Created using Colab

Author: lovnishverma

RNN_basics.ipynb

@@ -0,0 +1,222 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/lovnishverma/Python-Getting-Started/blob/main/RNN_basics.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "c9345e09",
+      "metadata": {
+        "id": "c9345e09"
+      },
+      "source": [
+        "# Beginner RNN Basics\n",
+        "M.TECH AI - Practical 4"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "b8df6bb4",
+      "metadata": {
+        "id": "b8df6bb4"
+      },
+      "outputs": [],
+      "source": [
+        "import torch\n",
+        "import torch.nn as nn\n",
+        "import torch.optim as optim"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "39b6f123",
+      "metadata": {
+        "id": "39b6f123"
+      },
+      "source": [
+        "## 1. Generate Data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "18c71a3f",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "18c71a3f",
+        "outputId": "0b808b4f-791d-495a-9f56-2a7d9029adf5"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "torch.Size([500, 5, 1]) torch.Size([500, 1])\n"
+          ]
+        }
+      ],
+      "source": [
+        "def generate_data(n=500, seq_len=5):\n",
+        "    X = torch.randn(n, seq_len, 1)\n",
+        "    y = (X.sum(dim=1) > 0).float()\n",
+        "    return X, y\n",
+        "\n",
+        "X, y = generate_data()\n",
+        "\n",
+        "print(X.shape, y.shape)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "334eae52",
+      "metadata": {
+        "id": "334eae52"
+      },
+      "source": [
+        "## 2. Simple RNN Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "4542f5ff",
+      "metadata": {
+        "id": "4542f5ff"
+      },
+      "outputs": [],
+      "source": [
+        "class SimpleRNN(nn.Module):\n",
+        "    def __init__(self):\n",
+        "        super().__init__()\n",
+        "        self.rnn = nn.RNN(input_size=1, hidden_size=8, batch_first=True)\n",
+        "        self.fc = nn.Linear(8, 1)\n",
+        "\n",
+        "    def forward(self, x):\n",
+        "        h0 = torch.zeros(1, x.size(0), 8)\n",
+        "        out, _ = self.rnn(x, h0)\n",
+        "        out = out[:, -1, :]\n",
+        "        out = self.fc(out)\n",
+        "        return torch.sigmoid(out)\n",
+        "\n",
+        "model = SimpleRNN()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "3a79a18b",
+      "metadata": {
+        "id": "3a79a18b"
+      },
+      "source": [
+        "## 3. Training"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "63128b5d",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "63128b5d",
+        "outputId": "cf8632e4-3886-4a19-9071-ed160045c983"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Epoch 10, Loss: 0.6385\n",
+            "Epoch 20, Loss: 0.5232\n",
+            "Epoch 30, Loss: 0.2741\n",
+            "Epoch 40, Loss: 0.2147\n",
+            "Epoch 50, Loss: 0.1879\n"
+          ]
+        }
+      ],
+      "source": [
+        "loss_fn = nn.BCELoss()\n",
+        "optimizer = optim.Adam(model.parameters(), lr=0.01)\n",
+        "\n",
+        "for epoch in range(50):\n",
+        "    preds = model(X)\n",
+        "    loss = loss_fn(preds, y)\n",
+        "\n",
+        "    optimizer.zero_grad()\n",
+        "    loss.backward()\n",
+        "    optimizer.step()\n",
+        "\n",
+        "    if (epoch+1) % 10 == 0:\n",
+        "        print(f\"Epoch {epoch+1}, Loss: {loss.item():.4f}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "30dc228e",
+      "metadata": {
+        "id": "30dc228e"
+      },
+      "source": [
+        "## 4. Testing"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "cf68e653",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "cf68e653",
+        "outputId": "ae0d5783-1e10-4d51-92ae-cc16340c9912"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Predictions: [0.0, 1.0, 0.0, 1.0, 1.0]\n",
+            "Actual: [0.0, 1.0, 0.0, 1.0, 1.0]\n"
+          ]
+        }
+      ],
+      "source": [
+        "test_X, test_y = generate_data(5)\n",
+        "\n",
+        "with torch.no_grad():\n",
+        "    preds = model(test_X)\n",
+        "    preds = (preds > 0.5).float()\n",
+        "\n",
+        "print(\"Predictions:\", preds.squeeze().tolist())\n",
+        "print(\"Actual:\", test_y.squeeze().tolist())"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "include_colab_link": true
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}