{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Imagenette"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%reload_ext autoreload\n",
    "%autoreload 2\n",
    "%matplotlib inline\n",
    "\n",
    "from fastai.vision import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = Path('/mnt/fe2_disk/imagenet/')\n",
    "names = {o.name for o in (path/'train').ls()}\n",
    "classes = pd.read_csv(path/'classids.txt', delimiter=' ', header=None, names=['id','name'])\n",
    "classes = {k:v for k,v in [o.strip().split() for o in (path/'classids.txt').open().readlines()] if k in names}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#doggies\n",
    "subids = 'n02096294 n02093754 n02111889 n02088364 n02086240 n02089973 n02087394 n02115641 n02099601 n02105641'.split()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#nette\n",
    "subids = 'n01440764 n02102040 n02979186 n03000684 n03028079 n03394916 n03417042 n03425413 n03445777 n03888257'.split()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ds = '{' + ','.join(subids) + '}'\n",
    "ds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "', '.join([classes[o] for o in subids])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for o in ['160','320','imagenet']:\n",
    "    for p in ['val','train']:\n",
    "        src = Path('/mnt/fe2_disk')/o/p\n",
    "        dst = Path('/mnt/fe2_disk/imagewoof')/o/p\n",
    "        dst.mkdir(exist_ok=True, parents=True)\n",
    "        for s in subids: shutil.copytree(src/s, dst/s)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Test flip"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bs,size = 64,224\n",
    "path = untar_data(URLs.PETS)/'images'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "src = ImageList.from_folder(path).split_by_rand_pct(0.2)\n",
    "data = src.label_from_re(r'([^/]+)_\\d+.jpg$').presize(size)\n",
    "img = data.train.x[0]\n",
    "img.px.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%timeit flip_lr(img)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%timeit t = tensor(np.ascontiguousarray(np.array(img.px)[...,::-1]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "idxs = torch.arange(224-1,-1,-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%timeit t=img.px[...,idxs];"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%timeit t=img.px[...,torch.arange(224-1,-1,-1)];"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## fin"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}