606ce93e"
      },
      "source": [
        "Notice how `auto_transforms` is very similar to `manual_transforms`, the only difference is that `auto_transforms` came with the model architecture we chose, where as we had to create `manual_transforms` by hand.\n",
        "\n",
        "The benefit of automatically creating a transform through `weights.transforms()` is that you ensure you're using the same data transformation as the pretrained model used when it was trained.\n",
        "\n",
        "However, the tradeoff of using automatically created transforms is a lack of customization.\n",
        "\n",
        "We can use `auto_transforms` to create DataLoaders with `create_dataloaders()` just as before."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "7c21ffb5-a6d9-40d5-b0d0-47828612d282",
      "metadata": {
        "id": "7c21ffb5-a6d9-40d5-b0d0-47828612d282",
        "outputId": "41ea2013-b33b-47c7-fc69-7565e5522568"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "(<torch.utils.data.dataloader.DataLoader at 0x7fa942951460>,\n",
              " <torch.utils.data.dataloader.DataLoader at 0x7fa942951550>,\n",
              " ['pizza', 'steak', 'sushi'])"
            ]
          },
          "execution_count": 10,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Create training and testing DataLoaders as well as get a list of class names\n",
        "train_dataloader, test_dataloader, class_names = data_setup.create_dataloaders(train_dir=train_dir,\n",
        "                                                                               test_dir=test_dir,\n",
        "                                                                               transform=auto_transforms, # perform same data transforms on our own data as the pretrained model\n",
        "                                                                               batch_size=32) # set mini-batch size to 32\n",
        "\n",
        "train_dataloader, test_dataloader, class_names"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "71a4f3eb-9349-472f-96b1-735fac55ba73",
      "metadata": {
        "id": "71a4f3eb-9349-472f-96b1-735fac55ba73"
      },
      "source": [
        "## 3. Getting a pretrained model\n",
        "\n",
        "Alright, here comes the fun part!\n",
        "\n",
        "Over the past few notebooks we've been building PyTorch neural networks from scratch.\n",
        "\n",
        "And while that's a good skill to have, our models haven't been performing as well as we'd like.\n",
        "\n",
        "That's where **transfer learning** comes in.\n",
        "\n",
        "The whole idea of transfer learning is to **take an already well-performing model on a problem-space similar to yours and then customising it to your use case**.\n",
        "\n",
        "Since we're working on a computer vision problem (image classification with FoodVision Mini), we can find pretrained classification models in [`torchvision.models`](https://pytorch.org/vision/stable/models.html#classification).\n",
        "\n",
        "Exploring the documentation, you'll find plenty of common computer vision architecture backbones such as:\n",
        "\n",
        "| **Architecuture backbone** | **Code** |\n",
        "| ----- | ----- |\n",
        "| [ResNet](https://arxiv.org/abs/1512.03385)'s | `torchvision.models.resnet18()`, `torchvision.models.resnet50()`... |\n",
        "| [VGG](https://arxiv.org/abs/1409.1556) (similar to what we used for TinyVGG) | `torchvision.models.vgg16()` |\n",
        "| [EfficientNet](https://arxiv.org/abs/1905.11946)'s | `torchvision.models.efficientnet_b0()`, `torchvision.models.efficientnet_b1()`... |\n",
        "| [VisionTransformer](https://arxiv.org/abs/2010.11929) (ViT's)| `torchvision.models.vit_b_16()`, `torchvision.models.vit_b_32()`... |\n",
        "| [ConvNeXt](https://arxiv.org/abs/2201.03545) | `torchvision.models.convnext_tiny()`,  `torchvision.models.convnext_small()`... |\n",
        "| More available in `torchvision.models` | `torchvision.models...` |"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "c570cca9-9dd6-4a88-a5ca-4237f7f94663",
      "metadata": {
        "id": "c570cca9-9dd6-4a88-a5ca-4237f7f94663"
      },
      "source": [
        "### 3.1 Which pretrained model should you use?\n",
        "\n",
        "It depends on your problem/the device you're working with.\n",
        "\n",
        "Generally, the higher number in the model name (e.g. `efficientnet_b0()` -> `efficientnet_b1()` -> `efficientnet_b7()`) means *better performance* but a *larger* model.\n",
        "\n",
        "You might think better performance is *always better*, right?\n",
        "\n",
        "That's true but **some better performing models are too big for some devices**.\n",
        "\n",
        "For example, say you'd like to run your model on a mobile-device, you'll have to take into account the limited compute resources on the device, thus you'd be looking for a smaller model.\n",
        "\n",
        "But if you've got unlimited compute power, as [*The Bitter Lesson*](http://www.incompleteideas.net/IncIdeas/BitterLesson.html) states, you'd likely take the biggest, most compute hungry model you can.\n",
        "\n",
        "Understanding this **performance vs. speed vs. size tradeoff** will come with time and practice.\n",
        "\n",
        "For me, I've found a nice balance in the `efficientnet_bX` models.\n",
        "\n",
        "As of May 2022, [Nutrify](https://nutrify.app) (the machine learning powered app I'm working on) is powered by an `efficientnet_b0`.\n",
        "\n",
        "[Comma.ai](https://comma.ai/) (a company that makes open source self-driving car software) [uses an `efficientnet_b2`](https://geohot.github.io/blog/jekyll/update/2021/10/29/an-architecture-for-life.html) to learn a representation of the road.\n",
        "\n",
        "> **Note:** Even though we're using `efficientnet_bX`, it's important not to get too attached to any one architecture, as they are always changing as new research gets released. Best to experiment, experiment, experiment and see what works for your problem."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "5d2d5d0b-ba3c-4f6a-a7eb-ae8b3bbc5a34",
      "metadata": {
        "id": "5d2d5d0b-ba3c-4f6a-a7eb-ae8b3bbc5a34"
      },
      "source": [
        "### 3.2 Setting up a pretrained model\n",
        "\n",
        "The pretrained model we're going to be using is [`torchvision.models.efficientnet_b0()`](https://pytorch.org/vision/main/models/generated/torchvision.models.efficientnet_b0.html).\n",
        "\n",
        "The architecture is from the paper *[EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946)*.\n",
        "\n",
        "<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/06-effnet-b0-feature-extractor.png\" alt=\"efficienet_b0 from PyTorch torchvision feature extraction model\" width=900/>\n",
        "\n",
        "*Example of what we're going to create, a pretrained [`EfficientNet_B0` model](https://ai.googleblog.com/2019/05/efficientnet-improving-accuracy-and.html) from `torchvision.models` with the output layer adjusted for our use case of classifying pizza, steak and sushi images.*\n",
        "\n",
        "We can setup the `EfficientNet_B0` pretrained ImageNet weights using the same code as we used to create the transforms.\n",
        "\n",
        "\n",
        "```python\n",
        "weights = torchvision.models.EfficientNet_B0_Weights.DEFAULT # .DEFAULT = best available weights for ImageNet\n",
        "```\n",
        "\n",
        "This means the model has already been trained on millions of images and has a good base representation of image data.\n",
        "\n",
        "The PyTorch version of this pretrained model is capable of achieving ~77.7% accuracy across ImageNet's 1000 classes.\n",
        "\n",
        "We'll also send it to the target device."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "7593110c-0b32-47e6-9e29-f33d6c0ac840",
      "metadata": {
        "id": "7593110c-0b32-47e6-9e29-f33d6c0ac840"
      },
      "outputs": [],
      "source": [
        "# OLD: Setup the model with pretrained weights and send it to the target device (this was prior to torchvision v0.13)\n",
        "# model = torchvision.models.efficientnet_b0(pretrained=True).to(device) # OLD method (with pretrained=True)\n",
        "\n",
        "# NEW: Setup the model with pretrained weights and send it to the target device (torchvision v0.13+)\n",
        "weights = torchvision.models.EfficientNet_B0_Weights.DEFAULT # .DEFAULT = best available weights\n",
        "model = torchvision.models.efficientnet_b0(weights=weights).to(device)\n",
        "\n",
        "#model # uncomment to output (it's very long)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "06f6dc93-8e39-4394-ad45-30730c40fa72",
      "metadata": {
        "id": "06f6dc93-8e39-4394-ad45-30730c40fa72"
      },
      "source": [
        "> **Note:** In previous versions of `torchvision`, you'd create a pretrained model with code like:\n",
        ">\n",
        "> `model = torchvision.models.efficientnet_b0(pretrained=True).to(device)`\n",
        ">\n",
        "> However, running this using `torchvision` v0.13+ will result in errors such as the following:\n",
        ">\n",
        "> `UserWarning: The parameter 'pretrained' is deprecated since 0.13 and will be removed in 0.15, please use 'weights' instead.`\n",
        ">\n",
        "> And...\n",
        ">\n",
        "> `UserWarning: Arguments other than a weight enum or None for weights are deprecated since 0.13 and will be removed in 0.15. The current behavior is equivalent to passing weights=EfficientNet_B0_Weights.IMAGENET1K_V1. You can also use weights=EfficientNet_B0_Weights.DEFAULT to get the most up-to-date weights.`"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "9a681f58-458a-47f0-a18a-cabe772df7b3",
      "metadata": {
        "id": "9a681f58-458a-47f0-a18a-cabe772df7b3"
      },
      "source": [
        "If we print the model, we get something similar to the following:\n",
        "\n",
        "<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/06-v2-effnetb0-model-print-out.png\" alt=\"output of printing the efficientnet_b0 model from torchvision.models\" width=900/>\n",
        "\n",
        "Lots and lots and lots of layers.\n",
        "\n",
        "This is one of the benefits of transfer learning, taking an existing model, that's been crafted by some of the best engineers in the world and applying to your own problem.\n",
        "\n",
        "Our `efficientnet_b0` comes in three main parts:\n",
        "1. `features` - A collection of convolutional layers and other various activation layers to learn a base representation of vision data (this base representation/collection of layers is often referred to as **features** or **feature extractor**, \"the base layers of the model learn the different **features** of images\").\n",
        "2. `avgpool` - Takes the average of the output of the `features` layer(s) and turns it into a **feature vector**.\n",
        "3. `classifier` - Turns the **feature vector** into a vector with the same dimensionality as the number of required output classes (since `efficientnet_b0` is pretrained on ImageNet and because ImageNet has 1000 classes, `out_features=1000` is the default)."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "29912dff-574a-47c7-b514-86841532dbe3",
      "metadata": {
        "id": "29912dff-574a-47c7-b514-86841532dbe3"
      },
      "source": [
        "### 3.3 Getting a summary of our model with `torchinfo.summary()`\n",
        "\n",
        "To learn more about our model, let's use `torchinfo`'s [`summary()` method](https://github.com/TylerYep/torchinfo#documentation).\n",
        "\n",
        "To do so, we'll pass in:\n",
        " * `model` - the model we'd like to get a summary of.\n",
        " * `input_size` - the shape of the data we'd like to pass to our model, for the case of `efficientnet_b0`, the input size is `(batch_size, 3, 224, 224)`, though [other variants of `efficientnet_bX` have different input sizes](https://github.com/pytorch/vision/blob/d2bfd639e46e1c5dc3c177f889dc7750c8d137c7/references/classification/train.py#L92-L93).\n",
        "    * **Note:** Many modern models can handle input images of varying sizes thanks to [`torch.nn.AdaptiveAvgPool2d()`](https://pytorch.org/docs/stable/generated/torch.nn.AdaptiveAvgPool2d.html), this layer adaptively adjusts the `output_size` of a given input as required. You can try this out by passing different size input images to `summary()` or your models.\n",
        " * `col_names` - the various information columns we'd like to see about our model.\n",
        " * `col_width` - how wide the columns should be for the summary.\n",
        " * `row_settings` - what features to show in a row."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "524020c6-09d3-4ecf-b791-dbd71ed389e3",
      "metadata": {
        "id": "524020c6-09d3-4ecf-b791-dbd71ed389e3",
        "outputId": "bc61fcf6-b546-4307-8ed0-9cfd0d800070"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "============================================================================================================================================\n",
              "Layer (type (var_name))                                      Input Shape          Output Shape         Param #              Trainable\n",
              "============================================================================================================================================\n",
              "EfficientNet (EfficientNet)                                  [32, 3, 224, 224]    [32, 1000]           --                   True\n",
              "├─Sequential (features)                                      [32, 3, 224, 224]    [32, 1280, 7, 7]     --                   True\n",
              "│    └─Conv2dNormActivation (0)                              [32, 3, 224, 224]    [32, 32, 112, 112]   --                   True\n",
              "│    │    └─Conv2d (0)                                       [32, 3, 224, 224]    [32, 32, 112, 112]   864                  True\n",
              "│    │    └─BatchNorm2d (1)                                  [32, 32, 112, 112]   [32, 32, 112, 112]   64                   True\n",
              "│    │    └─SiLU (2)                                         [32, 32, 112, 112]   [32, 32, 112, 112]   --                   --\n",
              "│    └─Sequential (1)                                        [32, 32, 112, 112]   [32, 16, 112, 112]   --                   True\n",
              "│    │    └─MBConv (0)                                       [32, 32, 112, 112]   [32, 16, 112, 112]   1,448                True\n",
              "│    └─Sequential (2)                                        [32, 16, 112, 112]   [32, 24, 56, 56]     --                   True\n",
              "│    │    └─MBConv (0)                                       [32, 16, 112, 112]   [32, 24, 56, 56]     6,004                True\n",
              "│    │    └─MBConv (1)                                       [32, 24, 56, 56]     [32, 24, 56, 56]     10,710               True\n",
              "│    └─Sequential (3)                                        [32, 24, 56, 56]     [32, 40, 28, 28]     --                   True\n",
              "│    │    └─MBConv (0)                                       [32, 24, 56, 56]     [32, 40, 28, 28]     15,350               True\n",
              "│    │    └─MBConv (1)                                       [32, 40, 28, 28]     [32, 40, 28, 28]     31,290               True\n",
              "│    └─Sequential (4)                                        [32, 40, 28, 28]     [32, 80, 14, 14]     --                   True\n",
              "│    │    └─MBConv (0)                                       [32, 40, 28, 28]     [32, 80, 14, 14]     37,130               True\n",
              "│    │    └─MBConv (1)                                       [32, 80, 14, 14]     [32, 80, 14, 14]     102,900              True\n",
              "│    │    └─MBConv (2)                                       [32, 80, 14, 14]     [32, 80, 14, 14]     102,900              True\n",
              "│    └─Sequential (5)                                        [32, 80, 14, 14]     [32, 112, 14, 14]    --                   True\n",
              "│    │    └─MBConv (0)                                       [32, 80, 14, 14]     [32, 112, 14, 14]    126,004              True\n",
              "│    │    └─MBConv (1)                                       [32, 112, 14, 14]    [32, 112, 14, 14]    208,572              True\n",
              "│    │    └─MBConv (2)                                       [32, 112, 14, 14]    [32, 112, 14, 14]    208,572              True\n",
              "│    └─Sequential (6)                                        [32, 112, 14, 14]    [32, 192, 7, 7]      --                   True\n",
              "│    │    └─MBConv (0)                                       [32, 112, 14, 14]    [32, 192, 7, 7]      262,492              True\n",
              "│    │    └─MBConv (1)                                       [32, 192, 7, 7]      [32, 192, 7, 7]      587,952              True\n",
              "│    │    └─MBConv (2)                                       [32, 192, 7, 7]      [32, 192, 7, 7]      587,952              True\n",
              "│    │    └─MBConv (3)                                       [32, 192, 7, 7]      [32, 192, 7, 7]      587,952              True\n",
              "│    └─Sequential (7)                                        [32, 192, 7, 7]      [32, 320, 7, 7]      --                   True\n",
              "│    │    └─MBConv (0)                                       [32, 192, 7, 7]      [32, 320, 7, 7]      717,232              True\n",
              "│    └─Conv2dNormActivation (8)                              [32, 320, 7, 7]      [32, 1280, 7, 7]     --                   True\n",
              "│    │    └─Conv2d (0)                                       [32, 320, 7, 7]      [32, 1280, 7, 7]     409,600              True\n",
              "│    │    └─BatchNorm2d (1)                                  [32, 1280, 7, 7]     [32, 1280, 7, 7]     2,560                True\n",
              "│    │    └─SiLU (2)                                         [32, 1280, 7, 7]     [32, 1280, 7, 7]     --                   --\n",
              "├─AdaptiveAvgPool2d (avgpool)                                [32, 1280, 7, 7]     [32, 1280, 1, 1]     --                   --\n",
              "├─Sequential (classifier)                                    [32, 1280]           [32, 1000]           --                   True\n",
              "│    └─Dropout (0)                                           [32, 1280]           [32, 1280]           --                   --\n",
              "│    └─Linear (1)                                            [32, 1280]           [32, 1000]           1,281,000            True\n",
              "============================================================================================================================================\n",
              "Total params: 5,288,548\n",
              "Trainable params: 5,288,548\n",
              "Non-trainable params: 0\n",
              "Total mult-adds (G): 12.35\n",
              "============================================================================================================================================\n",
              "Input size (MB): 19.27\n",
              "Forward/backward pass size (MB): 3452.35\n",
              "Params size (MB): 21.15\n",
              "Estimated Total Size (MB): 3492.77\n",
              "============================================================================================================================================"
            ]
          },
          "execution_count": 12,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Print a summary using torchinfo (uncomment for actual output)\n",
        "summary(model=model,\n",
        "        input_size=(32, 3, 224, 224), # make sure this is \"input_size\", not \"input_shape\"\n",
        "        # col_names=[\"input_size\"], # uncomment for smaller output\n",
        "        col_names=[\"input_size\", \"output_size\", \"num_params\", \"trainable\"],\n",
        "        col_width=20,\n",
        "        row_settings=[\"var_names\"]\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "d0ebecfb-1635-48b6-bd89-cbe710d8410f",
      "metadata": {
        "id": "d0ebecfb-1635-48b6-bd89-cbe710d8410f"
      },
      "source": [
        "<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/06-torchinfo-summary-unfrozen-layers.png\" alt=\"output of torchinfo.summary() when passed our model with all layers as trainable\" width=900/>\n",
        "\n",
        "Woah!\n",
        "\n",
        "Now that's a big model!\n",
        "\n",
        "From the output of the summary, we can see all of the various input and output shape changes as our image data goes through the model.\n",
        "\n",
        "And there are a whole bunch more total parameters (pretrained weights) to recognize different patterns in our data.\n",
        "\n",
        "For reference, our model from previous sections, **TinyVGG had 8,083 parameters vs. 5,288,548 parameters for `efficientnet_b0`, an increase of ~654x**!\n",
        "\n",
        "What do you think, will this mean better performance?"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "24af9d91-7ddc-4eb7-b39e-7459b529fb38",
      "metadata": {
        "id": "24af9d91-7ddc-4eb7-b39e-7459b529fb38"
      },
      "source": [
        "### 3.4 Freezing the base model and changing the output layer to suit our needs\n",
        "\n",
        "The process of transfer learning usually goes: freeze some base layers of a pretrained model (typically the `features` section) and then adjust the output layers (also called head/classifier layers) to suit your needs.\n",
        "\n",
        "<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/06-v2-effnet-changing-the-classifier-head.png\" alt=\"changing the efficientnet classifier head to a custom number of outputs\" width=900/>\n",
        "\n",
        "*You can customise the outputs of a pretrained model by changing the output layer(s) to suit your problem. The original `torchvision.models.efficientnet_b0()` comes with `out_features=1000` because there are 1000 classes in ImageNet, the dataset it was trained on. However, for our problem, classifying images of pizza, steak and sushi we only need `out_features=3`.*\n",
        "\n",
        "Let's freeze all of the layers/parameters in the `features` section of our `efficientnet_b0` model.\n",
        "\n",
        "> **Note:** To *freeze* layers means to keep them how they are during training. For example, if your model has pretrained layers, to *freeze* them would be to say, \"don't change any of the patterns in these layers during training, keep them how they are.\" In essence, we'd like to keep the pretrained weights/patterns our model has learned from ImageNet as a backbone and then only change the output layers.\n",
        "\n",
        "We can freeze all of the layers/parameters in the `features` section by setting the attribute `requires_grad=False`.\n",
        "\n",
        "For parameters with `requires_grad=False`, PyTorch doesn't track gradient updates and in turn, these parameters won't be changed by our optimizer during training.\n",
        "\n",
        "In essence, a parameter with `requires_grad=False` is \"untrainable\" or \"frozen\" in place."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "d9cbf97f-5dbf-4283-b70f-91b49e3713e5",
      "metadata": {
        "id": "d9cbf97f-5dbf-4283-b70f-91b49e3713e5"
      },
      "outputs": [],
      "source": [
        "# Freeze all base layers in the \"features\" section of the model (the feature extractor) by setting requires_grad=False\n",
        "for param in model.features.parameters():\n",
        "    param.requires_grad = False"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "e65359fc-116c-44a3-a2d0-42efd958aea1",
      "metadata": {
        "id": "e65359fc-116c-44a3-a2d0-42efd958aea1"
      },
      "source": [
        "Feature extractor layers frozen!\n",
        "\n",
        "Let's now adjust the output layer or the `classifier` portion of our pretrained model to our needs.\n",
        "\n",
        "Right now our pretrained model has `out_features=1000` because there are 1000 classes in ImageNet.\n",
        "\n",
        "However, we don't have 1000 classes, we only have three, pizza, steak and sushi.\n",
        "\n",
        "We can change the `classifier` portion of our model by creating a new series of layers.\n",
        "\n",
        "The current `classifier` consists of:\n",
        "\n",
        "```\n",
        "(classifier): Sequential(\n",
        "    (0): Dropout(p=0.2, inplace=True)\n",
        "    (1): Linear(in_features=1280, out_features=1000, bias=True)\n",
        "```\n",
        "\n",
        "We'll keep the `Dropout` layer the same using [`torch.nn.Dropout(p=0.2, inplace=True)`](https://pytorch.org/docs/stable/generated/torch.nn.Dropout.html).\n",
        "\n",
        "> **Note:** [Dropout layers](https://developers.google.com/machine-learning/glossary#dropout_regularization) randomly remove connections between two neural network layers with a probability of `p`. For example, if `p=0.2`, 20% of connections between neural network layers will be removed at random each pass. This practice is meant to help regularize (prevent overfitting) a model by making sure the connections that remain learn features to compensate for the removal of the other connections (hopefully these remaining features are *more general*).\n",
        "\n",
        "And we'll keep `in_features=1280` for our `Linear` output layer but we'll change the `out_features` value to the length of our `class_names` (`len(['pizza', 'steak', 'sushi']) = 3`).\n",
        "\n",
        "Our new `classifier` layer should be on the same device as our `model`."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "79e804bd-5ddd-470c-9c95-a4150cc1cc3c",
      "metadata": {
        "id": "79e804bd-5ddd-470c-9c95-a4150cc1cc3c"
      },
      "outputs": [],
      "source": [
        "# Set the manual seeds\n",
        "torch.manual_seed(42)\n",
        "torch.cuda.manual_seed(42)\n",
        "\n",
        "# Get the length of class_names (one output unit for each class)\n",
        "output_shape = len(class_names)\n",
        "\n",
        "# Recreate the classifier layer and seed it to the target device\n",
        "model.classifier = torch.nn.Sequential(\n",
        "    torch.nn.Dropout(p=0.2, inplace=True),\n",
        "    torch.nn.Linear(in_features=1280,\n",
        "                    out_features=output_shape, # same number of output units as our number of classes\n",
        "                    bias=True)).to(device)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "cb8248ca-1599-45f5-8ca5-6bb2b760bb31",
      "metadata": {
        "id": "cb8248ca-1599-45f5-8ca5-6bb2b760bb31"
      },
      "source": [
        "Nice!\n",
        "\n",
        "Output layer updated, let's get another summary of our model and see what's changed."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "d5370a8b-34cf-441f-925d-4120a929ed62",
      "metadata": {
        "id": "d5370a8b-34cf-441f-925d-4120a929ed62",
        "outputId": "f0e82f5b-b6d6-418a-f240-abab0ad7fea9"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "============================================================================================================================================\n",
              "Layer (type (var_name))                                      Input Shape          Output Shape         Param #              Trainable\n",
              "============================================================================================================================================\n",
              "EfficientNet (EfficientNet)                                  [32, 3, 224, 224]    [32, 3]              --                   Partial\n",
              "├─Sequential (features)                                      [32, 3, 224, 224]    [32, 1280, 7, 7]     --                   False\n",
              "│    └─Conv2dNormActivation (0)                              [32, 3, 224, 224]    [32, 32, 112, 112]   --                   False\n",
              "│    │    └─Conv2d (0)                                       [32, 3, 224, 224]    [32, 32, 112, 112]   (864)                False\n",
              "│    │    └─BatchNorm2d (1)                                  [32, 32, 112, 112]   [32, 32, 112, 112]   (64)                 False\n",
              "│    │    └─SiLU (2)                                         [32, 32, 112, 112]   [32, 32, 112, 112]   --                   --\n",
              "│    └─Sequential (1)                                        [32, 32, 112, 112]   [32, 16, 112, 112]   --                   False\n",
              "│    │    └─MBConv (0)                                       [32, 32, 112, 112]   [32, 16, 112, 112]   (1,448)              False\n",
              "│    └─Sequential (2)                                        [32, 16, 112, 112]   [32, 24, 56, 56]     --                   False\n",
              "│    │    └─MBConv (0)                                       [32, 16, 112, 112]   [32, 24, 56, 56]     (6,004)              False\n",
              "│    │    └─MBConv (1)                                       [32, 24, 56, 56]     [32, 24, 56, 56]     (10,710)             False\n",
              "│    └─Sequential (3)                                        [32, 24, 56, 56]     [32, 40, 28, 28]     --                   False\n",
              "│    │    └─MBConv (0)                                       [32, 24, 56, 56]     [32, 40, 28, 28]     (15,350)             False\n",
              "│    │    └─MBConv (1)                                       [32, 40, 28, 28]     [32, 40, 28, 28]     (31,290)             False\n",
              "│    └─Sequential (4)                                        [32, 40, 28, 28]     [32, 80, 14, 14]     --                   False\n",
              "│    │    └─MBConv (0)                                       [32, 40, 28, 28]     [32, 80, 14, 14]     (37,130)             False\n",
              "│    │    └─MBConv (1)                                       [32, 80, 14, 14]     [32, 80, 14, 14]     (102,900)            False\n",
              "│    │    └─MBConv (2)                                       [32, 80, 14, 14]     [32, 80, 14, 14]     (102,900)            False\n",
              "│    └─Sequential (5)                                        [32, 80, 14, 14]     [32, 112, 14, 14]    --                   False\n",
              "│    │    └─MBConv (0)                                       [32, 80, 14, 14]     [32, 112, 14, 14]    (126,004)            False\n",
              "│    │    └─MBConv (1)                                       [32, 112, 14, 14]    [32, 112, 14, 14]    (208,572)            False\n",
              "│    │    └─MBConv (2)                                       [32, 112, 14, 14]    [32, 112, 14, 14]    (208,572)            False\n",
              "│    └─Sequential (6)                                        [32, 112, 14, 14]    [32, 192, 7, 7]      --                   False\n",
              "│    │    └─MBConv (0)                                       [32, 112, 14, 14]    [32, 192, 7, 7]      (262,492)            False\n",
              "│    │    └─MBConv (1)                                       [32, 192, 7, 7]      [32, 192, 7, 7]      (587,952)            False\n",
              "│    │    └─MBConv (2)                                       [32, 192, 7, 7]      [32, 192, 7, 7]      (587,952)            False\n",
              "│    │    └─MBConv (3)                                       [32, 192, 7, 7]      [32, 192, 7, 7]      (587,952)            False\n",
              "│    └─Sequential (7)                                        [32, 192, 7, 7]      [32, 320, 7, 7]      --                   False\n",
              "│    │    └─MBConv (0)                                       [32, 192, 7, 7]      [32, 320, 7, 7]      (717,232)            False\n",
              "│    └─Conv2dNormActivation (8)                              [32, 320, 7, 7]      [32, 1280, 7, 7]     --                   False\n",
              "│    │    └─Conv2d (0)                                       [32, 320, 7, 7]      [32, 1280, 7, 7]     (409,600)            False\n",
              "│    │    └─BatchNorm2d (1)                                  [32, 1280, 7, 7]     [32, 1280, 7, 7]     (2,560)              False\n",
              "│    │    └─SiLU (2)                                         [32, 1280, 7, 7]     [32, 1280, 7, 7]     --                   --\n",
              "├─AdaptiveAvgPool2d (avgpool)                                [32, 1280, 7, 7]     [32, 1280, 1, 1]     --                   --\n",
              "├─Sequential (classifier)                                    [32, 1280]           [32, 3]              --                   True\n",
              "│    └─Dropout (0)                                           [32, 1280]           [32, 1280]           --                   --\n",
              "│    └─Linear (1)                                            [32, 1280]           [32, 3]              3,843                True\n",
              "============================================================================================================================================\n",
              "Total params: 4,011,391\n",
              "Trainable params: 3,843\n",
              "Non-trainable params: 4,007,548\n",
              "Total mult-adds (G): 12.31\n",
              "============================================================================================================================================\n",
              "Input size (MB): 19.27\n",
              "Forward/backward pass size (MB): 3452.09\n",
              "Params size (MB): 16.05\n",
              "Estimated Total Size (MB): 3487.41\n",
              "============================================================================================================================================"
            ]
          },
          "execution_count": 15,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# # Do a summary *after* freezing the features and changing the output classifier layer (uncomment for actual output)\n",
        "summary(model,\n",
        "        input_size=(32, 3, 224, 224), # make sure this is \"input_size\", not \"input_shape\" (batch_size, color_channels, height, width)\n",
        "        verbose=0,\n",
        "        col_names=[\"input_size\", \"output_size\", \"num_params\", \"trainable\"],\n",
        "        col_width=20,\n",
        "        row_settings=[\"var_names\"]\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "0604eef1-edc2-45c1-86a7-ebf20a147b59",
      "metadata": {
        "id": "0604eef1-edc2-45c1-86a7-ebf20a147b59"
      },
      "source": [
        "<img src=\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/06-torchinfo-summary-frozen-layers.png\" alt=\"output of torchinfo.summary() after freezing multiple layers in our model and changing the classifier head\" width=900/>\n",
        "\n",
        "Ho, ho! There's a fair few changes here!\n",
        "\n",
        "Let's go through them:\n",
        "* **Trainable column** - You'll see that many of the base layers (the ones in the `features` portion) have their Trainable value as `False`. This is because we set their attribute `requires_grad=False`. Unless we change this, these layers won't be updated during furture training.\n",
        "* **Output shape of `classifier`** - The `classifier` portion of the model now has an Output Shape value of `[32, 3]` instead of `[32, 1000]`. It's Trainable value is also `True`. This means its parameters will be updated during training. In essence, we're using the `features` portion to feed our `classifier` portion a base representation of an image and then our `classifier` layer is going to learn how to base representation aligns with our problem.\n",
        "* **Less trainable parameters** - Previously there was 5,288,548 trainable parameters. But since we froze many of the layers of the model and only left the `classifier` as trainable, there's now only 3,843 trainable parameters (even less than our TinyVGG model). Though there's also 4,007,548 non-trainable parameters, these will create a base representation of our input images to feed into our `classifier` layer.\n",
        "\n",
        "> **Note:** The more trainable parameters a model has, the more compute power/longer it takes to train. Freezing the base layers of our model and leaving it with less trainable parameters means our model should train quite quickly. This is one huge benefit of transfer learning, taking the already learned parameters of a model trained on a problem similar to yours and only tweaking the outputs slightly to suit your problem."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "dc075f8d-4394-49b3-83e6-5bf3500209f5",
      "metadata": {
        "id": "dc075f8d-4394-49b3-83e6-5bf3500209f5"
      },
      "source": [
        "## 4. Train model\n",
        "\n",
        "Now we've got a pretrained model that's semi-frozen and has a customised `classifier`, how about we see transfer learning in action?\n",
        "\n",
        "To begin training, let's create a loss function and an optimizer.\n",
        "\n",
        "Because we're still working with multi-class classification, we'll use `nn.CrossEntropyLoss()` for the loss function.\n",
        "\n",
        "And we'll stick with `torch.optim.Adam()` as our optimizer with `lr=0.001`.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "582200bb-c3f8-4044-ae59-007b921a2422",
      "metadata": {
        "id": "582200bb-c3f8-4044-ae59-007b921a2422"
      },
      "outputs": [],
      "source": [
        "# Define loss and optimizer\n",
        "loss_fn = nn.CrossEntropyLoss()\n",
        "optimizer = torch.optim.Adam(model.parameters(), lr=0.001)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "b94c81d7-e583-4171-9191-62b83d6e002e",
      "metadata": {
        "id": "b94c81d7-e583-4171-9191-62b83d6e002e"
      },
      "source": [
        "Wonderful!\n",
        "\n",
        "To train our model, we can use `train()` function we defined in the [05. PyTorch Going Modular section 04](https://www.learnpytorch.io/05_pytorch_going_modular/#4-creating-train_step-and-test_step-functions-and-train-to-combine-them).\n",
        "\n",
        "The `train()` function is in the [`engine.py`](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/going_modular/going_modular/engine.py) script inside the [`going_modular` directory](https://github.com/mrdbourke/pytorch-deep-learning/tree/main/going_modular/going_modular).\n",
        "\n",
        "Let's see how long it takes to train our model for 5 epochs.\n",
        "\n",
        "> **Note:** We're only going to be training the parameters `classifier` here as all of the other parameters in our model have been frozen."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "0e698d13-dedf-48f7-bca3-b21cd969b2d2",
      "metadata": {
        "id": "0e698d13-dedf-48f7-bca3-b21cd969b2d2",
        "outputId": "66c5fe76-f152-4fed-9c7d-6e1547cc0611",
        "colab": {
          "referenced_widgets": [
            "b61588abc1df499286a8e260d139026b"
          ]
        }
      },
      "outputs": [
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "b61588abc1df499286a8e260d139026b",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/5 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Epoch: 1 | train_loss: 1.0924 | train_acc: 0.3984 | test_loss: 0.9133 | test_acc: 0.5398\n",
            "Epoch: 2 | train_loss: 0.8717 | train_acc: 0.7773 | test_loss: 0.7912 | test_acc: 0.8153\n",
            "Epoch: 3 | train_loss: 0.7648 | train_acc: 0.7930 | test_loss: 0.7463 | test_acc: 0.8561\n",
            "Epoch: 4 | train_loss: 0.7108 | train_acc: 0.7539 | test_loss: 0.6372 | test_acc: 0.8655\n",
            "Epoch: 5 | train_loss: 0.6254 | train_acc: 0.7852 | test_loss: 0.6260 | test_acc: 0.8561\n",
            "[INFO] Total training time: 8.977 seconds\n"
          ]
        }
      ],
      "source": [
        "# Set the random seeds\n",
        "torch.manual_seed(42)\n",
        "torch.cuda.manual_seed(42)\n",
        "\n",
        "# Start the timer\n",
        "from timeit import default_timer as timer\n",
        "start_time = timer()\n",
        "\n",
        "# Setup training and save the results\n",
        "results = engine.train(model=model,\n",
        "                       train_dataloader=train_dataloader,\n",
        "                       test_dataloader=test_dataloader,\n",
        "                       optimizer=optimizer,\n",
        "                       loss_fn=loss_fn,\n",
        "                       epochs=5,\n",
        "                       device=device)\n",
        "\n",
        "# End the timer and print out how long it took\n",
        "end_time = timer()\n",
        "print(f\"[INFO] Total training time: {end_time-start_time:.3f} seconds\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "6ef14d56-d23a-4550-a19a-1a7cff1f3189",
      "metadata": {
        "id": "6ef14d56-d23a-4550-a19a-1a7cff1f3189"
      },
      "source": [
        "Wow!\n",
        "\n",
        "Our model trained quite fast (~5 seconds on my local machine with a [NVIDIA TITAN RTX GPU](https://www.nvidia.com/en-au/deep-learning-ai/products/titan-rtx/)/about 15 seconds on Google Colab with a [NVIDIA P100 GPU](https://www.nvidia.com/en-au/data-center/tesla-p100/)).\n",
        "\n",
        "And it looks like it smashed our previous model results out of the park!\n",
        "\n",
        "With an `efficientnet_b0` backbone, our model achieves almost 85%+ accuracy on the test dataset, almost *double* what we were able to achieve with TinyVGG.\n",
        "\n",
        "Not bad for a model we downloaded with a few lines of code."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "1a5fb2e3-4e5a-4517-a5ab-409dbe92ad86",
      "metadata": {
        "id": "1a5fb2e3-4e5a-4517-a5ab-409dbe92ad86"
      },
      "source": [
        "## 5. Evaluate model by plotting loss curves\n",
        "\n",
        "Our model looks like it's performing pretty well.\n",
        "\n",
        "Let's plot it's loss curves to see what the training looks like over time.\n",
        "\n",
        "We can plot the loss curves using the function `plot_loss_curves()` we created in [04. PyTorch Custom Datasets section 7.8](https://www.learnpytorch.io/04_pytorch_custom_datasets/#78-plot-the-loss-curves-of-model-0).\n",
        "\n",
        "The function is stored in the [`helper_functions.py`](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/helper_functions.py) script so we'll try to import it and download the script if we don't have it."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "c3c0c6af-3685-4814-b4f6-bd7abeeda28f",
      "metadata": {
        "id": "c3c0c6af-3685-4814-b4f6-bd7abeeda28f",
        "outputId": "a3478cf4-2a30-4974-a2fc-f57d0bafeb06"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1080x504 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Get the plot_loss_curves() function from helper_functions.py, download the file if we don't have it\n",
        "try:\n",
        "    from helper_functions import plot_loss_curves\n",
        "except:\n",
        "    print(\"[INFO] Couldn't find helper_functions.py, downloading...\")\n",
        "    with open(\"helper_functions.py\", \"wb\") as f:\n",
        "        import requests\n",
        "        request = requests.get(\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/helper_functions.py\")\n",
        "        f.write(request.content)\n",
        "    from helper_functions import plot_loss_curves\n",
        "\n",
        "# Plot the loss curves of our model\n",
        "plot_loss_curves(results)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "79d4b223-d9ee-48d3-84b5-56c082aa9016",
      "metadata": {
        "id": "79d4b223-d9ee-48d3-84b5-56c082aa9016"
      },
      "source": [
        "Those are some excellent looking loss curves!\n",
        "\n",
        "It looks like the loss for both datasets (train and test) is heading in the right direction.\n",
        "\n",
        "The same with the accuracy values, trending upwards.\n",
        "\n",
        "That goes to show the power of **transfer learning**. Using a pretrained model often leads to pretty good results with a small amount of data in less time.\n",
        "\n",
        "I wonder what would happen if you tried to train the model for longer? Or if we added more data?\n",
        "\n",
        "> **Question:** Looking at the loss curves, does our model look like it's overfitting or underfitting? Or perhaps neither? Hint: Check out notebook [04. PyTorch Custom Datasets part 8. What should an ideal loss curve look like?](https://www.learnpytorch.io/04_pytorch_custom_datasets/#8-what-should-an-ideal-loss-curve-look-like) for ideas."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "88eff8af-9fee-4ef2-881c-ff811827b0f3",
      "metadata": {
        "id": "88eff8af-9fee-4ef2-881c-ff811827b0f3"
      },
      "source": [
        "## 6. Make predictions on images from the test set\n",
        "\n",
        "It looks like our model performs well quantitatively but how about qualitatively?\n",
        "\n",
        "Let's find out by making some predictions with our model on images from the test set (these aren't seen during training) and plotting them.\n",
        "\n",
        "*Visualize, visualize, visualize!*\n",
        "\n",
        "One thing we'll have to remember is that for our model to make predictions on an image, the image has to be in *same* format as the images our model was trained on.\n",
        "\n",
        "This means we'll need to make sure our images have:\n",
        "* **Same shape** - If our images are different shapes to what our model was trained on, we'll get shape errors.\n",
        "* **Same datatype** - If our images are a different datatype (e.g. `torch.int8` vs. `torch.float32`) we'll get datatype errors.\n",
        "* **Same device** - If our images are on a different device to our model, we'll get device errors.\n",
        "* **Same transformations** - If our model is trained on images that have been transformed in certain way (e.g. normalized with a specific mean and standard deviation) and we try and make preidctions on images transformed in a different way, these predictions may be off.\n",
        "\n",
        "> **Note:** These requirements go for all kinds of data if you're trying to make predictions with a trained model. Data you'd like to predict on should be in the same format as your model was trained on.\n",
        "\n",
        "To do all of this, we'll create a function `pred_and_plot_image()` to:\n",
        "\n",
        "1. Take in a trained model, a list of class names, a filepath to a target image, an image size, a transform and a target device.\n",
        "2. Open an image with [`PIL.Image.open()`](https://pillow.readthedocs.io/en/stable/reference/Image.html#PIL.Image.open).\n",
        "3. Create a transform for the image (this will default to the `manual_transforms` we created above or it could use a transform generated from `weights.transforms()`).\n",
        "4. Make sure the model is on the target device.\n",
        "5. Turn on model eval mode with `model.eval()` (this turns off layers like `nn.Dropout()`, so they aren't used for inference) and the inference mode context manager.\n",
        "6. Transform the target image with the transform made in step 3 and add an extra batch dimension with `torch.unsqueeze(dim=0)` so our input image has shape `[batch_size, color_channels, height, width]`.\n",
        "7. Make a prediction on the image by passing it to the model ensuring it's on the target device.\n",
        "8. Convert the model's output logits to prediction probabilities with `torch.softmax()`.\n",
        "9. Convert model's prediction probabilities to prediction labels with `torch.argmax()`.\n",
        "10. Plot the image with `matplotlib` and set the title to the prediction label from step 9 and prediction probability from step 8.\n",
        "\n",
        "> **Note:** This is a similar function to [04. PyTorch Custom Datasets section 11.3's](https://www.learnpytorch.io/04_pytorch_custom_datasets/#113-putting-custom-image-prediction-together-building-a-function) `pred_and_plot_image()` with a few tweaked steps."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "96fcc4a2-2e27-499b-aa28-05c37c529a5c",
      "metadata": {
        "id": "96fcc4a2-2e27-499b-aa28-05c37c529a5c"
      },
      "outputs": [],
      "source": [
        "from typing import List, Tuple\n",
        "\n",
        "from PIL import Image\n",
        "\n",
        "# 1. Take in a trained model, class names, image path, image size, a transform and target device\n",
        "def pred_and_plot_image(model: torch.nn.Module,\n",
        "                        image_path: str,\n",
        "                        class_names: List[str],\n",
        "                        image_size: Tuple[int, int] = (224, 224),\n",
        "                        transform: torchvision.transforms = None,\n",
        "                        device: torch.device=device):\n",
        "\n",
        "\n",
        "    # 2. Open image\n",
        "    img = Image.open(image_path)\n",
        "\n",
        "    # 3. Create transformation for image (if one doesn't exist)\n",
        "    if transform is not None:\n",
        "        image_transform = transform\n",
        "    else:\n",
        "        image_transform = transforms.Compose([\n",
        "            transforms.Resize(image_size),\n",
        "            transforms.ToTensor(),\n",
        "            transforms.Normalize(mean=[0.485, 0.456, 0.406],\n",
        "                                 std=[0.229, 0.224, 0.225]),\n",
        "        ])\n",
        "\n",
        "    ### Predict on image ###\n",
        "\n",
        "    # 4. Make sure the model is on the target device\n",
        "    model.to(device)\n",
        "\n",
        "    # 5. Turn on model evaluation mode and inference mode\n",
        "    model.eval()\n",
        "    with torch.inference_mode():\n",
        "      # 6. Transform and add an extra dimension to image (model requires samples in [batch_size, color_channels, height, width])\n",
        "      transformed_image = image_transform(img).unsqueeze(dim=0)\n",
        "\n",
        "      # 7. Make a prediction on image with an extra dimension and send it to the target device\n",
        "      target_image_pred = model(transformed_image.to(device))\n",
        "\n",
        "    # 8. Convert logits -> prediction probabilities (using torch.softmax() for multi-class classification)\n",
        "    target_image_pred_probs = torch.softmax(target_image_pred, dim=1)\n",
        "\n",
        "    # 9. Convert prediction probabilities -> prediction labels\n",
        "    target_image_pred_label = torch.argmax(target_image_pred_probs, dim=1)\n",
        "\n",
        "    # 10. Plot image with predicted label and probability\n",
        "    plt.figure()\n",
        "    plt.imshow(img)\n",
        "    plt.title(f\"Pred: {class_names[target_image_pred_label]} | Prob: {target_image_pred_probs.max():.3f}\")\n",
        "    plt.axis(False);"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "4075c6d1-e329-435f-b688-7b21f1630265",
      "metadata": {
        "id": "4075c6d1-e329-435f-b688-7b21f1630265"
      },
      "source": [
        "What a good looking function!\n",
        "\n",
        "Let's test it out by making predictions on a few random images from the test set.\n",
        "\n",
        "We can get a list of all the test image paths using `list(Path(test_dir).glob(\"*/*.jpg\"))`, the stars in the `glob()` method say \"any file matching this pattern\", in other words, any file ending in `.jpg` (all of our images).\n",
        "\n",
        "And then we can randomly sample a number of these using Python's [`random.sample(populuation, k)`](https://docs.python.org/3/library/random.html#random.sample) where `population` is the sequence to sample and `k` is the number of samples to retrieve."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "e5e431b7-b7b7-4b7e-99a8-076bc96c8fa4",
      "metadata": {
        "id": "e5e431b7-b7b7-4b7e-99a8-076bc96c8fa4",
        "outputId": "ab317033-299b-4554-ef13-6e06e755b0c3"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Get a random list of image paths from test set\n",
        "import random\n",
        "num_images_to_plot = 3\n",
        "test_image_path_list = list(Path(test_dir).glob(\"*/*.jpg\")) # get list all image paths from test data\n",
        "test_image_path_sample = random.sample(population=test_image_path_list, # go through all of the test image paths\n",
        "                                       k=num_images_to_plot) # randomly select 'k' image paths to pred and plot\n",
        "\n",
        "# Make predictions on and plot the images\n",
        "for image_path in test_image_path_sample:\n",
        "    pred_and_plot_image(model=model,\n",
        "                        image_path=image_path,\n",
        "                        class_names=class_names,\n",
        "                        # transform=weights.transforms(), # optionally pass in a specified transform from our pretrained model weights\n",
        "                        image_size=(224, 224))"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "c7f6dc1c-0ef3-49a1-bd3d-ad56311898b1",
      "metadata": {
        "id": "c7f6dc1c-0ef3-49a1-bd3d-ad56311898b1"
      },
      "source": [
        "Woohoo!\n",
        "\n",
        "Those predictions look far better than the ones our TinyVGG model was previously making."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "d56c914f-e653-454e-b14a-09f8e0f032e6",
      "metadata": {
        "id": "d56c914f-e653-454e-b14a-09f8e0f032e6"
      },
      "source": [
        "### 6.1 Making predictions on a custom image\n",
        "\n",
        "It looks like our model does well qualitatively on data from the test set.\n",
        "\n",
        "But how about on our own custom image?\n",
        "\n",
        "That's where the real fun of machine learning is!\n",
        "\n",
        "Predicting on your own custom data, outisde of any training or test set.\n",
        "\n",
        "To test our model on a custom image, let's import the old faithful `pizza-dad.jpeg` image (an image of my dad eating pizza).\n",
        "\n",
        "We'll then pass it to the `pred_and_plot_image()` function we created above and see what happens."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "db9f9b21-4b58-4394-8ed4-b4ba704812a3",
      "metadata": {
        "id": "db9f9b21-4b58-4394-8ed4-b4ba704812a3",
        "outputId": "2dbdff63-3c41-4db8-c763-11ab0af4b929"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "data/04-pizza-dad.jpeg already exists, skipping download.\n"
          ]
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Download custom image\n",
        "import requests\n",
        "\n",
        "# Setup custom image path\n",
        "custom_image_path = data_path / \"04-pizza-dad.jpeg\"\n",
        "\n",
        "# Download the image if it doesn't already exist\n",
        "if not custom_image_path.is_file():\n",
        "    with open(custom_image_path, \"wb\") as f:\n",
        "        # When downloading from GitHub, need to use the \"raw\" file link\n",
        "        request = requests.get(\"https://raw.githubusercontent.com/mrdbourke/pytorch-deep-learning/main/images/04-pizza-dad.jpeg\")\n",
        "        print(f\"Downloading {custom_image_path}...\")\n",
        "        f.write(request.content)\n",
        "else:\n",
        "    print(f\"{custom_image_path} already exists, skipping download.\")\n",
        "\n",
        "# Predict on custom image\n",
        "pred_and_plot_image(model=model,\n",
        "                    image_path=custom_image_path,\n",
        "                    class_names=class_names)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "cc078b95-c95b-43b6-a1d0-7d4e32f18fa7",
      "metadata": {
        "id": "cc078b95-c95b-43b6-a1d0-7d4e32f18fa7"
      },
      "source": [
        "Two thumbs up!\n",
        "\n",
        "Looks like our model got it right again!\n",
        "\n",
        "But this time the prediction probability is higher than the one from TinyVGG (`0.373`) in [04. PyTorch Custom Datasets section 11.3](https://www.learnpytorch.io/04_pytorch_custom_datasets/#113-putting-custom-image-prediction-together-building-a-function).\n",
        "\n",
        "This indicates our `efficientnet_b0` model is *more* confident in its prediction where as our TinyVGG model was par with just guessing."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "20aa0596-d655-4b2f-a7b4-2ccfeceba958",
      "metadata": {
        "id": "20aa0596-d655-4b2f-a7b4-2ccfeceba958"
      },
      "source": [
        "## Main takeaways\n",
        "* **Transfer learning** often allows to you get good results with a relatively small amount of custom data.\n",
        "* Knowing the power of transfer learning, it's a good idea to ask at the start of every problem, \"does an existing well-performing model exist for my problem?\"\n",
        "* When using a pretrained model, it's important that your custom data be formatted/preprocessed in the same way that the original model was trained on, otherwise you may get degraded performance.\n",
        "* The same goes for predicting on custom data, ensure your custom data is in the same format as the data your model was trained on.\n",
        "* There are [several different places to find pretrained models](https://www.learnpytorch.io/06_pytorch_transfer_learning/#where-to-find-pretrained-models) from the PyTorch domain libraries, HuggingFace Hub and libraries such as `timm` (PyTorch Image Models)."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "15b7cd60-fe0f-4a74-b121-9525c82913b1",
      "metadata": {
        "id": "15b7cd60-fe0f-4a74-b121-9525c82913b1"
      },
      "source": [
        "## Exercises\n",
        "\n",
        "All of the exercises are focused on practicing the code above.\n",
        "\n",
        "You should be able to complete them by referencing each section or by following the resource(s) linked.\n",
        "\n",
        "All exercises should be completed using [device-agnostic code](https://pytorch.org/docs/stable/notes/cuda.html#device-agnostic-code).\n",
        "\n",
        "**Resources:**\n",
        "* [Exercise template notebook for 06](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/exercises/06_pytorch_transfer_learning_exercises.ipynb)\n",
        "* [Example solutions notebook for 06](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/solutions/06_pytorch_transfer_learning_exercise_solutions.ipynb) (try the exercises *before* looking at this)\n",
        "    * See a live [video walkthrough of the solutions on YouTube](https://youtu.be/ueLolShyFqs) (errors and all)\n",
        "\n",
        "1. Make predictions on the entire test dataset and plot a confusion matrix for the results of our model compared to the truth labels. Check out [03. PyTorch Computer Vision section 10](https://www.learnpytorch.io/03_pytorch_computer_vision/#10-making-a-confusion-matrix-for-further-prediction-evaluation) for ideas.\n",
        "2. Get the \"most wrong\" of the predictions on the test dataset and plot the 5 \"most wrong\" images. You can do this by:\n",
        "    * Predicting across all of the test dataset, storing the labels and predicted probabilities.\n",
        "    * Sort the predictions by *wrong prediction* and then *descending predicted probabilities*, this will give you the wrong predictions with the *highest* prediction probabilities, in other words, the \"most wrong\".\n",
        "    * Plot the top 5 \"most wrong\" images, why do you think the model got these wrong?\n",
        "3. Predict on your own image of pizza/steak/sushi - how does the model go? What happens if you predict on an image that isn't pizza/steak/sushi?\n",
        "4. Train the model from section 4 above for longer (10 epochs should do), what happens to the performance?\n",
        "5. Train the model from section 4 above with more data, say 20% of the images from Food101 of Pizza, Steak and Sushi images.\n",
        "    * You can find the [20% Pizza, Steak, Sushi dataset](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/data/pizza_steak_sushi_20_percent.zip) on the course GitHub. It was created with the notebook [`extras/04_custom_data_creation.ipynb`](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/04_custom_data_creation.ipynb).\n",
        "6. Try a different model from [`torchvision.models`](https://pytorch.org/vision/stable/models.html) on the Pizza, Steak, Sushi data, how does this model perform?\n",
        "    * You'll have to change the size of the classifier layer to suit our problem.\n",
        "    * You may want to try an EfficientNet with a higher number than our B0, perhaps `torchvision.models.efficientnet_b2()`?\n",
        "  \n",
        "## Extra-curriculum\n",
        "* Look up what \"model fine-tuning\" is and spend 30-minutes researching different methods to perform it with PyTorch. How would we change our code to fine-tine? Tip: fine-tuning usually works best if you have *lots* of custom data, where as, feature extraction is typically better if you have less custom data.\n",
        "* Check out the new/upcoming [PyTorch multi-weights API](https://pytorch.org/blog/introducing-torchvision-new-multi-weight-support-api/) (still in beta at time of writing, May 2022), it's a new way to perform transfer learning in PyTorch. What changes to our code would need to made to use the new API?\n",
        "* Try to create your own classifier on two classes of images, for example, you could collect 10 photos of your dog and your friends dog and train a model to classify the two dogs. This would be a good way to practice creating a dataset as well as building a model on that dataset."
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.9.13"
    },
    "vscode": {
      "interpreter": {
        "hash": "3fbe1355223f7b2ffc113ba3ade6a2b520cadace5d5ec3e828c83ce02eb221bf"
      }
    },
    "colab": {
      "provenance": []
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}