cat classification using 1 sigmoid hidden layer

cat_vs_noncat/cat_simple_nn.ipynb

@@ -0,0 +1,286 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Cat classification with sigmoid function"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<b><i>Importing python libraries</i></b>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import h5py\n",
+    "import scipy\n",
+    "from PIL import Image\n",
+    "from scipy import ndimage\n",
+    "from random import shuffle\n",
+    "from tqdm import tqdm\n",
+    "import os\n",
+    "import cv2\n",
+    "from sklearn.metrics import accuracy_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "training_data = np.load('C:/Users/Rohit/Music/machine_learning_projects/cat_vs_noncat/cat_vs_noncat_10000.npy')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<b><i>Preprocessing step:</i></b>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "labels = training_data[0, 1]\n",
+    "for i in range(1, training_data.shape[0]):\n",
+    "\tlabels = np.concatenate((labels, training_data[i, 1]), axis = 0)\n",
+    "labels = labels.reshape(labels.shape[0], 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_data = training_data[0, 0]\n",
+    "for i in range(1, training_data.shape[0]):\n",
+    "\ttrain_data = np.concatenate((train_data, training_data[i, 0]), axis = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_data = train_data/255"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(3072, 19000)\n"
+     ]
+    }
+   ],
+   "source": [
+    "X = train_data[:,:19000]\n",
+    "Y = labels[:19000,:]\n",
+    "X_test = train_data[:, 19000:]\n",
+    "Y_test = labels[19000:, :]\n",
+    "print(X.shape)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<b><i>Initialization of parameters. </i></b>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "w = np.zeros((train_data.shape[0], 1))\n",
+    "b = 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def sigmoid(z):\n",
+    "\n",
+    "\ts = 1/(1 + np.exp(-z.astype(float)))\n",
+    "\n",
+    "\treturn s"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<b><i>Gradient calculation using Forward and Backward Propagation</i></b>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def propagate(w, b, X, Y):\n",
+    "\tz = np.dot(X.T, w) + b\n",
+    "\ta = sigmoid(z)\n",
+    "\tdz = a - Y\n",
+    "\tdw = np.dot(X, dz)/X.shape[1]\n",
+    "\tdb = np.sum(dz)/X.shape[1]\n",
+    "\t#print(db)\n",
+    "\tgrads = {\"dw\": dw,\n",
+    "\t\t\t\"db\": db}\n",
+    "\treturn grads"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<b><i>Optimization function</i></b>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def optimize(w, b, X, Y, num_iterations, learning_rate):\n",
+    "\n",
+    "\tfor i in range(num_iterations):\n",
+    "\n",
+    "\t\tgrads = propagate(w, b, X, Y)\n",
+    "\t\tdw = grads[\"dw\"]\n",
+    "\t\tdb = grads[\"db\"]\n",
+    "\t\tw = w - learning_rate*dw\n",
+    "\t\tb = b - learning_rate*db\n",
+    "\tparams = {\"w\": w,\n",
+    "\t\t\t\t\"b\": b}\n",
+    "\tgrads = {\"dw\": dw,\n",
+    "\t\t\t\t\"db\":db}\n",
+    "\treturn params, grads"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "params, grads = optimize(w, b, X, Y, num_iterations= 100, learning_rate = 0.009)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<b><i>Prediction on test data</i></b>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def predict(w, b, X, Y):\n",
+    "\tz = np.dot(X.T, w) + b\n",
+    "\ta = sigmoid(z)\n",
+    "\tfor i in range(a.shape[0]):\n",
+    "\t\tif a[i, 0] < 0.5:\n",
+    "\t\t\ta[i, 0] = np.array([0])\n",
+    "\t\telse:\n",
+    "\t\t\ta[i, 0] = np.array([1])\n",
+    "\treturn a\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "w = params[\"w\"]\n",
+    "b = params[\"b\"]\n",
+    "pred_Y = predict(w, b, X_test, Y_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy:  0.631\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"Accuracy: \",accuracy_score(Y_test, pred_Y))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<h3 style = \"color:red\">Note: </h3><b><i>This neural network model uses only one layer i.e. output layer with one sigmoid unit just to predict 0/1. This model is trained on just 1800 train images and tested on 200 test images.</i><b>"
+   ]
+  },
+  {
+   "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": "3.5.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}