963 lines (963 with data), 226.7 kB

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 65,
      "metadata": {
        "id": "UJOq3mdA8PAH",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "outputId": "8e871ff0-046c-4354-bf46-124aeba22f97"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Time in seconds since beginning of run: 1695669942.0228107\n",
            "Mon Sep 25 19:25:42 2023\n"
          ]
        }
      ],
      "source": [
        "# This cell is added by sphinx-gallery\n",
        "# It can be customized to whatever you like\n",
        "%matplotlib inline\n",
        "\n",
        "# from google.colab import drive\n",
        "# drive.mount('/content/drive')\n",
        "# !pip install pennylane\n",
        "\n",
        "import time\n",
        "seconds = time.time()\n",
        "print(\"Time in seconds since beginning of run:\", seconds)\n",
        "local_time = time.ctime(seconds)\n",
        "print(local_time)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 66,
      "metadata": {
        "id": "5ljdosVS8PAP"
      },
      "outputs": [],
      "source": [
        "# Some parts of this code are based on the Python script:\n",
        "# https://github.com/pytorch/tutorials/blob/master/beginner_source/transfer_learning_tutorial.py\n",
        "# License: BSD\n",
        "\n",
        "import os\n",
        "import copy\n",
        "\n",
        "# PyTorch\n",
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "from torch.optim import lr_scheduler\n",
        "import torchvision\n",
        "from torchvision import datasets, transforms\n",
        "\n",
        "# Pennylane\n",
        "import pennylane as qml\n",
        "from pennylane import numpy as np\n",
        "\n",
        "torch.manual_seed(42)\n",
        "np.random.seed(42)\n",
        "\n",
        "# Plotting\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "# OpenMP: number of parallel threads.\n",
        "os.environ[\"OMP_NUM_THREADS\"] = \"1\""
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "1AFilzYk8PAQ"
      },
      "source": [
        "Setting of the main hyper-parameters of the model\n",
        "=================================================\n",
        "\n",
        "::: {.note}\n",
        "::: {.title}\n",
        "Note\n",
        ":::\n",
        "\n",
        "To reproduce the results of Ref. \\[1\\], `num_epochs` should be set to\n",
        "`30` which may take a long time. We suggest to first try with\n",
        "`num_epochs=1` and, if everything runs smoothly, increase it to a larger\n",
        "value.\n",
        ":::\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 67,
      "metadata": {
        "id": "5LRcEYZg8PAR"
      },
      "outputs": [],
      "source": [
        "n_qubits = 4                # Number of qubits\n",
        "step = 0.0004               # Learning rate\n",
        "batch_size = 4              # Number of samples for each training step\n",
        "num_epochs = 5              # Number of training epochs\n",
        "q_depth = 3                 # Depth of the quantum circuit (number of variational layers)\n",
        "gamma_lr_scheduler = 0.1    # Learning rate reduction applied every 10 epochs.\n",
        "q_delta = 0.01              # Initial spread of random quantum weights\n",
        "start_time = time.time()    # Start of the computation timer"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NlU2Q7zd8PAR"
      },
      "source": [
        "We initialize a PennyLane device with a `default.qubit` backend.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 68,
      "metadata": {
        "id": "0prgZPLK8PAR"
      },
      "outputs": [],
      "source": [
        "dev = qml.device(\"default.qubit\", wires=n_qubits)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "54jRIpbZ8PAS"
      },
      "source": [
        "We configure PyTorch to use CUDA only if available. Otherwise the CPU is\n",
        "used.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 69,
      "metadata": {
        "id": "23nQUjLm8PAS"
      },
      "outputs": [],
      "source": [
        "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-AJzWJGi8PAT"
      },
      "source": [
        "Dataset loading\n",
        "===============\n",
        "\n",
        "::: {.note}\n",
        "::: {.title}\n",
        "Note\n",
        ":::\n",
        "\n",
        "The dataset containing images of *ants* and *bees* can be downloaded\n",
        "[here](https://download.pytorch.org/tutorial/hymenoptera_data.zip) and\n",
        "should be extracted in the subfolder `../_data/hymenoptera_data`.\n",
        ":::\n",
        "\n",
        "This is a very small dataset (roughly 250 images), too small for\n",
        "training from scratch a classical or quantum model, however it is enough\n",
        "when using *transfer learning* approach.\n",
        "\n",
        "The PyTorch packages `torchvision` and `torch.utils.data` are used for\n",
        "loading the dataset and performing standard preliminary image\n",
        "operations: resize, center, crop, normalize, *etc.*\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 70,
      "metadata": {
        "id": "XaNa12un8PAT"
      },
      "outputs": [],
      "source": [
        "data_transforms = {\n",
        "    \"train\": transforms.Compose(\n",
        "        [\n",
        "            # transforms.RandomResizedCrop(224),     # uncomment for data augmentation\n",
        "            # transforms.RandomHorizontalFlip(),     # uncomment for data augmentation\n",
        "            transforms.Resize(256),\n",
        "            transforms.CenterCrop(224),\n",
        "            transforms.ToTensor(),\n",
        "            # Normalize input channels using mean values and standard deviations of ImageNet.\n",
        "            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),\n",
        "        ]\n",
        "    ),\n",
        "    \"val\": transforms.Compose(\n",
        "        [\n",
        "            transforms.Resize(256),\n",
        "            transforms.CenterCrop(224),\n",
        "            transforms.ToTensor(),\n",
        "            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),\n",
        "        ]\n",
        "    ),\n",
        "}\n",
        "\n",
        "data_dir = \"/content/drive/MyDrive/Colab Notebooks/data/44 Class 4478 Brain Tumor Images Split 0.627 Shuffle Rename\"\n",
        "image_datasets = {\n",
        "    x if x == \"train\" else \"validation\": datasets.ImageFolder(\n",
        "        os.path.join(data_dir, x), data_transforms[x]\n",
        "    )\n",
        "    for x in [\"train\", \"val\"]\n",
        "}\n",
        "dataset_sizes = {x: len(image_datasets[x]) for x in [\"train\", \"validation\"]}\n",
        "class_names = image_datasets[\"train\"].classes\n",
        "\n",
        "# Initialize dataloader\n",
        "dataloaders = {\n",
        "    x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True)\n",
        "    for x in [\"train\", \"validation\"]\n",
        "}\n",
        "\n",
        "# function to plot images\n",
        "def imshow(inp, title=None):\n",
        "    \"\"\"Display image from tensor.\"\"\"\n",
        "    inp = inp.numpy().transpose((1, 2, 0))\n",
        "    # Inverse of the initial normalization operation.\n",
        "    mean = np.array([0.485, 0.456, 0.406])\n",
        "    std = np.array([0.229, 0.224, 0.225])\n",
        "    inp = std * inp + mean\n",
        "    inp = np.clip(inp, 0, 1)\n",
        "    plt.imshow(inp)\n",
        "    if title is not None:\n",
        "        plt.title(title)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ANdmcnR98PAU"
      },
      "source": [
        "Let us show a batch of the test data, just to have an idea of the\n",
        "classification problem.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 71,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 207
        },
        "id": "QzIKQxS78PAU",
        "outputId": "e684d191-9bd3-4507-a383-78bdb08084c9"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Get a batch of training data\n",
        "inputs, classes = next(iter(dataloaders[\"validation\"]))\n",
        "\n",
        "# Make a grid from batch\n",
        "out = torchvision.utils.make_grid(inputs)\n",
        "\n",
        "imshow(out, title=[class_names[x] for x in classes])\n",
        "\n",
        "dataloaders = {\n",
        "    x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True)\n",
        "    for x in [\"train\", \"validation\"]\n",
        "}"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_ULbO8f28PAU"
      },
      "source": [
        "Variational quantum circuit\n",
        "===========================\n",
        "\n",
        "We first define some quantum layers that will compose the quantum\n",
        "circuit.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 72,
      "metadata": {
        "id": "6gMomjvL8PAV"
      },
      "outputs": [],
      "source": [
        "def H_layer(nqubits):\n",
        "    \"\"\"Layer of single-qubit Hadamard gates.\n",
        "    \"\"\"\n",
        "    for idx in range(nqubits):\n",
        "        qml.Hadamard(wires=idx)\n",
        "\n",
        "\n",
        "def RY_layer(w):\n",
        "    \"\"\"Layer of parametrized qubit rotations around the y axis.\n",
        "    \"\"\"\n",
        "    for idx, element in enumerate(w):\n",
        "        qml.RY(element, wires=idx)\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0iroynmF8PAV"
      },
      "source": [
        "Now we define the quantum circuit through the PennyLane\n",
        "[qnode]{.title-ref} decorator .\n",
        "\n",
        "The structure is that of a typical variational quantum circuit:\n",
        "\n",
        "-   **Embedding layer:** All qubits are first initialized in a balanced\n",
        "    superposition of *up* and *down* states, then they are rotated\n",
        "    according to the input parameters (local embedding).\n",
        "-   **Variational layers:** A sequence of trainable rotation layers and\n",
        "    constant entangling layers is applied.\n",
        "-   **Measurement layer:** For each qubit, the local expectation value\n",
        "    of the $Z$ operator is measured. This produces a classical output\n",
        "    vector, suitable for additional post-processing.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 73,
      "metadata": {
        "id": "ONyq04RY8PAV"
      },
      "outputs": [],
      "source": [
        "@qml.qnode(dev, interface=\"torch\")\n",
        "def quantum_net(q_input_features, q_weights_flat):\n",
        "    \"\"\"\n",
        "    The variational quantum circuit.\n",
        "    \"\"\"\n",
        "\n",
        "    # Reshape weights\n",
        "    q_weights = q_weights_flat.reshape(q_depth, n_qubits)\n",
        "\n",
        "    # Start from state |+> , unbiased w.r.t. |0> and |1>\n",
        "    H_layer(n_qubits)\n",
        "\n",
        "    # Embed features in the quantum node\n",
        "    RY_layer(q_input_features)\n",
        "\n",
        "    # Sequence of trainable variational layers\n",
        "    for k in range(q_depth):\n",
        "        RY_layer(q_weights[k])\n",
        "\n",
        "    # Expectation values in the Z basis\n",
        "    exp_vals = [qml.expval(qml.PauliZ(position)) for position in range(n_qubits)]\n",
        "    return tuple(exp_vals)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4eG97j4f8PAV"
      },
      "source": [
        "Dressed quantum circuit\n",
        "=======================\n",
        "\n",
        "We can now define a custom `torch.nn.Module` representing a *dressed*\n",
        "quantum circuit.\n",
        "\n",
        "This is a concatenation of:\n",
        "\n",
        "-   A classical pre-processing layer (`nn.Linear`).\n",
        "-   A classical activation function (`torch.tanh`).\n",
        "-   A constant `np.pi/2.0` scaling.\n",
        "-   The previously defined quantum circuit (`quantum_net`).\n",
        "-   A classical post-processing layer (`nn.Linear`).\n",
        "\n",
        "The input of the module is a batch of vectors with 512 real parameters\n",
        "(features) and the output is a batch of vectors with two real outputs\n",
        "(associated with the two classes of images: *ants* and *bees*).\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 74,
      "metadata": {
        "id": "hIljGdv_8PAW"
      },
      "outputs": [],
      "source": [
        "class DressedQuantumNet(nn.Module):\n",
        "    \"\"\"\n",
        "    Torch module implementing the *dressed* quantum net.\n",
        "    \"\"\"\n",
        "\n",
        "    def __init__(self):\n",
        "        \"\"\"\n",
        "        Definition of the *dressed* layout.\n",
        "        \"\"\"\n",
        "\n",
        "        super().__init__()\n",
        "        self.pre_net = nn.Linear(2048, n_qubits)\n",
        "        self.q_params = nn.Parameter(q_delta * torch.randn(q_depth * n_qubits))\n",
        "        self.post_net = nn.Linear(n_qubits, 44)\n",
        "\n",
        "    def forward(self, input_features):\n",
        "        \"\"\"\n",
        "        Defining how tensors are supposed to move through the *dressed* quantum\n",
        "        net.\n",
        "        \"\"\"\n",
        "\n",
        "        # obtain the input features for the quantum circuit\n",
        "        # by reducing the feature dimension from 512 to 4\n",
        "        pre_out = self.pre_net(input_features)\n",
        "        q_in = torch.tanh(pre_out) * np.pi / 2.0\n",
        "\n",
        "        # Apply the quantum circuit to each element of the batch and append to q_out\n",
        "        q_out = torch.Tensor(0, n_qubits)\n",
        "        q_out = q_out.to(device)\n",
        "        for elem in q_in:\n",
        "            q_out_elem = torch.hstack(quantum_net(elem, self.q_params)).float().unsqueeze(0)\n",
        "            q_out = torch.cat((q_out, q_out_elem))\n",
        "\n",
        "        # return the two-dimensional prediction from the postprocessing layer\n",
        "        return self.post_net(q_out)\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "E8-EDnhn8PAW"
      },
      "source": [
        "Hybrid classical-quantum model\n",
        "==============================\n",
        "\n",
        "We are finally ready to build our full hybrid classical-quantum network.\n",
        "We follow the *transfer learning* approach:\n",
        "\n",
        "1.  First load the classical pre-trained network *ResNet18* from the\n",
        "    `torchvision.models` zoo.\n",
        "2.  Freeze all the weights since they should not be trained.\n",
        "3.  Replace the last fully connected layer with our trainable dressed\n",
        "    quantum circuit (`DressedQuantumNet`).\n",
        "\n",
        "::: {.note}\n",
        "::: {.title}\n",
        "Note\n",
        ":::\n",
        "\n",
        "The *ResNet18* model is automatically downloaded by PyTorch and it may\n",
        "take several minutes (only the first time).\n",
        ":::\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 75,
      "metadata": {
        "id": "lnJnW_ra8PAX"
      },
      "outputs": [],
      "source": [
        "model_hybrid = torchvision.models.resnet50(pretrained=True)\n",
        "\n",
        "for param in model_hybrid.parameters():\n",
        "    param.requires_grad = False\n",
        "\n",
        "\n",
        "# Notice that model_hybrid.fc is the last layer of ResNet18\n",
        "model_hybrid.fc = DressedQuantumNet()\n",
        "\n",
        "# Use CUDA or CPU according to the \"device\" object.\n",
        "model_hybrid = model_hybrid.to(device)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5k96EBuZ8PAX"
      },
      "source": [
        "Training and results\n",
        "====================\n",
        "\n",
        "Before training the network we need to specify the *loss* function.\n",
        "\n",
        "We use, as usual in classification problem, the *cross-entropy* which is\n",
        "directly available within `torch.nn`.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 76,
      "metadata": {
        "id": "BKvfgR5N8PAX"
      },
      "outputs": [],
      "source": [
        "criterion = nn.CrossEntropyLoss()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "UUvuVdii8PAX"
      },
      "source": [
        "We also initialize the *Adam optimizer* which is called at each training\n",
        "step in order to update the weights of the model.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 77,
      "metadata": {
        "id": "bPI2SbMQ8PAX"
      },
      "outputs": [],
      "source": [
        "optimizer_hybrid = optim.Adam(model_hybrid.fc.parameters(), lr=step)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "a8wMKvP48PAY"
      },
      "source": [
        "We schedule to reduce the learning rate by a factor of\n",
        "`gamma_lr_scheduler` every 10 epochs.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 78,
      "metadata": {
        "id": "dLQsPIzy8PAY"
      },
      "outputs": [],
      "source": [
        "exp_lr_scheduler = lr_scheduler.StepLR(\n",
        "    optimizer_hybrid, step_size=10, gamma=gamma_lr_scheduler\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Q-xTUZhq8PAY"
      },
      "source": [
        "What follows is a training function that will be called later. This\n",
        "function should return a trained model that can be used to make\n",
        "predictions (classifications).\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 79,
      "metadata": {
        "id": "rppVRya_8PAY"
      },
      "outputs": [],
      "source": [
        "def train_model(model, criterion, optimizer, scheduler, num_epochs):\n",
        "    since = time.time()\n",
        "    best_model_wts = copy.deepcopy(model.state_dict())\n",
        "    best_acc = 0.0\n",
        "    best_loss = 10000.0  # Large arbitrary number\n",
        "    best_acc_train = 0.0\n",
        "    best_loss_train = 10000.0  # Large arbitrary number\n",
        "    print(\"Training started:\")\n",
        "\n",
        "    for epoch in range(num_epochs):\n",
        "\n",
        "        # Each epoch has a training and validation phase\n",
        "        for phase in [\"train\", \"validation\"]:\n",
        "            if phase == \"train\":\n",
        "                # Set model to training mode\n",
        "                model.train()\n",
        "            else:\n",
        "                # Set model to evaluate mode\n",
        "                model.eval()\n",
        "            running_loss = 0.0\n",
        "            running_corrects = 0\n",
        "\n",
        "            # Iterate over data.\n",
        "            n_batches = dataset_sizes[phase] // batch_size\n",
        "            it = 0\n",
        "            for inputs, labels in dataloaders[phase]:\n",
        "                since_batch = time.time()\n",
        "                batch_size_ = len(inputs)\n",
        "                inputs = inputs.to(device)\n",
        "                labels = labels.to(device)\n",
        "                optimizer.zero_grad()\n",
        "\n",
        "                # Track/compute gradient and make an optimization step only when training\n",
        "                with torch.set_grad_enabled(phase == \"train\"):\n",
        "                    outputs = model(inputs)\n",
        "                    _, preds = torch.max(outputs, 1)\n",
        "                    loss = criterion(outputs, labels)\n",
        "                    if phase == \"train\":\n",
        "                        loss.backward()\n",
        "                        optimizer.step()\n",
        "\n",
        "                # Print iteration results\n",
        "                running_loss += loss.item() * batch_size_\n",
        "                batch_corrects = torch.sum(preds == labels.data).item()\n",
        "                running_corrects += batch_corrects\n",
        "                print(\n",
        "                    \"Phase: {} Epoch: {}/{} Iter: {}/{} Batch time: {:.4f}\".format(\n",
        "                        phase,\n",
        "                        epoch + 1,\n",
        "                        num_epochs,\n",
        "                        it + 1,\n",
        "                        n_batches + 1,\n",
        "                        time.time() - since_batch,\n",
        "                    ),\n",
        "                    end=\"\\r\",\n",
        "                    flush=True,\n",
        "                )\n",
        "                it += 1\n",
        "\n",
        "            # Print epoch results\n",
        "            epoch_loss = running_loss / dataset_sizes[phase]\n",
        "            epoch_acc = running_corrects / dataset_sizes[phase]\n",
        "            print(\n",
        "                \"Phase: {} Epoch: {}/{} Loss: {:.4f} Acc: {:.4f}        \".format(\n",
        "                    \"train\" if phase == \"train\" else \"validation  \",\n",
        "                    epoch + 1,\n",
        "                    num_epochs,\n",
        "                    epoch_loss,\n",
        "                    epoch_acc,\n",
        "                )\n",
        "            )\n",
        "\n",
        "            # Check if this is the best model wrt previous epochs\n",
        "            if phase == \"validation\" and epoch_acc > best_acc:\n",
        "                best_acc = epoch_acc\n",
        "                best_model_wts = copy.deepcopy(model.state_dict())\n",
        "            if phase == \"validation\" and epoch_loss < best_loss:\n",
        "                best_loss = epoch_loss\n",
        "            if phase == \"train\" and epoch_acc > best_acc_train:\n",
        "                best_acc_train = epoch_acc\n",
        "            if phase == \"train\" and epoch_loss < best_loss_train:\n",
        "                best_loss_train = epoch_loss\n",
        "\n",
        "            # Update learning rate\n",
        "            if phase == \"train\":\n",
        "                scheduler.step()\n",
        "\n",
        "    # Print final results\n",
        "    model.load_state_dict(best_model_wts)\n",
        "    time_elapsed = time.time() - since\n",
        "    print(\n",
        "        \"Training completed in {:.0f}m {:.0f}s\".format(time_elapsed // 60, time_elapsed % 60)\n",
        "    )\n",
        "    print(\"Best test loss: {:.4f} | Best test accuracy: {:.4f}\".format(best_loss, best_acc))\n",
        "    return model"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "a_XtRwDI8PAZ"
      },
      "source": [
        "We are ready to perform the actual training process.\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from IPython.display import display, Javascript\n",
        "\n",
        "# Run this cell to keep Colab awake\n",
        "display(Javascript('''\n",
        "  function keep_colab_awake(){\n",
        "    console.log(\"Colab is being kept awake.\");\n",
        "    document.querySelector(\"#top-toolbar > colab-connect-button\").shadowRoot.querySelector(\"#connect\").click();\n",
        "    document.querySelector(\"body > colab-sandbox-output > div > div.output.container.output-wrapper > div.output > pre\").innerText;\n",
        "    setTimeout(keep_colab_awake, 61000);\n",
        "  }\n",
        "  keep_colab_awake();\n",
        "'''))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 17
        },
        "id": "p2W621Tsy2hY",
        "outputId": "4b78ea53-4cc0-45d8-87bd-e71c6135eec4"
      },
      "execution_count": 80,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "  function keep_colab_awake(){\n",
              "    console.log(\"Colab is being kept awake.\");\n",
              "    document.querySelector(\"#top-toolbar > colab-connect-button\").shadowRoot.querySelector(\"#connect\").click();\n",
              "    document.querySelector(\"body > colab-sandbox-output > div > div.output.container.output-wrapper > div.output > pre\").innerText;\n",
              "    setTimeout(keep_colab_awake, 61000);\n",
              "  }\n",
              "  keep_colab_awake();\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 81,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "5VgfdD3-8PAZ",
        "outputId": "c8ac013c-f4da-4125-88ca-f76c371a1caa"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training started:\n",
            "Phase: train Epoch: 1/5 Loss: 3.7091 Acc: 0.0492        \n",
            "Phase: validation   Epoch: 1/5 Loss: 3.6138 Acc: 0.0604        \n",
            "Phase: train Epoch: 2/5 Loss: 3.5824 Acc: 0.0623        \n",
            "Phase: validation   Epoch: 2/5 Loss: 3.4941 Acc: 0.0664        \n",
            "Phase: train Epoch: 3/5 Loss: 3.4782 Acc: 0.0734        \n",
            "Phase: validation   Epoch: 3/5 Loss: 3.4243 Acc: 0.0826        \n",
            "Phase: train Epoch: 4/5 Loss: 3.4022 Acc: 0.0965        \n",
            "Phase: validation   Epoch: 4/5 Loss: 3.3335 Acc: 0.0963        \n",
            "Phase: train Epoch: 5/5 Loss: 3.3282 Acc: 0.1429        \n",
            "Phase: validation   Epoch: 5/5 Loss: 3.2782 Acc: 0.1610        \n",
            "Training completed in 13m 40s\n",
            "Best test loss: 3.2782 | Best test accuracy: 0.1610\n"
          ]
        }
      ],
      "source": [
        "model_hybrid = train_model(\n",
        "    model_hybrid, criterion, optimizer_hybrid, exp_lr_scheduler, num_epochs=num_epochs\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "AG82Ot6Y8PAZ"
      },
      "source": [
        "Visualizing the model predictions\n",
        "=================================\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cwycKwbd8PAZ"
      },
      "source": [
        "We first define a visualization function for a batch of test data.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 82,
      "metadata": {
        "id": "_8R2rHzF8PAZ"
      },
      "outputs": [],
      "source": [
        "def visualize_model(model, num_images=6, fig_name=\"Predictions\"):\n",
        "    images_so_far = 0\n",
        "    _fig = plt.figure(fig_name)\n",
        "    model.eval()\n",
        "    with torch.no_grad():\n",
        "        for _i, (inputs, labels) in enumerate(dataloaders[\"validation\"]):\n",
        "            inputs = inputs.to(device)\n",
        "            labels = labels.to(device)\n",
        "            outputs = model(inputs)\n",
        "            _, preds = torch.max(outputs, 1)\n",
        "            for j in range(inputs.size()[0]):\n",
        "                images_so_far += 1\n",
        "                ax = plt.subplot(num_images // 2, 2, images_so_far)\n",
        "                ax.axis(\"off\")\n",
        "                ax.set_title(\"[{}]\".format(class_names[preds[j]]))\n",
        "                imshow(inputs.cpu().data[j])\n",
        "                if images_so_far == num_images:\n",
        "                    return"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LQvJfmme8PAa"
      },
      "source": [
        "Finally, we can run the previous function to see a batch of images with\n",
        "the corresponding predictions.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 83,
      "metadata": {
        "id": "mKBJn2x68PAa",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 428
        },
        "outputId": "fb3c6a3c-e25a-40fe-d87f-4550341d5b9d"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 16 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "visualize_model(model_hybrid, num_images=16)\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "seconds = time.time()\n",
        "print(\"Time in seconds since end of run:\", seconds)\n",
        "local_time = time.ctime(seconds)\n",
        "print(local_time)"
      ],
      "metadata": {
        "id": "D3AaQc2xMk-G",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "outputId": "b3221470-fa7a-47e0-aacf-fcb8d5e61017"
      },
      "execution_count": 84,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Time in seconds since end of run: 1695670764.346076\n",
            "Mon Sep 25 19:39:24 2023\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# from google.colab import runtime\n",
        "# runtime.unassign()"
      ],
      "metadata": {
        "id": "fALJ8tZXA0to"
      },
      "execution_count": 85,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0yhgWSns8PAa"
      },
      "source": [
        "References\n",
        "==========\n",
        "\n",
        "\\[1\\] Andrea Mari, Thomas R. Bromley, Josh Izaac, Maria Schuld, and\n",
        "Nathan Killoran. *Transfer learning in hybrid classical-quantum neural\n",
        "networks*. arXiv:1912.08278 (2019).\n",
        "\n",
        "\\[2\\] Rajat Raina, Alexis Battle, Honglak Lee, Benjamin Packer, and\n",
        "Andrew Y Ng. *Self-taught learning: transfer learning from unlabeled\n",
        "data*. Proceedings of the 24th International Conference on Machine\n",
        "Learning\\*, 759--766 (2007).\n",
        "\n",
        "\\[3\\] Kaiming He, Xiangyu Zhang, Shaoqing ren and Jian Sun. *Deep\n",
        "residual learning for image recognition*. Proceedings of the IEEE\n",
        "Conference on Computer Vision and Pattern Recognition, 770-778 (2016).\n",
        "\n",
        "\\[4\\] Ville Bergholm, Josh Izaac, Maria Schuld, Christian Gogolin,\n",
        "Carsten Blank, Keri McKiernan, and Nathan Killoran. *PennyLane:\n",
        "Automatic differentiation of hybrid quantum-classical computations*.\n",
        "arXiv:1811.04968 (2018).\n",
        "\n",
        "About the author\n",
        "================\n"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "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": "3.9.17"
    },
    "colab": {
      "provenance": [],
      "machine_shape": "hm",
      "gpuType": "V100"
    },
    "accelerator": "GPU"
  },
  "nbformat": 4,
  "nbformat_minor": 0
}