time_warp.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7fd5ece15240>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "from random import randint\n",
    "\n",
    "from PIL import Image\n",
    "from PIL.Image import BICUBIC\n",
    "from matplotlib import pyplot\n",
    "\n",
    "import torchvision\n",
    "from torchvision.transforms.functional import resized_crop, to_tensor, to_pil_image\n",
    "\n",
    "dataset = torchvision.datasets.MNIST(\"./data\", download=True)\n",
    "img = to_tensor(dataset[0][0])[0].float() / 255\n",
    "pyplot.imshow(img)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x7fd5ecc3b828>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "def time_warp(tens, w):\n",
    "    i = Image.fromarray(tens.numpy())\n",
    "    x = randint(0, w-1)\n",
    "    y = resized_crop(i, 0, x, i.size[0], i.size[1] - 2 * w, i.size, Image.BICUBIC)\n",
    "    return to_tensor(y)[0]\n",
    "\n",
    "pyplot.imshow(time_warp(img, 8))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Help on function resized_crop in module torchvision.transforms.functional:\n",
      "\n",
      "resized_crop(img, i, j, h, w, size, interpolation=2)\n",
      "    Crop the given PIL Image and resize it to desired size.\n",
      "    \n",
      "    Notably used in :class:`~torchvision.transforms.RandomResizedCrop`.\n",
      "    \n",
      "    Args:\n",
      "        img (PIL Image): Image to be cropped.\n",
      "        i: i in (i,j) i.e coordinates of the upper left corner\n",
      "        j: j in (i,j) i.e coordinates of the upper left corner\n",
      "        h: Height of the cropped image.\n",
      "        w: Width of the cropped image.\n",
      "        size (sequence or int): Desired output size. Same semantics as ``resize``.\n",
      "        interpolation (int, optional): Desired interpolation. Default is\n",
      "            ``PIL.Image.BILINEAR``.\n",
      "    Returns:\n",
      "        PIL Image: Cropped image.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "help(resized_crop)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}