working on p3

tutorial/P3_trasnfer_learning.ipynb

@@ -1,16 +1,18 @@
 {
  "cells": [
   {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "initial_id",
+   "cell_type": "markdown",
+   "source": [
+    "# Install drillvision"
+   ],
    "metadata": {
-    "collapsed": true,
-    "ExecuteTime": {
-     "end_time": "2023-11-19T23:01:14.962884700Z",
-     "start_time": "2023-11-19T23:01:12.698957700Z"
-    }
+    "collapsed": false
    },
+   "id": "622c05a88fb1ad42"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
    "outputs": [
     {
      "name": "stdout",
@@ -133,49 +135,61 @@
    ],
    "source": [
     "!pip install drillvision"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "outputs": [],
-   "source": [
-    "from neural_network_model.transfer_learning import TransferModel"
    ],
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2023-11-19T23:03:12.479404900Z",
-     "start_time": "2023-11-19T23:03:08.237223100Z"
+     "start_time": "2023-11-19T23:01:12.698957700Z"
     }
    },
-   "id": "84ca0b4d0189f28d"
+   "id": "initial_id"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Import appropriate modules"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "439b3b5a21172450"
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "outputs": [],
    "source": [
+    "from neural_network_model.transfer_learning import TransferModel\n",
     "from pathlib import Path"
    ],
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2023-11-19T23:03:18.103265500Z",
-     "start_time": "2023-11-19T23:03:18.086228500Z"
+     "end_time": "2023-11-20T16:51:03.501628800Z",
+     "start_time": "2023-11-20T16:50:59.045558600Z"
     }
    },
-   "id": "3669aa9df2c03862"
+   "id": "84ca0b4d0189f28d"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Initiate TransferModel object and set the directory for dataset"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "34462e32d53d05bc"
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2023-11-19 17:04:39,056 - INFO - Data was prepared\n"
+      "2023-11-20 10:51:28,192 - INFO - Data was prepared\n"
      ]
     }
    ],
@@ -187,12 +201,22 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2023-11-19T23:04:39.062545700Z",
-     "start_time": "2023-11-19T23:04:38.981546Z"
+     "end_time": "2023-11-20T16:51:28.201827400Z",
+     "start_time": "2023-11-20T16:51:28.113667400Z"
     }
    },
    "id": "2ba10e6cc8c4643c"
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Illustrate the distribution of images across various classes in the dataset"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "3df1d198986baf26"
+  },
   {
    "cell_type": "code",
    "execution_count": 7,
@@ -232,6 +256,16 @@
    },
    "id": "c3e459d730220077"
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Examine the images and assess their width and height to identify any discrepancies in dimensions"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "cd41f9f350cbf147"
+  },
   {
    "cell_type": "code",
    "execution_count": 8,
@@ -288,6 +322,16 @@
    },
    "id": "75722466fedc4d4f"
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Plot the images using cmap jet"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "5394be1157063d66"
+  },
   {
    "cell_type": "code",
    "execution_count": 9,
@@ -313,6 +357,16 @@
    },
    "id": "5d89fcd09e4483df"
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Utilize transfer learning for training and specify the save path for the trained transfer_model along with its given name."
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "134ca2f14e87a109"
+  },
   {
    "cell_type": "code",
    "execution_count": 11,
@@ -349,6 +403,16 @@
    },
    "id": "df17c7ccf46c4eee"
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Graph the metrics against the iteration number for visualization."
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "d4e6c530f420b6ee"
+  },
   {
    "cell_type": "code",
    "execution_count": 12,
@@ -432,6 +496,16 @@
    },
    "id": "fce9e3bb6b88543b"
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Generate plots for images belonging to the specified classes, and employ the model to predict their respective labels"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "1abfacbcf41826df"
+  },
   {
    "cell_type": "code",
    "execution_count": 15,
@@ -508,6 +582,16 @@
    },
    "id": "3b1ec4518767e307"
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Apply Grad-CAM (Gradient-weighted Class Activation Mapping) to visualize and interpret the activations of a specific layer in the model"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "59fd765de4675e88"
+  },
   {
    "cell_type": "code",
    "execution_count": 16,