{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Source: https://course.fast.ai/Lessons/lesson2.html"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "# #hide\n",
    "! [ -e /content ] && mamba install -Uqq fastbook\n",
    "import fastbook\n",
    "fastbook.setup_book()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastbook import *\n",
    "from fastai.vision.widgets import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ims = search_images_ddg('gingko biloba tree leaf', max_images=10)\n",
    "len(ims)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dest = 'images/tree.jpg'\n",
    "download_url(ims[0], dest)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "im = Image.open(dest)\n",
    "im.to_thumb(128,128)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "categories = ('ash', 'chestnut', 'ginkgo biloba', 'silver maple', 'willow oak')\n",
    "path = Path('trees')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "if not path.exists():\n",
    "    path.mkdir()\n",
    "    for o in categories:\n",
    "        dest = (path/o)\n",
    "        dest.mkdir(exist_ok=True)\n",
    "        results = search_images_ddg(f'{o} tree leaf', max_images=100)\n",
    "        download_images(dest, urls=results)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fns = get_image_files(path)\n",
    "fns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "failed = verify_images(fns)\n",
    "failed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "failed.map(Path.unlink);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## From Data to DataLoaders"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "trees = DataBlock(blocks=(ImageBlock, CategoryBlock),\n",
    "                  get_items=get_image_files,\n",
    "                  splitter=RandomSplitter(valid_pct=0.2, seed=42),\n",
    "                  get_y=parent_label,\n",
    "                  item_tfms=Resize(128))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dls = trees.dataloaders(path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dls.valid.show_batch(max_n=12, nrows=3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Data Augmentation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "trees = trees.new(item_tfms=Resize(128), batch_tfms=aug_transforms(mult=2))\n",
    "dls = trees.dataloaders(path)\n",
    "dls.train.show_batch(max_n=8, nrows=2, unique=True)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Training Your Model, and Using It to Clean Your Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "trees = trees.new(item_tfms=RandomResizedCrop(224, min_scale=0.5),\n",
    "                  batch_tfms=aug_transforms())\n",
    "dls = trees.dataloaders(path)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn = vision_learner(dls, resnet18, metrics=error_rate)\n",
    "learn.fine_tune(5)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "interp = ClassificationInterpretation.from_learner(learn)\n",
    "interp.plot_confusion_matrix()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "interp.plot_top_losses(8, nrows=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cleaner = ImageClassifierCleaner(learn)\n",
    "cleaner"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#hide\n",
    "for idx in cleaner.delete(): cleaner.fns[idx].unlink()\n",
    "for idx,cat in cleaner.change(): shutil.move(str(cleaner.fns[idx]), path/cat)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Turning Your Model into an Online Application"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Using the Model for Inference"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn.export('model.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = Path()\n",
    "path.ls(file_exts='.pkl')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn_inf = load_learner(path/'model.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn_inf.predict('images/ash.jpg')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "learn_inf.dls.vocab"
   ]
  }
 ],
 "metadata": {
  "jupytext": {
   "split_at_heading": true
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.15"
  },
  "vscode": {
   "interpreter": {
    "hash": "6dbec04a431f157b103533e84207c2f49dc4e813632efce31ad46431e6a7d537"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}