963 lines (963 with data), 236.3 kB

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 338,
      "metadata": {
        "id": "UJOq3mdA8PAH",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "outputId": "08e67e5f-4939-4776-9398-cc6e5831020a"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Time in seconds since beginning of run: 1695691400.3309948\n",
            "Tue Sep 26 01:23:20 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": 339,
      "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": 340,
      "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": 341,
      "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": 342,
      "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": 343,
      "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/Shuffle Split 10 of 17 Classes Big Brain Tumor MRI Images\"\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": 344,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 207
        },
        "id": "QzIKQxS78PAU",
        "outputId": "10ef6a40-16fc-4162-f154-eb52ac2dedf7"
      },
      "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": 345,
      "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": 346,
      "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": 347,
      "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, 10)\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": 348,
      "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": 349,
      "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": 350,
      "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": 351,
      "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": 352,
      "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": "30918ced-2136-4141-a8ff-5797f6b4d848"
      },
      "execution_count": 353,
      "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": 354,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "5VgfdD3-8PAZ",
        "outputId": "be64c1a9-0dad-49f7-b4c9-f7d3e3c26e12"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training started:\n",
            "Phase: train Epoch: 1/5 Loss: 2.2737 Acc: 0.1328        \n",
            "Phase: validation   Epoch: 1/5 Loss: 2.1016 Acc: 0.2299        \n",
            "Phase: train Epoch: 2/5 Loss: 2.0742 Acc: 0.2639        \n",
            "Phase: validation   Epoch: 2/5 Loss: 1.9511 Acc: 0.3254        \n",
            "Phase: train Epoch: 3/5 Loss: 1.9891 Acc: 0.2912        \n",
            "Phase: validation   Epoch: 3/5 Loss: 1.8546 Acc: 0.3461        \n",
            "Phase: train Epoch: 4/5 Loss: 1.9033 Acc: 0.3180        \n",
            "Phase: validation   Epoch: 4/5 Loss: 1.8061 Acc: 0.3361        \n",
            "Phase: train Epoch: 5/5 Loss: 1.8542 Acc: 0.3194        \n",
            "Phase: validation   Epoch: 5/5 Loss: 1.7367 Acc: 0.3316        \n",
            "Training completed in 10m 46s\n",
            "Best test loss: 1.7367 | Best test accuracy: 0.3461\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": 355,
      "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": 356,
      "metadata": {
        "id": "mKBJn2x68PAa",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 428
        },
        "outputId": "a808d3f6-1dc9-4486-d52e-9fab0f01f91c"
      },
      "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": "f281e30a-8e2a-4330-9e93-148076f53585"
      },
      "execution_count": 357,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Time in seconds since end of run: 1695692048.2999928\n",
            "Tue Sep 26 01:34:08 2023\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# from google.colab import runtime\n",
        "# runtime.unassign()"
      ],
      "metadata": {
        "id": "fALJ8tZXA0to"
      },
      "execution_count": 358,
      "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
}