rdm

Co-Authored-By: Ranuga <[email protected]>

Author: Programmer-RD-AI

.ipynb_checkpoints/04-checkpoint.ipynb

@@ -0,0 +1,181 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "501aa46e-5a51-4905-abba-9c9d162887ff",
+   "metadata": {},
+   "source": [
+    "# PyTorch Custom Datasets Video Notebook\n",
+    "\n",
+    "We've used some datasets with PyTorch before.\n",
+    "\n",
+    "But how do you get your own data into PyTorch?\n",
+    "\n",
+    "One of the ways to do is via: custom Datasets\n",
+    "\n",
+    "## Domain libraries\n",
+    "\n",
+    "Depending on what you're working on, vision, text, audio, recommendation, you'll want to look into each of PyTorch domain libraries for existing data loading functions and customalizable functionsm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "27b3dc99-7f43-4eb6-8a74-fc1b3e4fa86b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'1.9.1'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "from torch import nn,optim\n",
+    "torch.__version__"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f1cc4468-8832-4c43-b801-965f7a1575f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "device = 'cuda' if torch.cuda.is_available() else 'cpu'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "53fad586-2be6-4902-82ed-59465dbb01fc",
+   "metadata": {},
+   "source": [
+    "## Get data\n",
+    "\n",
+    "Our dataset is a subset of the Food101 dataset.\n",
+    "\n",
+    "Food101 start 101 different classes of food. (750,250)\n",
+    "\n",
+    "Our dataset starts with 3 classes of fodd and only 10% of the images(75 and 25 testing)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "209c6a08-719f-4af8-a58c-377a1f873757",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "import zipfile\n",
+    "from pathlib import Path\n",
+    "\n",
+    "# Setup path to a data folder\n",
+    "\n",
+    "data_path = Path(\"data/04/01\")\n",
+    "\n",
+    "data_path.mkdir(parents=True,exist_ok=True)\n",
+    "\n",
+    "with open(data_path / \"data.zip\",'wb') as f:\n",
+    "    request = requests.get(\"https://github.com/mrdbourke/pytorch-deep-learning/raw/main/data/pizza_steak_sushi.zip\")\n",
+    "    f.write(request.content)\n",
+    "with zipfile.ZipFile(data_path / \"data.zip\", 'r') as zip_ref:\n",
+    "    zip_ref.extractall(data_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "88a16a48-0f37-4f6e-a179-f19319e83244",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "def walk_through_dir(dir_path):\n",
+    "    \"\"\"Walks through dir_path returning its contents.\"\"\"\n",
+    "    for dirpath,dirnames,filenames in os.walk(dir_path):\n",
+    "        print(f\"There are {len(dirnames)} and {len(filenames)} images in {dirpath}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "cba4eb63-9135-46ff-8b77-eb5fec60cb85",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "There are 2 and 1 images in data/04/01\n",
+      "There are 3 and 0 images in data/04/01/train\n",
+      "There are 0 and 75 images in data/04/01/train/steak\n",
+      "There are 1 and 78 images in data/04/01/train/pizza\n",
+      "There are 0 and 3 images in data/04/01/train/pizza/.ipynb_checkpoints\n",
+      "There are 0 and 72 images in data/04/01/train/sushi\n",
+      "There are 3 and 0 images in data/04/01/test\n",
+      "There are 0 and 19 images in data/04/01/test/steak\n",
+      "There are 0 and 25 images in data/04/01/test/pizza\n",
+      "There are 0 and 31 images in data/04/01/test/sushi\n"
+     ]
+    }
+   ],
+   "source": [
+    "walk_through_dir(data_path)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e5eb494b-a379-4123-acef-ae52c1c83bd7",
+   "metadata": {},
+   "source": [
+    "## Visualizing an image\n",
+    "\n",
+    "Let's write some code to:\n",
+    "1. Get all of the image paths\n",
+    "2. Pick a random image path using `random.choice()`\n",
+    "3. Get the image class name using `pathlib.Path.parent.stem`\n",
+    "4. Science we're working with images, let open it with PIL\n",
+    "5. Show and tell metadata"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a908ae02-c671-4567-84d7-5d25e4d37c03",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "from PIL import Image"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}