{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "013df7bd-6b5f-4fd6-8ad0-62d05bd46e34",
   "metadata": {},
   "source": [
    "# Fastai Environment Validation"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "93f9190c-31af-4b0e-945c-23ada2d37cdd",
   "metadata": {},
   "source": [
    "This notebook validates your Fastai environment. This assumes you have a default installation of Fastai with all dependencies and datasets and the environment was built using the example `.yml` file. Open this notebook with the `fastai` kernel to verify your environment."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c76f580-82af-4caa-ac38-6394910fa92d",
   "metadata": {},
   "source": [
    "### Import Packages\n",
    "Make sure you can import packages without any errors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "23ef4b76-74f3-42a6-8e42-a0676568affa",
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastai.vision.all import *"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "98e71ef0-7a01-465d-b23d-f0e52bfb7a99",
   "metadata": {},
   "source": [
    "### Extract Data \n",
    "Verify you can extract the sample datasets to your local directories "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e8803cdd-0087-4f6e-9348-6766198e9a09",
   "metadata": {},
   "outputs": [],
   "source": [
    "path = untar_data(URLs.PETS)/'images'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4c168baa-bc32-43ec-bb5c-05614694167a",
   "metadata": {},
   "source": [
    "### Define a Dataloader\n",
    "Define a `fastai` dataloader and specify a validation set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "74229bf3-5c2f-4440-a642-459dd13907b7",
   "metadata": {},
   "outputs": [],
   "source": [
    "def is_cat(x): return x[0].isupper()\n",
    "dls = ImageDataLoaders.from_name_func(\n",
    "    path, get_image_files(path), valid_pct=0.2, seed=42,\n",
    "    label_func=is_cat, item_tfms=Resize(224))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ab1faa2b-3a30-41c7-a8d0-9c759da8bf30",
   "metadata": {},
   "source": [
    "### Train a Classifier\n",
    "Create a fastai learner and run a training (finetuning)job for 1 epoch using the dataloader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "373b3f26-9d3f-4fa7-ade3-7d2ba66fe51b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>error_rate</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0.167120</td>\n",
       "      <td>0.026278</td>\n",
       "      <td>0.008119</td>\n",
       "      <td>00:30</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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>error_rate</th>\n",
       "      <th>time</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0.061470</td>\n",
       "      <td>0.010634</td>\n",
       "      <td>0.003383</td>\n",
       "      <td>00:35</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "learn = cnn_learner(dls, resnet34, metrics=error_rate)\n",
    "learn.fine_tune(1)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "fastai:Python",
   "language": "python",
   "name": "conda-env-fastai-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}