940 lines (940 with data), 247.6 kB

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 54,
      "metadata": {
        "id": "WNXEyZ23rdz-"
      },
      "outputs": [],
      "source": [
        "# This cell is added by sphinx-gallery\n",
        "# It can be customized to whatever you like\n",
        "#from google.colab import drive\n",
        "#drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "WYVI3RMhAdap"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 55,
      "metadata": {
        "id": "sANL984ird0B"
      },
      "outputs": [],
      "source": [
        "#!pip install pennylane\n",
        "# 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 time\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": "o7eGTk_Prd0B"
      },
      "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": 56,
      "metadata": {
        "id": "Wncy61Mdrd0B"
      },
      "outputs": [],
      "source": [
        "n_qubits = 8                # Number of qubits\n",
        "step = 0.0006               # Learning rate\n",
        "batch_size = 6              # Number of samples for each training step\n",
        "num_epochs = 30              # Number of training epochs\n",
        "q_depth = 6                 # 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": "PVqjLo8Rrd0B"
      },
      "source": [
        "We initialize a PennyLane device with a `default.qubit` backend.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 57,
      "metadata": {
        "id": "qLOa5trRrd0B"
      },
      "outputs": [],
      "source": [
        "dev = qml.device(\"default.qubit\", wires=n_qubits)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "dxlK7Jjtrd0C"
      },
      "source": [
        "We configure PyTorch to use CUDA only if available. Otherwise the CPU is\n",
        "used.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 58,
      "metadata": {
        "id": "Br_YGwRDrd0C"
      },
      "outputs": [],
      "source": [
        "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WFHuYd5xrd0C"
      },
      "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",
      "source": [
        "#os.system(\"rm -rf /content/data/.ipynb_checkpoints\")\n",
        "#os.system(\"rm -rf /content/data/braintumor_data/.ipynb_checkpoints\")\n",
        "#os.system(\"rm -rf /content/data/braintumor_data/train/.ipynb_checkpoints\")\n",
        "#os.system(\"rm -rf /content/data/braintumor_data/val/.ipynb_checkpoints\")"
      ],
      "metadata": {
        "id": "DM8SDO3Wthcc"
      },
      "execution_count": 59,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": 60,
      "metadata": {
        "id": "jQrNNVnUrd0C"
      },
      "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/4_cl_Mxbraintumor_data\"\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": "piWk71nkrd0C"
      },
      "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": 61,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 166
        },
        "id": "u55iZYEOrd0D",
        "outputId": "03e1c8c0-5719-4e96-c228-a89486076446"
      },
      "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": "ds09ighxrd0D"
      },
      "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": 62,
      "metadata": {
        "id": "OIbOa-KBrd0D"
      },
      "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",
        "\n",
        "\n",
        "def entangling_layer(nqubits):\n",
        "    \"\"\"Layer of CNOTs followed by another shifted layer of CNOT.\n",
        "    \"\"\"\n",
        "    # In other words it should apply something like :\n",
        "    # CNOT  CNOT  CNOT  CNOT...  CNOT\n",
        "    #   CNOT  CNOT  CNOT...  CNOT\n",
        "    for i in range(0, nqubits - 1, 2):  # Loop over even indices: i=0,2,...N-2\n",
        "        qml.CNOT(wires=[i, i + 1])\n",
        "    for i in range(1, nqubits - 1, 2):  # Loop over odd indices:  i=1,3,...N-3\n",
        "        qml.CNOT(wires=[i, i + 1])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Ue__y4sQrd0D"
      },
      "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": 63,
      "metadata": {
        "id": "C-O_cK6jrd0D"
      },
      "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",
        "        #entangling_layer(n_qubits)\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": "7FNHREgVrd0D"
      },
      "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": 64,
      "metadata": {
        "id": "C96kWCjWrd0D"
      },
      "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(512, n_qubits)\n",
        "        self.q_params = nn.Parameter(q_delta * torch.randn(q_depth * n_qubits))\n",
        "        self.post_net = nn.Linear(n_qubits, 4)\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)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7hQlpDQdrd0D"
      },
      "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": 65,
      "metadata": {
        "id": "MAh4FqBYrd0D"
      },
      "outputs": [],
      "source": [
        "model_hybrid = torchvision.models.resnet18(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": "ovX-Tkb0rd0E"
      },
      "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": 66,
      "metadata": {
        "id": "gkmFIK4Brd0E"
      },
      "outputs": [],
      "source": [
        "criterion = nn.CrossEntropyLoss()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qhFORuvard0E"
      },
      "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": 67,
      "metadata": {
        "id": "_K9M-VPMrd0E"
      },
      "outputs": [],
      "source": [
        "optimizer_hybrid = optim.Adam(model_hybrid.fc.parameters(), lr=step)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IGG8pksyrd0E"
      },
      "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": 68,
      "metadata": {
        "id": "nco3IrE6rd0E"
      },
      "outputs": [],
      "source": [
        "exp_lr_scheduler = lr_scheduler.StepLR(\n",
        "    optimizer_hybrid, step_size=10, gamma=gamma_lr_scheduler\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yJvpPNCRrd0E"
      },
      "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": 69,
      "metadata": {
        "id": "8uO5BrOPrd0E"
      },
      "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": "CmAl9fIQrd0E"
      },
      "source": [
        "We are ready to perform the actual training process.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 70,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "rAQBdDA_rd0E",
        "outputId": "62f2e0a1-3993-41a9-b3ef-645af5d45015"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training started:\n",
            "Phase: train Epoch: 1/30 Loss: 1.1556 Acc: 0.5980        \n",
            "Phase: validation   Epoch: 1/30 Loss: 1.0822 Acc: 0.6396        \n",
            "Phase: train Epoch: 2/30 Loss: 0.9781 Acc: 0.6777        \n",
            "Phase: validation   Epoch: 2/30 Loss: 1.0021 Acc: 0.6267        \n",
            "Phase: train Epoch: 3/30 Loss: 0.8916 Acc: 0.7200        \n",
            "Phase: validation   Epoch: 3/30 Loss: 0.9388 Acc: 0.6682        \n",
            "Phase: train Epoch: 4/30 Loss: 0.8058 Acc: 0.7550        \n",
            "Phase: validation   Epoch: 4/30 Loss: 0.8502 Acc: 0.7493        \n",
            "Phase: train Epoch: 5/30 Loss: 0.7467 Acc: 0.7827        \n",
            "Phase: validation   Epoch: 5/30 Loss: 0.7929 Acc: 0.7641        \n",
            "Phase: train Epoch: 6/30 Loss: 0.6968 Acc: 0.8065        \n",
            "Phase: validation   Epoch: 6/30 Loss: 0.7902 Acc: 0.7253        \n",
            "Phase: train Epoch: 7/30 Loss: 0.6437 Acc: 0.8153        \n",
            "Phase: validation   Epoch: 7/30 Loss: 0.7479 Acc: 0.7760        \n",
            "Phase: train Epoch: 8/30 Loss: 0.6389 Acc: 0.8080        \n",
            "Phase: validation   Epoch: 8/30 Loss: 0.6328 Acc: 0.8092        \n",
            "Phase: train Epoch: 9/30 Loss: 0.5774 Acc: 0.8367        \n",
            "Phase: validation   Epoch: 9/30 Loss: 0.6095 Acc: 0.8276        \n",
            "Phase: train Epoch: 10/30 Loss: 0.5776 Acc: 0.8269        \n",
            "Phase: validation   Epoch: 10/30 Loss: 0.6437 Acc: 0.7945        \n",
            "Phase: train Epoch: 11/30 Loss: 0.4912 Acc: 0.8595        \n",
            "Phase: validation   Epoch: 11/30 Loss: 0.5739 Acc: 0.8212        \n",
            "Phase: train Epoch: 12/30 Loss: 0.5035 Acc: 0.8610        \n",
            "Phase: validation   Epoch: 12/30 Loss: 0.5897 Acc: 0.8212        \n",
            "Phase: train Epoch: 13/30 Loss: 0.4953 Acc: 0.8576        \n",
            "Phase: validation   Epoch: 13/30 Loss: 0.5859 Acc: 0.8184        \n",
            "Phase: train Epoch: 14/30 Loss: 0.4896 Acc: 0.8673        \n",
            "Phase: validation   Epoch: 14/30 Loss: 0.5672 Acc: 0.8240        \n",
            "Phase: train Epoch: 15/30 Loss: 0.4769 Acc: 0.8629        \n",
            "Phase: validation   Epoch: 15/30 Loss: 0.5773 Acc: 0.8230        \n",
            "Phase: train Epoch: 16/30 Loss: 0.4808 Acc: 0.8634        \n",
            "Phase: validation   Epoch: 16/30 Loss: 0.5601 Acc: 0.8350        \n",
            "Phase: train Epoch: 17/30 Loss: 0.4698 Acc: 0.8717        \n",
            "Phase: validation   Epoch: 17/30 Loss: 0.5597 Acc: 0.8295        \n",
            "Phase: train Epoch: 18/30 Loss: 0.4780 Acc: 0.8571        \n",
            "Phase: validation   Epoch: 18/30 Loss: 0.5352 Acc: 0.8415        \n",
            "Phase: train Epoch: 19/30 Loss: 0.4636 Acc: 0.8673        \n",
            "Phase: validation   Epoch: 19/30 Loss: 0.5650 Acc: 0.8258        \n",
            "Phase: train Epoch: 20/30 Loss: 0.4568 Acc: 0.8707        \n",
            "Phase: validation   Epoch: 20/30 Loss: 0.5538 Acc: 0.8258        \n",
            "Phase: train Epoch: 21/30 Loss: 0.4569 Acc: 0.8731        \n",
            "Phase: validation   Epoch: 21/30 Loss: 0.5626 Acc: 0.8184        \n",
            "Phase: train Epoch: 22/30 Loss: 0.4591 Acc: 0.8712        \n",
            "Phase: validation   Epoch: 22/30 Loss: 0.5683 Acc: 0.8258        \n",
            "Phase: train Epoch: 23/30 Loss: 0.4427 Acc: 0.8824        \n",
            "Phase: validation   Epoch: 23/30 Loss: 0.5478 Acc: 0.8323        \n",
            "Phase: train Epoch: 24/30 Loss: 0.4537 Acc: 0.8731        \n",
            "Phase: validation   Epoch: 24/30 Loss: 0.5342 Acc: 0.8350        \n",
            "Phase: train Epoch: 25/30 Loss: 0.4603 Acc: 0.8697        \n",
            "Phase: validation   Epoch: 25/30 Loss: 0.5639 Acc: 0.8276        \n",
            "Phase: train Epoch: 26/30 Loss: 0.4559 Acc: 0.8794        \n",
            "Phase: validation   Epoch: 26/30 Loss: 0.5688 Acc: 0.8295        \n",
            "Phase: train Epoch: 27/30 Loss: 0.4502 Acc: 0.8794        \n",
            "Phase: validation   Epoch: 27/30 Loss: 0.5383 Acc: 0.8359        \n",
            "Phase: train Epoch: 28/30 Loss: 0.4396 Acc: 0.8712        \n",
            "Phase: validation   Epoch: 28/30 Loss: 0.5574 Acc: 0.8276        \n",
            "Phase: train Epoch: 29/30 Loss: 0.4587 Acc: 0.8644        \n",
            "Phase: validation   Epoch: 29/30 Loss: 0.5726 Acc: 0.8221        \n",
            "Phase: train Epoch: 30/30 Loss: 0.4583 Acc: 0.8678        \n",
            "Phase: validation   Epoch: 30/30 Loss: 0.5596 Acc: 0.8230        \n",
            "Training completed in 49m 56s\n",
            "Best test loss: 0.5342 | Best test accuracy: 0.8415\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": "s4cEc4mird0E"
      },
      "source": [
        "Visualizing the model predictions\n",
        "=================================\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ARvjv_lbrd0E"
      },
      "source": [
        "We first define a visualization function for a batch of test data.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 71,
      "metadata": {
        "id": "CtUY4xU_rd0E"
      },
      "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": "F6I5Rk92rd0E"
      },
      "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": 72,
      "metadata": {
        "id": "-RoYcZQXrd0E",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 428
        },
        "outputId": "2667c6bb-8c73-4eb0-b5d0-0664a3a45ec2"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 6 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "visualize_model(model_hybrid, num_images=6)\n",
        "plt.show()\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IBXZTnzjrd0E"
      },
      "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",
      "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": "3.9.16"
    },
    "colab": {
      "provenance": [],
      "gpuType": "V100"
    },
    "accelerator": "GPU",
    "gpuClass": "standard"
  },
  "nbformat": 4,
  "nbformat_minor": 0
}