Untitled10.ipynb

untitled10.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Untitled10.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyOXenI+xjgxKs/RK2sH5dFZ",
      "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/gist/moarshy/19d0a5a60797d5e86decf20adc5e7a8b/untitled10.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 26,
      "metadata": {
        "id": "75IDHaqSs-kF"
      },
      "outputs": [],
      "source": [
        "!pip install git+https://github.com/fastai/fastai.git -Uqq\n",
        "!pip install timm -Uqq"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from fastai.vision.all import *\n",
        "import timm"
      ],
      "metadata": {
        "id": "AujaDXNatQBN"
      },
      "execution_count": 27,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "path = untar_data(URLs.PETS)"
      ],
      "metadata": {
        "id": "aSglXkSYtIgf"
      },
      "execution_count": 28,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "files = get_image_files(path/\"images\")\n",
        "def label_func(f): return f[0].isupper()\n",
        "dls = ImageDataLoaders.from_name_func(path, files, label_func, item_tfms=Resize(224))"
      ],
      "metadata": {
        "id": "spBshfB0tO4H"
      },
      "execution_count": 29,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "timm.list_models()"
      ],
      "metadata": {
        "id": "I2_A15tRuEM0"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Resnet"
      ],
      "metadata": {
        "id": "xQbpSNO8zvDm"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "learn = cnn_learner(dls, \n",
        "                    'resnet18',\n",
        "                    metrics=accuracy).to_fp16()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3DzwLkAOt5L3",
        "outputId": "a6dca53d-1af9-45e6-c5d4-d91765501271"
      },
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/fastai/vision/learner.py:265: UserWarning: `cnn_learner` has been renamed to `vision_learner` -- please update your code\n",
            "  warn(\"`cnn_learner` has been renamed to `vision_learner` -- please update your code\")\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "learn.model[1]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9nZ1MyN7zxen",
        "outputId": "76c4a532-b692-4ed6-aff3-e6aa166837d3"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Sequential(\n",
              "  (0): AdaptiveConcatPool2d(\n",
              "    (ap): AdaptiveAvgPool2d(output_size=1)\n",
              "    (mp): AdaptiveMaxPool2d(output_size=1)\n",
              "  )\n",
              "  (1): Flatten(full=False)\n",
              "  (2): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "  (3): Dropout(p=0.25, inplace=False)\n",
              "  (4): Linear(in_features=1024, out_features=512, bias=False)\n",
              "  (5): ReLU(inplace=True)\n",
              "  (6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "  (7): Dropout(p=0.5, inplace=False)\n",
              "  (8): Linear(in_features=512, out_features=2, bias=False)\n",
              ")"
            ]
          },
          "metadata": {},
          "execution_count": 43
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "learn.fit_one_cycle(1)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "dH7fa2mtuXqw",
        "outputId": "4d189d6c-3e60-41f3-b401-bbc38aeaa8f0"
      },
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "<style>\n",
              "    /* Turns off some styling */\n",
              "    progress {\n",
              "        /* gets rid of default border in Firefox and Opera. */\n",
              "        border: none;\n",
              "        /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
              "        background-size: auto;\n",
              "    }\n",
              "    .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
              "        background: #F44336;\n",
              "    }\n",
              "</style>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: left;\">\n",
              "      <th>epoch</th>\n",
              "      <th>train_loss</th>\n",
              "      <th>valid_loss</th>\n",
              "      <th>accuracy</th>\n",
              "      <th>time</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <td>0</td>\n",
              "      <td>0.647062</td>\n",
              "      <td>0.246660</td>\n",
              "      <td>0.904601</td>\n",
              "      <td>01:08</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "body = TimmBody('resnet18')"
      ],
      "metadata": {
        "id": "h3ENbeFO1PLN"
      },
      "execution_count": 46,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "body.needs_pool"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cZFpzA5h1Vbu",
        "outputId": "8217d109-71af-435e-f24f-a2549c77c82f"
      },
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(7, 7)"
            ]
          },
          "metadata": {},
          "execution_count": 48
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Transformer Model"
      ],
      "metadata": {
        "id": "GuuUr8eq0j00"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "learn = cnn_learner(dls, \n",
        "                    'vit_base_patch8_224',\n",
        "                    metrics=accuracy).to_fp16()"
      ],
      "metadata": {
        "id": "FI3ppdJdyLuR",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "02cb5a75-1fbe-4b27-be7f-191f7bddfc85"
      },
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/fastai/vision/learner.py:265: UserWarning: `cnn_learner` has been renamed to `vision_learner` -- please update your code\n",
            "  warn(\"`cnn_learner` has been renamed to `vision_learner` -- please update your code\")\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "learn.model[1]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LCv-qPjJ03cB",
        "outputId": "763744ca-9413-4044-c7c2-61a538766afc"
      },
      "execution_count": 45,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Sequential(\n",
              "  (0): BatchNorm1d(1536, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "  (1): Dropout(p=0.25, inplace=False)\n",
              "  (2): Linear(in_features=1536, out_features=512, bias=False)\n",
              "  (3): ReLU(inplace=True)\n",
              "  (4): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
              "  (5): Dropout(p=0.5, inplace=False)\n",
              "  (6): Linear(in_features=512, out_features=2, bias=False)\n",
              ")"
            ]
          },
          "metadata": {},
          "execution_count": 45
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "body = TimmBody('vit_base_patch8_224')"
      ],
      "metadata": {
        "id": "Nqj9Vb5b07jF"
      },
      "execution_count": 49,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#needs pool is none\n",
        "body.needs_pool"
      ],
      "metadata": {
        "id": "G3a4VkMx1gJL"
      },
      "execution_count": 51,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        ""
      ],
      "metadata": {
        "id": "-4IcebOE1hzc"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}