Forward vs Call.ipynb

forward-vs-call.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Forward vs Call.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/nathanhubens/5a9fc090dcfbf03759068ae0fc3df1c9/forward-vs-call.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "metadata": {
        "id": "P8bU6AqJ9Z5U",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.nn.functional as F"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "m3HJTzwy9hj-",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "class Net(nn.Module):\n",
        "\n",
        "    def __init__(self):\n",
        "        super(Net, self).__init__()\n",
        "        self.fc1 = nn.Linear(1, 10)\n",
        "\n",
        "    def forward(self, x):\n",
        "        x = self.fc1(x)\n",
        "        return x"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "Zk_jlJGJ-OuE",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "net = Net()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "Tk2L0q2u9ztm",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 357
        },
        "outputId": "ac095735-01db-4dfa-d773-f30c7d77e653"
      },
      "cell_type": "code",
      "source": [
        "input = torch.randn(10, 1)\n",
        "out = net(input); out"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[-0.3731,  1.3823,  0.0515, -0.5198,  0.5836, -1.0378,  0.5496,  0.4065,\n",
              "          1.0506,  0.3349],\n",
              "        [ 0.5514,  0.1857, -0.4676, -0.2912,  0.3555,  0.0757,  0.8639, -0.6369,\n",
              "          0.0750,  0.7080],\n",
              "        [ 0.1788,  0.6679, -0.2584, -0.3833,  0.4474, -0.3730,  0.7373, -0.2165,\n",
              "          0.4681,  0.5576],\n",
              "        [ 0.8737, -0.2315, -0.6486, -0.2115,  0.2759,  0.4639,  0.9735, -1.0007,\n",
              "         -0.2652,  0.8381],\n",
              "        [ 1.0532, -0.4638, -0.7494, -0.1671,  0.2317,  0.6801,  1.0345, -1.2033,\n",
              "         -0.4546,  0.9106],\n",
              "        [ 0.7490, -0.0701, -0.5785, -0.2424,  0.3067,  0.3137,  0.9311, -0.8600,\n",
              "         -0.1336,  0.7878],\n",
              "        [ 1.2528, -0.7222, -0.8615, -0.1178,  0.1824,  0.9205,  1.1024, -1.4286,\n",
              "         -0.6653,  0.9912],\n",
              "        [ 0.9843, -0.3747, -0.7107, -0.1842,  0.2486,  0.5972,  1.0111, -1.1256,\n",
              "         -0.3819,  0.8828],\n",
              "        [ 0.8114, -0.1510, -0.6136, -0.2269,  0.2913,  0.3889,  0.9524, -0.9305,\n",
              "         -0.1995,  0.8130],\n",
              "        [ 0.9214, -0.2933, -0.6754, -0.1997,  0.2642,  0.5214,  0.9897, -1.0546,\n",
              "         -0.3155,  0.8574]], grad_fn=<AddmmBackward>)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "metadata": {
        "id": "yosLq6xW9xKQ",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "class Net(nn.Module):\n",
        "\n",
        "    def __init__(self):\n",
        "        super(Net, self).__init__()\n",
        "        self.fc1 = nn.Linear(1, 10)\n",
        "\n",
        "    def __call__(self, x):\n",
        "        x = self.fc1(x)\n",
        "        return x"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "XMNi5RdH-Wta",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "net = Net()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "qaxe6pTA-EEO",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 357
        },
        "outputId": "37cd68ed-83ef-4e61-dcad-8f4951183b43"
      },
      "cell_type": "code",
      "source": [
        "out = net(input); out"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[-2.0674, -0.6294,  1.9423,  0.0444, -0.4427, -0.5925, -1.7611,  0.2161,\n",
              "         -1.3422,  0.4794],\n",
              "        [-0.7436, -0.1677,  0.3849, -0.5462, -0.7569,  0.1370, -0.3460, -0.1350,\n",
              "         -0.3681,  0.1131],\n",
              "        [-1.2770, -0.3538,  1.0125, -0.3082, -0.6303, -0.1570, -0.9162,  0.0065,\n",
              "         -0.7606,  0.2607],\n",
              "        [-0.2820, -0.0067, -0.1581, -0.7521, -0.8665,  0.3913,  0.1473, -0.2574,\n",
              "         -0.0284, -0.0147],\n",
              "        [-0.0250,  0.0829, -0.4604, -0.8667, -0.9275,  0.5329,  0.4220, -0.3255,\n",
              "          0.1607, -0.0858],\n",
              "        [-0.4606, -0.0690,  0.0520, -0.6724, -0.8241,  0.2929, -0.0436, -0.2100,\n",
              "         -0.1598,  0.0348],\n",
              "        [ 0.2609,  0.1826, -0.7968, -0.9942, -0.9953,  0.6905,  0.7276, -0.4014,\n",
              "          0.3710, -0.1649],\n",
              "        [-0.1235,  0.0485, -0.3445, -0.8227, -0.9041,  0.4786,  0.3167, -0.2994,\n",
              "          0.0881, -0.0585],\n",
              "        [-0.3711, -0.0378, -0.0532, -0.7123, -0.8453,  0.3422,  0.0521, -0.2338,\n",
              "         -0.0940,  0.0100],\n",
              "        [-0.2136,  0.0171, -0.2385, -0.7825, -0.8827,  0.4290,  0.2204, -0.2755,\n",
              "          0.0219, -0.0336]], grad_fn=<AddmmBackward>)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    }
  ]
}