Created using Colaboratory

PytorchTutorials/Regression.ipynb

@@ -0,0 +1,140 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyNVDGf+dNdyK86DjeRVtAfY"
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "pP_BRWga5u1n"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import torch\n",
+        "import torch.nn as nn\n",
+        "import torch.optim as optim\n",
+        "from torch.utils.data import DataLoader, TensorDataset\n",
+        "\n",
+        "# Set random seed for reproducibility\n",
+        "np.random.seed(0)\n",
+        "torch.manual_seed(0)\n",
+        "\n",
+        "# Generate synthetic data\n",
+        "x = np.random.randn(1000,2)\n",
+        "y = 3*x.sum(axis=1) + 2*np.random.randn(x.shape[0])\n",
+        "\n",
+        "x = np.vstack(x)\n",
+        "y = np.hstack(y)\n",
+        "\n",
+        "# Convert to PyTorch tensors\n",
+        "x_tensor = torch.tensor(x, dtype=torch.float32)\n",
+        "y_tensor = torch.tensor(y, dtype=torch.float32)\n",
+        "\n",
+        "# Create a TensorDataset and DataLoader\n",
+        "dataset = TensorDataset(x_tensor, y_tensor)\n",
+        "dataloader = DataLoader(dataset, batch_size=10, shuffle=True)\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Neural network\n",
+        "class SimpleRegressor(nn.Module):\n",
+        "    def __init__(self):\n",
+        "        super(SimpleRegressor, self).__init__()\n",
+        "        self.fc = nn.Linear(2, 1)  # One input feature, one output feature\n",
+        "\n",
+        "    def forward(self, x):\n",
+        "        return self.fc(x)\n",
+        "\n",
+        "model = SimpleRegressor()\n",
+        "\n",
+        "# Loss and optimizer\n",
+        "criterion = nn.MSELoss()  # Mean Squared Error for regression\n",
+        "optimizer = optim.SGD(model.parameters(), lr=0.01)\n",
+        "\n",
+        "# Training loop\n",
+        "num_epochs = 100\n",
+        "for epoch in range(num_epochs):\n",
+        "    for inputs, targets in dataloader:\n",
+        "        # Forward pass\n",
+        "        outputs = model(inputs)\n",
+        "        loss = criterion(outputs, targets)\n",
+        "\n",
+        "        # Backward and optimize\n",
+        "        optimizer.zero_grad()\n",
+        "        loss.backward()\n",
+        "        optimizer.step()\n",
+        "\n",
+        "    if epoch % 10 == 0:\n",
+        "        print(f'Epoch [{epoch}/{num_epochs}], Loss: {loss.item():.4f}')\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ETGXjGCo538n",
+        "outputId": "75c6af6d-fe44-4c3e-a449-c125a9555b7b"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Epoch [0/100], Loss: 35.8108\n",
+            "Epoch [10/100], Loss: 21.7872\n",
+            "Epoch [20/100], Loss: 13.4255\n",
+            "Epoch [30/100], Loss: 23.3474\n",
+            "Epoch [40/100], Loss: 14.4495\n",
+            "Epoch [50/100], Loss: 9.5928\n",
+            "Epoch [60/100], Loss: 10.4794\n",
+            "Epoch [70/100], Loss: 8.2940\n",
+            "Epoch [80/100], Loss: 25.8117\n",
+            "Epoch [90/100], Loss: 13.2736\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "# Test the model\n",
+        "model.eval()\n",
+        "with torch.no_grad():\n",
+        "    predicted = model(x_tensor).detach().numpy()\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "7SGMBKNP9R-X"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "dv-nwyAsGuMj"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}