elly bootcamp code

wargbootcamp.ipynb

@@ -0,0 +1,141 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "collapsed_sections": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "o7Rn9olzZu2j"
+      },
+      "outputs": [],
+      "source": [
+        "import matplotlib.pyplot as plt \n",
+        "import numpy as np \n",
+        "import pandas as pd\n",
+        "\n",
+        "import tensorflow as tf\n",
+        "from tensorflow.keras import datasets, layers, models\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# defining test and train data and importing the dataset\n",
+        "(X_train, y_train), (X_test,y_test) = datasets.cifar10.load_data()"
+      ],
+      "metadata": {
+        "id": "LLFckBO-Z3HE"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#naming the classes\n",
+        "classes = [\"airplane\", \"automobile\", \"bird\", \"cat\", \"deer\", \"dog\", \"frog\", \"horse\", \"ship\", \"truck\"]"
+      ],
+      "metadata": {
+        "id": "4b3U5Wala_zI"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# normalize the data so pixel value is consistent\n",
+        "X_train = X_train/255\n",
+        "X_test = X_test/255"
+      ],
+      "metadata": {
+        "id": "EVEFWuJf6-v0"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#creating the convolutional neural network\n",
+        "cnn = models.Sequential ([\n",
+        "    #first cnn layer\n",
+        "    layers.Conv2D(filters=32, kernel_size=(3, 3), activation='relu', input_shape=(32, 32, 3)),\n",
+        "    #pooling the image to normalize pixels across images\n",
+        "    layers.MaxPooling2D((2,2)),\n",
+        "\n",
+        "    # second cnn layer \n",
+        "    layers.Conv2D(filters=32, kernel_size=(3, 3), activation='relu', input_shape=(32, 32, 3)),\n",
+        "    #pooling the image to normalize pixels across images\n",
+        "    layers.MaxPooling2D((2,2)),\n",
+        "\n",
+        "    #cnn dense layer\n",
+        "    layers.Flatten(),\n",
+        "    layers.Dense (64, activation='relu'),\n",
+        "    layers.Dense (10, activation='softmax')\n",
+        "\n",
+        "])"
+      ],
+      "metadata": {
+        "id": "Yyrw3bSAC9uj"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#compiling the CNN; \n",
+        "#using adam optimizer since it has good accuracy\n",
+        "# using sparse_categorical_crossentropy because it is good for classification\n",
+        "cnn.compile( optimizer ='adam', \n",
+        "               loss='sparse_categorical_crossentropy', \n",
+        "               metrics=['accuracy']    \n",
+        ")"
+      ],
+      "metadata": {
+        "id": "btb3w_pNE2b_"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#running the model on the training data with optimized epochs\n",
+        "cnn.fit(X_train, y_train, epochs=15)"
+      ],
+      "metadata": {
+        "id": "hcR2vMS6F1BA"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#running the model on the test data with optimized epochs\n",
+        "cnn.fit(X_test, y_test, epochs=15)"
+      ],
+      "metadata": {
+        "id": "DkIuDuBIMhhc"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}