Single_Pixel_Camera.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "authorship_tag": "ABX9TyP0N0wapvwG0hlxKBmoiX5v",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/leonsuarez24/Notebooks/blob/main/Single_Pixel_Camera.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_tbTIVnjlIr1",
        "outputId": "fd788af2-2de8-4e80-81fd-b25eb12deda7"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting torchinfo\n",
            "  Downloading torchinfo-1.8.0-py3-none-any.whl (23 kB)\n",
            "Installing collected packages: torchinfo\n",
            "Successfully installed torchinfo-1.8.0\n",
            "Collecting torchmetrics\n",
            "  Downloading torchmetrics-1.0.0-py3-none-any.whl (728 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m728.8/728.8 kB\u001b[0m \u001b[31m35.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: numpy>1.20.0 in /usr/local/lib/python3.10/dist-packages (from torchmetrics) (1.22.4)\n",
            "Requirement already satisfied: torch>=1.8.1 in /usr/local/lib/python3.10/dist-packages (from torchmetrics) (2.0.1+cu118)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from torchmetrics) (23.1)\n",
            "Collecting lightning-utilities>=0.7.0 (from torchmetrics)\n",
            "  Downloading lightning_utilities-0.9.0-py3-none-any.whl (23 kB)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from lightning-utilities>=0.7.0->torchmetrics) (4.6.3)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.1->torchmetrics) (3.12.2)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.1->torchmetrics) (1.11.1)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.1->torchmetrics) (3.1)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.1->torchmetrics) (3.1.2)\n",
            "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.1->torchmetrics) (2.0.0)\n",
            "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.8.1->torchmetrics) (3.25.2)\n",
            "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.8.1->torchmetrics) (16.0.6)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.8.1->torchmetrics) (2.1.3)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.8.1->torchmetrics) (1.3.0)\n",
            "Installing collected packages: lightning-utilities, torchmetrics\n",
            "Successfully installed lightning-utilities-0.9.0 torchmetrics-1.0.0\n"
          ]
        }
      ],
      "source": [
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "import torchvision\n",
        "import torchvision.transforms as transforms\n",
        "!pip install torchinfo\n",
        "from torchinfo import summary\n",
        "\n",
        "import torch\n",
        "import torch.nn as nn\n",
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "import torch.nn.functional as F\n",
        "!pip install torchmetrics\n",
        "\n",
        "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Prepare the data\n",
        "transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])\n",
        "trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)\n",
        "trainloader = torch.utils.data.DataLoader(trainset, batch_size=32, shuffle=True, num_workers=2)\n",
        "testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)\n",
        "testloader = torch.utils.data.DataLoader(testset, batch_size=32, shuffle=False, num_workers=2)\n",
        "\n",
        "print(trainset.data.size())\n",
        "print(trainset.targets.size())\n",
        "print(trainset.targets[12].item())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Rt_H39JClfYf",
        "outputId": "713a5718-84cc-4c18-cab5-d769689925a2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz\n",
            "Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz to ./data/MNIST/raw/train-images-idx3-ubyte.gz\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 9912422/9912422 [00:00<00:00, 382231580.52it/s]"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Extracting ./data/MNIST/raw/train-images-idx3-ubyte.gz to ./data/MNIST/raw\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz\n",
            "Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz to ./data/MNIST/raw/train-labels-idx1-ubyte.gz\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 28881/28881 [00:00<00:00, 120653081.50it/s]\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Extracting ./data/MNIST/raw/train-labels-idx1-ubyte.gz to ./data/MNIST/raw\n",
            "\n",
            "Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz\n",
            "Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw/t10k-images-idx3-ubyte.gz\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 1648877/1648877 [00:00<00:00, 107719131.45it/s]"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Extracting ./data/MNIST/raw/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw\n",
            "\n",
            "Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 4542/4542 [00:00<00:00, 20053188.18it/s]\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Extracting ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw\n",
            "\n",
            "torch.Size([60000, 28, 28])\n",
            "torch.Size([60000])\n",
            "3\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "fig, ax = plt.subplots(5, 5)\n",
        "fig.tight_layout()\n",
        "\n",
        "k = 0\n",
        "for i in range(5):\n",
        "  for j in range(5):\n",
        "    ax[i, j].imshow(trainset.data[k])\n",
        "    ax[i, j].set_title(f\"{trainset.targets[k]}\")\n",
        "    ax[i, j].axis('off')\n",
        "    k +=1\n",
        "\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 480
        },
        "id": "jsoR7UcTmIYW",
        "outputId": "729a55cf-3cf8-4ffa-8d0d-7e34d41af3fb"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 25 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "ca = (torch.normal(0, 1, (10, 28, 28))/ np.sqrt(28*28))\n",
        "plt.imshow(ca[0,:,:])\n",
        "plt.colorbar()\n",
        "plt.show()\n",
        "print(torch.std(ca[0]), torch.mean(ca[0]))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 450
        },
        "id": "4r-HJhHaKhNg",
        "outputId": "d8a46b24-9489-4546-d992-d9903afcb253"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "tensor(0.0349) tensor(7.1780e-05)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "class OpticalLayer(nn.Module):\n",
        "    def __init__(self, K, output_dim, input_dim):\n",
        "        super(OpticalLayer, self).__init__()\n",
        "        self.output_dim = output_dim\n",
        "        self.input_dim = input_dim\n",
        "        self.K = K\n",
        "        ca = torch.normal(0, 1, (self.K, self.output_dim, self.input_dim))\n",
        "        self.weights = nn.Parameter(ca / np.sqrt(self.output_dim * self.input_dim))\n",
        "        #torch.nn.init.normal_(self.weights, mean=0.0, std=0.04)\n",
        "\n",
        "    def forward(self, x):\n",
        "        # Downscale to 1 px\n",
        "        ca_w = torch.unsqueeze(self.weights, 0)\n",
        "        x = torch.mul(x, ca_w)\n",
        "        x = torch.sum(x, dim=(-2, -1))\n",
        "        x = torch.unsqueeze(x, -1)\n",
        "        x = torch.unsqueeze(x, -1)\n",
        "        # Upscale to 28x28\n",
        "        x = torch.mul(x, ca_w)\n",
        "        x = torch.sum(x, dim=1)\n",
        "        x = torch.unsqueeze(x, 1)\n",
        "        x = x / torch.max(x)\n",
        "        return x"
      ],
      "metadata": {
        "id": "ClCflvHtx_Gu"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "ol = OpticalLayer(160,28,28).to(device)\n",
        "summary(ol, input_size=(32, 1, 28, 28))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_RjXCT8bHXJ6",
        "outputId": "9272f43a-8a07-4d24-8579-7c7459b77658"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "==========================================================================================\n",
              "Layer (type:depth-idx)                   Output Shape              Param #\n",
              "==========================================================================================\n",
              "OpticalLayer                             [32, 1, 28, 28]           125,440\n",
              "==========================================================================================\n",
              "Total params: 125,440\n",
              "Trainable params: 125,440\n",
              "Non-trainable params: 0\n",
              "Total mult-adds (M): 4.01\n",
              "==========================================================================================\n",
              "Input size (MB): 0.10\n",
              "Forward/backward pass size (MB): 0.20\n",
              "Params size (MB): 0.50\n",
              "Estimated Total Size (MB): 0.80\n",
              "=========================================================================================="
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "class SinglePixelCamera(nn.Module):\n",
        "  def __init__(self, K, output_dim, input_dim):\n",
        "    super(SinglePixelCamera, self).__init__()\n",
        "    self.optical_layer = OpticalLayer(K, output_dim, input_dim)\n",
        "    self.conv1 = nn.Conv2d(1, 32, 3, padding=1)\n",
        "    self.conv2 = nn.Conv2d(32, 64, 3, padding=1)\n",
        "    self.conv3 = nn.Conv2d(64, 64, 3, padding=1)\n",
        "    self.pool = nn.MaxPool2d(2, 2)\n",
        "    self.fc1 = nn.Linear(64 * 3 * 3, 128)\n",
        "    self.fc2 = nn.Linear(128, 10)\n",
        "\n",
        "  def forward(self, x):\n",
        "    x = self.optical_layer(x)\n",
        "    x = nn.functional.relu(self.conv1(x)) #28x28\n",
        "    x = self.pool(x) #14x14\n",
        "    x = nn.functional.relu(self.conv2(x)) #14x14\n",
        "    x = self.pool(x) #7x7\n",
        "    x = nn.functional.relu(self.conv3(x)) #7x7\n",
        "    x = self.pool(x) #3x3\n",
        "    x = x.view(-1, 64 * 3 * 3)\n",
        "    x = nn.functional.relu(self.fc1(x))\n",
        "    x = self.fc2(x)\n",
        "    return x"
      ],
      "metadata": {
        "id": "C6wOg0APnB-5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "spc = SinglePixelCamera(160,28,28).to(device)\n",
        "summary(spc, (32,1,28,28))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "r1njaTd052Yn",
        "outputId": "f1aa5967-1404-4011-f773-1b7cd7674de2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "==========================================================================================\n",
              "Layer (type:depth-idx)                   Output Shape              Param #\n",
              "==========================================================================================\n",
              "SinglePixelCamera                        [32, 10]                  --\n",
              "├─OpticalLayer: 1-1                      [32, 1, 28, 28]           125,440\n",
              "├─Conv2d: 1-2                            [32, 32, 28, 28]          320\n",
              "├─MaxPool2d: 1-3                         [32, 32, 14, 14]          --\n",
              "├─Conv2d: 1-4                            [32, 64, 14, 14]          18,496\n",
              "├─MaxPool2d: 1-5                         [32, 64, 7, 7]            --\n",
              "├─Conv2d: 1-6                            [32, 64, 7, 7]            36,928\n",
              "├─MaxPool2d: 1-7                         [32, 64, 3, 3]            --\n",
              "├─Linear: 1-8                            [32, 128]                 73,856\n",
              "├─Linear: 1-9                            [32, 10]                  1,290\n",
              "==========================================================================================\n",
              "Total params: 256,330\n",
              "Trainable params: 256,330\n",
              "Non-trainable params: 0\n",
              "Total mult-adds (M): 188.36\n",
              "==========================================================================================\n",
              "Input size (MB): 0.10\n",
              "Forward/backward pass size (MB): 10.67\n",
              "Params size (MB): 1.03\n",
              "Estimated Total Size (MB): 11.80\n",
              "=========================================================================================="
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print((torch.sum(torch.mul(torch.pow(1 + spc.optical_layer.weights, 2), torch.pow(1 - spc.optical_layer.weights, 2)))))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4Lq92Bmok8jc",
        "outputId": "32ba8e5f-62fe-47dd-8aa9-a331309bc8aa"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "tensor(125119.5312, device='cuda:0', grad_fn=<SumBackward0>)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def plot_images(images):\n",
        "    fig, axes = plt.subplots(5, 5, figsize=(10, 10))\n",
        "    axes = axes.ravel()\n",
        "    for i in range(len(images)):\n",
        "        axes[i].imshow(images[i].squeeze(), cmap='gray')\n",
        "        axes[i].set_title(f'CA: {i + 1}')\n",
        "        axes[i].axis('off')\n",
        "    plt.tight_layout()\n",
        "    plt.show()\n",
        "\n",
        "def plot_images_labels(images, labels):\n",
        "    fig, axes = plt.subplots(5, 5, figsize=(10, 10))\n",
        "    axes = axes.ravel()\n",
        "    for i in range(len(images)):\n",
        "        axes[i].imshow(images[i].squeeze(), cmap='gray')\n",
        "        axes[i].set_title(f'Label: {labels[i]}')\n",
        "        axes[i].axis('off')\n",
        "    plt.tight_layout()\n",
        "    plt.show()"
      ],
      "metadata": {
        "id": "2hd_F9j2JTM4"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Initialize the network and optimizer\n",
        "criterion = nn.CrossEntropyLoss()\n",
        "optimizer = optim.Adam(spc.parameters(), lr=0.001)\n",
        "regularizer_parameter = 1e-3\n",
        "# Training loop\n",
        "for epoch in range(20):\n",
        "  running_loss = 0.0\n",
        "  for i, data in enumerate(trainloader, 0):\n",
        "    inputs, labels = data\n",
        "    inputs = inputs.to(device)\n",
        "    labels = labels.to(device)\n",
        "    optimizer.zero_grad()\n",
        "\n",
        "    pred = spc(inputs)\n",
        "    loss = criterion(pred, labels) + regularizer_parameter * (torch.sum(torch.mul(torch.pow(1 + spc.optical_layer.weights, 2), torch.pow(1 - spc.optical_layer.weights, 2))))\n",
        "\n",
        "    loss.backward()\n",
        "    optimizer.step()\n",
        "\n",
        "    running_loss += loss.item()\n",
        "    if (i + 1) % 375 == 0:  # Print the running loss every 375 mini-batches\n",
        "      print(f'Epoch: {epoch + 1}, Batch: {i + 1}, Loss: {running_loss / 375:.3f}')\n",
        "      running_loss = 0.0\n",
        "\n",
        "print('Training finished!')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5MGTnizpBVIz",
        "outputId": "7aaca50c-a0a6-475e-8185-09206cf829c9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch: 1, Batch: 375, Loss: 124.155\n",
            "Epoch: 1, Batch: 750, Loss: 115.007\n",
            "Epoch: 1, Batch: 1125, Loss: 94.177\n",
            "Epoch: 1, Batch: 1500, Loss: 61.737\n",
            "Epoch: 1, Batch: 1875, Loss: 33.206\n",
            "Epoch: 2, Batch: 375, Loss: 16.867\n",
            "Epoch: 2, Batch: 750, Loss: 9.058\n",
            "Epoch: 2, Batch: 1125, Loss: 5.277\n",
            "Epoch: 2, Batch: 1500, Loss: 3.256\n",
            "Epoch: 2, Batch: 1875, Loss: 2.095\n",
            "Epoch: 3, Batch: 375, Loss: 1.375\n",
            "Epoch: 3, Batch: 750, Loss: 0.954\n",
            "Epoch: 3, Batch: 1125, Loss: 0.689\n",
            "Epoch: 3, Batch: 1500, Loss: 0.533\n",
            "Epoch: 3, Batch: 1875, Loss: 0.405\n",
            "Epoch: 4, Batch: 375, Loss: 0.334\n",
            "Epoch: 4, Batch: 750, Loss: 0.276\n",
            "Epoch: 4, Batch: 1125, Loss: 0.247\n",
            "Epoch: 4, Batch: 1500, Loss: 0.230\n",
            "Epoch: 4, Batch: 1875, Loss: 0.204\n",
            "Epoch: 5, Batch: 375, Loss: 0.197\n",
            "Epoch: 5, Batch: 750, Loss: 0.180\n",
            "Epoch: 5, Batch: 1125, Loss: 0.174\n",
            "Epoch: 5, Batch: 1500, Loss: 0.174\n",
            "Epoch: 5, Batch: 1875, Loss: 0.170\n",
            "Epoch: 6, Batch: 375, Loss: 0.166\n",
            "Epoch: 6, Batch: 750, Loss: 0.163\n",
            "Epoch: 6, Batch: 1125, Loss: 0.157\n",
            "Epoch: 6, Batch: 1500, Loss: 0.152\n",
            "Epoch: 6, Batch: 1875, Loss: 0.160\n",
            "Epoch: 7, Batch: 375, Loss: 0.141\n",
            "Epoch: 7, Batch: 750, Loss: 0.136\n",
            "Epoch: 7, Batch: 1125, Loss: 0.148\n",
            "Epoch: 7, Batch: 1500, Loss: 0.131\n",
            "Epoch: 7, Batch: 1875, Loss: 0.148\n",
            "Epoch: 8, Batch: 375, Loss: 0.124\n",
            "Epoch: 8, Batch: 750, Loss: 0.132\n",
            "Epoch: 8, Batch: 1125, Loss: 0.132\n",
            "Epoch: 8, Batch: 1500, Loss: 0.131\n",
            "Epoch: 8, Batch: 1875, Loss: 0.134\n",
            "Epoch: 9, Batch: 375, Loss: 0.111\n",
            "Epoch: 9, Batch: 750, Loss: 0.114\n",
            "Epoch: 9, Batch: 1125, Loss: 0.120\n",
            "Epoch: 9, Batch: 1500, Loss: 0.118\n",
            "Epoch: 9, Batch: 1875, Loss: 0.129\n",
            "Epoch: 10, Batch: 375, Loss: 0.105\n",
            "Epoch: 10, Batch: 750, Loss: 0.111\n",
            "Epoch: 10, Batch: 1125, Loss: 0.116\n",
            "Epoch: 10, Batch: 1500, Loss: 0.112\n",
            "Epoch: 10, Batch: 1875, Loss: 0.110\n",
            "Epoch: 11, Batch: 375, Loss: 0.104\n",
            "Epoch: 11, Batch: 750, Loss: 0.097\n",
            "Epoch: 11, Batch: 1125, Loss: 0.101\n",
            "Epoch: 11, Batch: 1500, Loss: 0.103\n",
            "Epoch: 11, Batch: 1875, Loss: 0.112\n",
            "Epoch: 12, Batch: 375, Loss: 0.086\n",
            "Epoch: 12, Batch: 750, Loss: 0.096\n",
            "Epoch: 12, Batch: 1125, Loss: 0.094\n",
            "Epoch: 12, Batch: 1500, Loss: 0.096\n",
            "Epoch: 12, Batch: 1875, Loss: 0.103\n",
            "Epoch: 13, Batch: 375, Loss: 0.078\n",
            "Epoch: 13, Batch: 750, Loss: 0.090\n",
            "Epoch: 13, Batch: 1125, Loss: 0.090\n",
            "Epoch: 13, Batch: 1500, Loss: 0.083\n",
            "Epoch: 13, Batch: 1875, Loss: 0.098\n",
            "Epoch: 14, Batch: 375, Loss: 0.079\n",
            "Epoch: 14, Batch: 750, Loss: 0.084\n",
            "Epoch: 14, Batch: 1125, Loss: 0.082\n",
            "Epoch: 14, Batch: 1500, Loss: 0.087\n",
            "Epoch: 14, Batch: 1875, Loss: 0.088\n",
            "Epoch: 15, Batch: 375, Loss: 0.069\n",
            "Epoch: 15, Batch: 750, Loss: 0.087\n",
            "Epoch: 15, Batch: 1125, Loss: 0.082\n",
            "Epoch: 15, Batch: 1500, Loss: 0.083\n",
            "Epoch: 15, Batch: 1875, Loss: 0.080\n",
            "Epoch: 16, Batch: 375, Loss: 0.075\n",
            "Epoch: 16, Batch: 750, Loss: 0.078\n",
            "Epoch: 16, Batch: 1125, Loss: 0.076\n",
            "Epoch: 16, Batch: 1500, Loss: 0.073\n",
            "Epoch: 16, Batch: 1875, Loss: 0.079\n",
            "Epoch: 17, Batch: 375, Loss: 0.065\n",
            "Epoch: 17, Batch: 750, Loss: 0.070\n",
            "Epoch: 17, Batch: 1125, Loss: 0.080\n",
            "Epoch: 17, Batch: 1500, Loss: 0.074\n",
            "Epoch: 17, Batch: 1875, Loss: 0.075\n",
            "Epoch: 18, Batch: 375, Loss: 0.058\n",
            "Epoch: 18, Batch: 750, Loss: 0.068\n",
            "Epoch: 18, Batch: 1125, Loss: 0.072\n",
            "Epoch: 18, Batch: 1500, Loss: 0.074\n",
            "Epoch: 18, Batch: 1875, Loss: 0.075\n",
            "Epoch: 19, Batch: 375, Loss: 0.060\n",
            "Epoch: 19, Batch: 750, Loss: 0.067\n",
            "Epoch: 19, Batch: 1125, Loss: 0.062\n",
            "Epoch: 19, Batch: 1500, Loss: 0.074\n",
            "Epoch: 19, Batch: 1875, Loss: 0.067\n",
            "Epoch: 20, Batch: 375, Loss: 0.052\n",
            "Epoch: 20, Batch: 750, Loss: 0.066\n",
            "Epoch: 20, Batch: 1125, Loss: 0.063\n",
            "Epoch: 20, Batch: 1500, Loss: 0.070\n",
            "Epoch: 20, Batch: 1875, Loss: 0.078\n",
            "Training finished!\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Evaluation\n",
        "correct = 0\n",
        "total = 0\n",
        "with torch.no_grad():\n",
        "    for data in testloader:\n",
        "        images, labels = data\n",
        "        outputs= spc(images.to(device))\n",
        "        _, predicted = torch.max(outputs.data, 1)\n",
        "        total += labels.size(0)\n",
        "        correct += (predicted == labels.to(device)).sum().item()\n",
        "\n",
        "print(f'Accuracy on the test set: {100 * correct / total:.2f}%')\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "l2rZsFrzJQnF",
        "outputId": "bb470da3-c276-40ce-cd8a-431b59468b1a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy on the test set: 96.18%\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "spc.optical_layer.weights.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "i-JvyIvIkE6z",
        "outputId": "192c3d97-5b88-49a3-f586-6df868aae561"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "torch.Size([160, 28, 28])"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "subset_indices = torch.randint(0, len(testset), (25,))\n",
        "subset_images = [testset[i][0] for i in subset_indices]\n",
        "subset_labels = [testset[i][1] for i in subset_indices]\n",
        "subset_images = torch.stack(subset_images).to(device)\n",
        "spc.eval()\n",
        "spc = spc.cpu()\n",
        "subset_images = subset_images.cpu()\n",
        "\n",
        "with torch.no_grad():\n",
        "    outputs = spc(subset_images)\n",
        "    _, predicted = torch.max(outputs, 1)\n",
        "    print(spc.optical_layer.weights.shape)\n",
        "    plot_images(spc.optical_layer.weights[:25,:,:])\n",
        "    plot_images_labels(subset_images, predicted)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "MdZhJdgaLvJp",
        "outputId": "787821b2-6df9-4b0f-8516-639d6ece7a64"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "torch.Size([160, 28, 28])\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x1000 with 25 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x1000 with 25 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "aG3Xlpb3F2Yh"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}