added initial notebook for cnn model

ngilmore · Jan 12, 2020 · bc8d492 · bc8d492
1 parent 67dc20f
commit bc8d492
Showing 1 changed file with 126 additions and 0 deletions.
diff --git a/notebooks/2.0-ng-differentiate-weeds-using-cnn.ipynb b/notebooks/2.0-ng-differentiate-weeds-using-cnn.ipynb
@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Differentiate weeds from crop seedlings using a convolutional neural network (CNN)\n",
+    "\n",
+    "The goal of the project is to correctly identify the weed type from a variety of weed and crop RGB images using a relatively big dataset (~2GB).\n",
+    "\n",
+    "Created on Sun Jan 12 12:33:49 2020\n",
+    "\n",
+    "@author: neal gilmore"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## What is the objective of the machine learning model?\n",
+    "\n",
+    "We aim to maximise the accuracy, i.e., the correct classification of the different weed varieties."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Table of Contents<a id='0.0'></a>\n",
+    "\n",
+    "#### [STEP 1: Environment Preparation](#1.0)\n",
+    "1.1 [Import required libraries](#1.1)  \n",
+    "1.2 [Prepare for reproducability](#1.2)  \n",
+    "\n",
+    "#### [STEP 2: Data Preparation](#2.0)\n",
+    "2.1 [Join training and test sets](#2.1)  \n",
+    "2.2 [Import data](#2.2)  \n",
+    "2.3 [Summary statistics](#2.3) \n",
+    "\n",
+    "#### [STEP 3: Data Analysis](#3.0)\n",
+    "3.1 \n",
+    "\n",
+    "\n",
+    "#### [STEP 4: Feature Engineering](#4.0)\n",
+    "4.1  \n",
+    "\n",
+    "#### [STEP 5: Feature Selection](#5.0)\n",
+    "5.1 \n",
+    "\n",
+    "#### [STEP 6: Model Building](#6.0)\n",
+    "6.1   "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## STEP 1: Environment Preparation<a id='1.0'></a> [(Top)](#0.0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 1.1 Import required libraries<a id='1.1'></a> [(Top)](#0.0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 1.2 Prepare for reproducability<a id=\"1.2\"></a>[(Top)](#0.0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Set random seed to maintain reproducability\n",
+    "random_state = np.random.seed(42)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## STEP 2: Data Preparation<a id='2.0'></a> [(Top)](#0.0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "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": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}