Merge branch 'master' of https://git.cse.iitb.ac.in/smitgangurde/CS725_Project

Notebooks/CustomCNNs/CustomCNN725Project.ipynb

@@ -14,6 +14,16 @@
     "accelerator": "GPU"
   },
   "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ZzS6OM-yfixt"
+      },
+      "source": [
+        "**Indian Dance Form Recognition using custom CNNs**<br>\n",
+        "This is a classification problem with 8 classes. In this task, we will be doing 7-fold cross validation on a training set of 364 images. This will be done using varied CNN networks. We will analyse the average accuracies from the cross-validation."
+      ]
+    },
     {
       "cell_type": "code",
       "metadata": {
@@ -46,16 +56,13 @@
       ]
     },
     {
-      "cell_type": "code",
+      "cell_type": "markdown",
       "metadata": {
-        "id": "hhb1KDmXALaF"
+        "id": "pExcuhZqhHmq"
       },
       "source": [
-        "!mkdir helpers\n",
-        "!touch helpers/__init__.py"
-      ],
-      "execution_count": null,
-      "outputs": []
+        "You need to import the 'helpers' folder, it contains code for cross-validation, etc."
+      ]
     },
     {
       "cell_type": "code",
@@ -83,37 +90,6 @@
       "execution_count": null,
       "outputs": []
     },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "mKkJU_yHSim-",
-        "outputId": "761133a1-4389-4e39-beaf-af864b8ff6d7"
-      },
-      "source": [
-        "import importlib\n",
-        "importlib.reload(helper)\n",
-        "importlib.reload(base_model)\n",
-        "importlib.reload(CV)"
-      ],
-      "execution_count": null,
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": [
-              "<module 'helpers.cross_validation' from '/content/helpers/cross_validation.py'>"
-            ]
-          },
-          "metadata": {
-            "tags": []
-          },
-          "execution_count": 2
-        }
-      ]
-    },
     {
       "cell_type": "code",
       "metadata": {
@@ -197,7 +173,7 @@
         "outputId": "485bce42-02c3-4d07-e2bd-538521c85c21"
       },
       "source": [
-        "###############Data Distributions##############\n",
+        "############### Data Distributions for the 7 folds ##############\n",
         "distribution_dict = {}\n",
         "ctr = 0\n",
         "for i in image_labels:\n",
@@ -794,6 +770,15 @@
         }
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "mwlSHc5Wh4Qy"
+      },
+      "source": [
+        "As we can see, Model1, on average tends to perform relatively better."
+      ]
+    },
     {
       "cell_type": "code",
       "metadata": {

README.txt

-**************INITIAL README**************
-#Change later
+**************README**************
+
+TEAM:
+Aarushi Aiyyer - 203050045
+Bhavesh Yadav - 193050052
+Khyati Oswal - 203050058
+Raj Gite - 203050092
+Smit Gangurde - 203050108
+Yavnika Bhagat - 203050041
+
+Problem Statement:
+Identify the type of Indian dance form from a dance pose image 
+Use multiple techniques to classify the images and compare them 
 
 Dataset Links:
-1) https://www.kaggle.com/somnath796/indian-dance-form-recognition   #This is version 1, 27MB 
-2) https://www.kaggle.com/parthplc/indian-dance-images/version/2     #Version 2, 232MB
+1) https://www.kaggle.com/somnath796/indian-dance-form-recognition 27MB 
 
 Conventions:
-	- dataset1/ : Dataset Version 1 (Smaller size dataset)
-	- dataset2/ : Dataset Version 2 (Larger Size dataset)
+	- dataset1/ : Dataset Version 1
 
 Paper Links:
 1) https://arxiv.org/pdf/1812.05231.pdf (IIT Delhi)
@@ -15,22 +24,17 @@ Paper Links:
 3) https://ieeexplore.ieee.org/document/9182365
 
 Helpful reference code:
-1) https://github.com/ubsingh9/identify-the-dance-form
+1)https://www.kaggle.com/singhuday/identifythedanceform/version/1
+2)https://github.com/Tessellate-Imaging/monk_v1
+3)https://clever-noyce-f9d43f.netlify.app/#/introduction
+4)https://www.youtube.com/watch?v=zFA8Cm13Xmk
+5)https://medium.com/@dtuk81/confusion-matrix-visualization-fc31e3f30fea
 
 
 Added Dataset Version 1 to Google Drive: https://drive.google.com/file/d/1zTI002FEm0BcbXlUFpLs5zvurWGnx68v/view?usp=sharing
-Added Dataset Version 2 to Google Drive: https://drive.google.com/file/d/1I29xdtdJVd7FoT7Uyw1QHafKyRzsqPzK/view?usp=sharing
-Reason: To make it easier to work on Google Colab.
-----------------------------------------------------------------------------------
-*******THIS IS PURELY FOR CONVENIENCE, TO SETUP THE DATASET ENV IN COLAB.*******
-*******YOU DO NOT NEED TO NECESSARILY FOLLOW THIS.*******
-*******LINKS SUBJECT TO CHANGE AFTER PREPROCESSING.*******
-----------------------------------------------------------------------------------
-RUN THE FOLLOWING IN GOOGLE COLAB TO IMPORT FOLDERS:
-----------------------------------------------------------------------------------
-> !pip install gdown
-> !gdown --id <insert id of file here>
-#eg: !gdown --id 1I29xdtdJVd7FoT7Uyw1QHafKyRzsqPzK #for dataset2
-> !tar -zxf <tar-filename>
-> !rm <tar-filename>
-----------------------------------------------------------------------------------
+
+The Repository contains 3 notebooks:
+1. Custom CNN
+2. VGG16
+3. RESNET152
+