final submission

Co-Authored-By: Chirag Bhatt <[email protected]>

README.md

@@ -1,2 +1,9 @@
-# meme-classifier-competition
- In class Kaggle Meme Classification competiiton for MTL782 (Data Mining) course offered in Spring 2021
+# multimodal-meme-classification
+
+This repository contains the files for the InClass Kaggle competition, based on Multi-modal Meme Classification, for MTL782 (Data Mining) course offered in Spring 2021
+
+**Report:** [`Meme_Classification.pdf`](Meme_Classification.pdf)
+
+**Code**: [`codes/`](codes/) *(Also contains README)*
+
+**Competition Link:** https://www.kaggle.com/c/dataminingmtl782

codes/README.txt

@@ -0,0 +1,13 @@
+The folder contains 3 sub folders and 1 csv file
+1. github_package_downloads
+this folder contains all the available existing pre trained models and packages (taken from github) that were utilised/modified/referenced by us for the competition.
+
+2. submissions
+this folder contains sub folders for each submissions. The folder names is of the form sub_[]-the numbers between [] denote the submission number.
+subfolders contains the .ipynb files and other .py files containing the codes for each submissions. .ipynb files are python notebook which we used for executing the code interactively.
+
+3. backup
+this folder contains all the .pynb,.py files created/used by us during the whole competition. This folder can be ignored.
+
+4. submissions.csv
+this csv file contains description(name of the .csv file, description of the approach, public score, private score) about all the 15 .csv submission we made on the kaggle. The submission numbers are also mapped here.

codes/backup/[apr10]_sub-1_2-MTL782-memes(1).ipynb

@@ -0,0 +1 @@
+{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"MTL782-memes.ipynb","provenance":[],"authorship_tag":"ABX9TyN8+S2C8Ryc1HtpBvahglA5"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"l1E12hR9YXjm","executionInfo":{"status":"ok","timestamp":1618055015165,"user_tz":-330,"elapsed":16873,"user":{"displayName":"Subhalingam D","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg86bQ1NVmL-U0-lCsAdMpCA_G3d9fxrw_PlOwtJg=s64","userId":"08059846138458314824"}},"outputId":"c281d867-3632-4686-ba48-8df7d86237a2"},"source":["!mkdir /root/.kaggle/\n","!mv /kaggle.json /root/.kaggle/\n","!pip install -q kaggle\n","!kaggle competitions download -c dataminingmtl782 "],"execution_count":3,"outputs":[{"output_type":"stream","text":["mkdir: cannot create directory ‘/root/.kaggle/’: File exists\n","Warning: Your Kaggle API key is readable by other users on this system! To fix this, you can run 'chmod 600 /root/.kaggle/kaggle.json'\n","Warning: Looks like you're using an outdated API Version, please consider updating (server 1.5.12 / client 1.5.4)\n","Downloading 344_image_batch_2.png to /content\n"," 0% 0.00/38.0k [00:00<?, ?B/s]\n","100% 38.0k/38.0k [00:00<00:00, 10.5MB/s]\n","Downloading 178_image_batch_2.png to /content\n"," 0% 0.00/60.5k [00:00<?, ?B/s]\n","100% 60.5k/60.5k [00:00<00:00, 18.2MB/s]\n","Downloading 315_image_batch_2.png to /content\n"," 0% 0.00/30.3k [00:00<?, ?B/s]\n","100% 30.3k/30.3k [00:00<00:00, 35.7MB/s]\n","Downloading 310_image_batch_2.png to /content\n"," 0% 0.00/45.3k [00:00<?, ?B/s]\n","100% 45.3k/45.3k [00:00<00:00, 34.3MB/s]\n","Downloading 285_image_batch_2.png to /content\n"," 0% 0.00/96.6k [00:00<?, ?B/s]\n","100% 96.6k/96.6k [00:00<00:00, 29.2MB/s]\n","Downloading 183_image_batch_2.png to /content\n"," 0% 0.00/58.8k [00:00<?, ?B/s]\n","100% 58.8k/58.8k [00:00<00:00, 52.3MB/s]\n","Downloading 103_image_batch_2.png to /content\n"," 0% 0.00/30.5k [00:00<?, ?B/s]\n","100% 30.5k/30.5k [00:00<00:00, 24.9MB/s]\n","Downloading 309_image_batch_2.png to /content\n"," 0% 0.00/73.8k [00:00<?, ?B/s]\n","100% 73.8k/73.8k [00:00<00:00, 23.5MB/s]\n","Downloading 288_image_batch_2.png to /content\n"," 0% 0.00/60.0k [00:00<?, ?B/s]\n","100% 60.0k/60.0k [00:00<00:00, 60.6MB/s]\n","Downloading 248_image_batch_2.png to /content\n"," 0% 0.00/123k [00:00<?, ?B/s]\n","100% 123k/123k [00:00<00:00, 39.6MB/s]\n","Downloading 306_image_batch_2.png to /content\n"," 0% 0.00/33.6k [00:00<?, ?B/s]\n","100% 33.6k/33.6k [00:00<00:00, 31.8MB/s]\n","Downloading 237_image_batch_2.png to /content\n"," 0% 0.00/40.2k [00:00<?, ?B/s]\n","100% 40.2k/40.2k [00:00<00:00, 42.4MB/s]\n","Downloading 257_image_batch_2.png to /content\n"," 0% 0.00/31.9k [00:00<?, ?B/s]\n","100% 31.9k/31.9k [00:00<00:00, 26.3MB/s]\n","Downloading 169_image_batch_2.png to /content\n"," 0% 0.00/206k [00:00<?, ?B/s]\n","100% 206k/206k [00:00<00:00, 35.8MB/s]\n","Downloading 326_image_batch_2.png to /content\n"," 0% 0.00/29.3k [00:00<?, ?B/s]\n","100% 29.3k/29.3k [00:00<00:00, 26.1MB/s]\n","Downloading 268_image_batch_2.png to /content\n"," 0% 0.00/47.0k [00:00<?, ?B/s]\n","100% 47.0k/47.0k [00:00<00:00, 41.1MB/s]\n","Downloading 249_image_batch_2.png to /content\n"," 0% 0.00/47.5k [00:00<?, ?B/s]\n","100% 47.5k/47.5k [00:00<00:00, 34.4MB/s]\n","Downloading 259_image_batch_2.png to /content\n"," 0% 0.00/34.6k [00:00<?, ?B/s]\n","100% 34.6k/34.6k [00:00<00:00, 30.2MB/s]\n","Downloading 233_image_batch_2.png to /content\n"," 0% 0.00/77.9k [00:00<?, ?B/s]\n","100% 77.9k/77.9k [00:00<00:00, 86.6MB/s]\n","Downloading 232_image_batch_2.png to /content\n"," 0% 0.00/27.8k [00:00<?, ?B/s]\n","100% 27.8k/27.8k [00:00<00:00, 22.9MB/s]\n","Downloading 10_image_batch_2.png to /content\n"," 0% 0.00/69.2k [00:00<?, ?B/s]\n","100% 69.2k/69.2k [00:00<00:00, 53.0MB/s]\n","Downloading 426_image_batch_2.png to /content\n"," 0% 0.00/44.3k [00:00<?, ?B/s]\n","100% 44.3k/44.3k [00:00<00:00, 37.1MB/s]\n","Downloading 153_image.png to /content\n"," 0% 0.00/64.6k [00:00<?, ?B/s]\n","100% 64.6k/64.6k [00:00<00:00, 57.9MB/s]\n","Downloading 589_image_batch_2.png to /content\n"," 0% 0.00/25.5k [00:00<?, ?B/s]\n","100% 25.5k/25.5k [00:00<00:00, 25.9MB/s]\n","Downloading 94_image_batch_2.png to /content\n"," 0% 0.00/65.9k [00:00<?, ?B/s]\n","100% 65.9k/65.9k [00:00<00:00, 68.8MB/s]\n","Downloading 210_image_batch_2.png to /content\n"," 0% 0.00/54.4k [00:00<?, ?B/s]\n","100% 54.4k/54.4k [00:00<00:00, 49.7MB/s]\n","Downloading 198_image_batch_2.png to /content\n"," 0% 0.00/99.2k [00:00<?, ?B/s]\n","100% 99.2k/99.2k [00:00<00:00, 30.7MB/s]\n","Downloading 150_image.png to /content\n"," 0% 0.00/62.9k [00:00<?, ?B/s]\n","100% 62.9k/62.9k [00:00<00:00, 64.0MB/s]\n","Downloading 372_image_batch_2.png to /content\n"," 0% 0.00/132k [00:00<?, ?B/s]\n","100% 132k/132k [00:00<00:00, 38.2MB/s]\n","Downloading 101_image_batch_2.png to /content\n"," 0% 0.00/49.5k [00:00<?, ?B/s]\n","100% 49.5k/49.5k [00:00<00:00, 45.1MB/s]\n","Downloading 106_image.png to /content\n"," 0% 0.00/69.5k [00:00<?, ?B/s]\n","100% 69.5k/69.5k [00:00<00:00, 32.8MB/s]\n","Downloading 169_image.png to /content\n","100% 141k/141k [00:00<00:00, 1.41MB/s]\n","\n","Downloading 192_image_batch_2.png to /content\n"," 0% 0.00/13.9k [00:00<?, ?B/s]\n","100% 13.9k/13.9k [00:00<00:00, 11.4MB/s]\n","Downloading 655_image_batch_2.png to /content\n"," 0% 0.00/62.7k [00:00<?, ?B/s]\n","100% 62.7k/62.7k [00:00<00:00, 51.1MB/s]\n","Downloading 314_image_batch_2.png to /content\n"," 0% 0.00/34.1k [00:00<?, ?B/s]\n","100% 34.1k/34.1k [00:00<00:00, 27.8MB/s]\n","Downloading 328_image_batch_2.png to /content\n"," 0% 0.00/56.9k [00:00<?, ?B/s]\n","100% 56.9k/56.9k [00:00<00:00, 45.5MB/s]\n","Downloading 577_image_batch_2.png to /content\n"," 0% 0.00/36.4k [00:00<?, ?B/s]\n","100% 36.4k/36.4k [00:00<00:00, 67.8MB/s]\n","Downloading 335_image_batch_2.png to /content\n"," 0% 0.00/84.1k [00:00<?, ?B/s]\n","100% 84.1k/84.1k [00:00<00:00, 67.7MB/s]\n","Downloading 362_image_batch_2.png to /content\n"," 0% 0.00/36.8k [00:00<?, ?B/s]\n","100% 36.8k/36.8k [00:00<00:00, 31.7MB/s]\n","Downloading 123_image_batch_2.png to /content\n"," 0% 0.00/31.3k [00:00<?, ?B/s]\n","100% 31.3k/31.3k [00:00<00:00, 26.5MB/s]\n","Downloading Sample_submission.csv to /content\n"," 0% 0.00/4.70k [00:00<?, ?B/s]\n","100% 4.70k/4.70k [00:00<00:00, 3.82MB/s]\n","Downloading train.csv to /content\n"," 0% 0.00/225k [00:00<?, ?B/s]\n","100% 225k/225k [00:00<00:00, 49.1MB/s]\n","Downloading test.csv to /content\n"," 0% 0.00/64.2k [00:00<?, ?B/s]\n","100% 64.2k/64.2k [00:00<00:00, 56.5MB/s]\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"By2TuQ5qYf9G","executionInfo":{"status":"ok","timestamp":1618035089638,"user_tz":-330,"elapsed":735,"user":{"displayName":"Subhalingam D","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg86bQ1NVmL-U0-lCsAdMpCA_G3d9fxrw_PlOwtJg=s64","userId":"08059846138458314824"}}},"source":[""],"execution_count":4,"outputs":[]},{"cell_type":"code","metadata":{"id":"7peVMmmPZ1nK","executionInfo":{"status":"ok","timestamp":1618035160900,"user_tz":-330,"elapsed":798,"user":{"displayName":"Subhalingam D","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg86bQ1NVmL-U0-lCsAdMpCA_G3d9fxrw_PlOwtJg=s64","userId":"08059846138458314824"}}},"source":["import pandas as pd"],"execution_count":6,"outputs":[]},{"cell_type":"code","metadata":{"id":"UYTKwtgvaTNA","executionInfo":{"status":"ok","timestamp":1618035179924,"user_tz":-330,"elapsed":550,"user":{"displayName":"Subhalingam D","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg86bQ1NVmL-U0-lCsAdMpCA_G3d9fxrw_PlOwtJg=s64","userId":"08059846138458314824"}}},"source":["df = pd.read_csv(\"/content/train.csv\")"],"execution_count":7,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":204},"id":"I4dT6-eHaX6F","executionInfo":{"status":"ok","timestamp":1618035185346,"user_tz":-330,"elapsed":884,"user":{"displayName":"Subhalingam D","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg86bQ1NVmL-U0-lCsAdMpCA_G3d9fxrw_PlOwtJg=s64","userId":"08059846138458314824"}},"outputId":"125be7aa-204e-422c-9930-b4ee886b3a07"},"source":["df.head()"],"execution_count":8,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n"," .dataframe tbody tr th:only-of-type {\n"," vertical-align: middle;\n"," }\n","\n"," .dataframe tbody tr th {\n"," vertical-align: top;\n"," }\n","\n"," .dataframe thead th {\n"," text-align: right;\n"," }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: right;\">\n"," <th></th>\n"," <th>ID</th>\n"," <th>image id</th>\n"," <th>text</th>\n"," <th>label</th>\n"," <th>label_num</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <th>0</th>\n"," <td>1</td>\n"," <td>image_2455.jpg</td>\n"," <td>- It is not our fight - Are we not part of thi...</td>\n"," <td>troll</td>\n"," <td>2</td>\n"," </tr>\n"," <tr>\n"," <th>1</th>\n"," <td>2</td>\n"," <td>image_3701.jpg</td>\n"," <td>THAT'S THE DIFFERENCE BETWEEN YOU AND ME YOU...</td>\n"," <td>none</td>\n"," <td>0</td>\n"," </tr>\n"," <tr>\n"," <th>2</th>\n"," <td>3</td>\n"," <td>image_4166.png</td>\n"," <td>- WHAT DO THE TITANIC AND THE SIXTH SENSE HAVE...</td>\n"," <td>none</td>\n"," <td>0</td>\n"," </tr>\n"," <tr>\n"," <th>3</th>\n"," <td>4</td>\n"," <td>448_image_batch_2.png</td>\n"," <td>\"COME ON MAN, YOU KNOW THE THING.\\r\\nJUST ASK ...</td>\n"," <td>troll</td>\n"," <td>2</td>\n"," </tr>\n"," <tr>\n"," <th>4</th>\n"," <td>5</td>\n"," <td>653_image_batch_2.png</td>\n"," <td>\"Those who believe without reason cannot be co...</td>\n"," <td>none</td>\n"," <td>0</td>\n"," </tr>\n"," </tbody>\n","</table>\n","</div>"],"text/plain":[" ID image id ... label label_num\n","0 1 image_2455.jpg ... troll 2\n","1 2 image_3701.jpg ... none 0\n","2 3 image_4166.png ... none 0\n","3 4 448_image_batch_2.png ... troll 2\n","4 5 653_image_batch_2.png ... none 0\n","\n","[5 rows x 5 columns]"]},"metadata":{"tags":[]},"execution_count":8}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"9I7a3_P2aZII","executionInfo":{"status":"ok","timestamp":1618035866347,"user_tz":-330,"elapsed":758,"user":{"displayName":"Subhalingam D","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg86bQ1NVmL-U0-lCsAdMpCA_G3d9fxrw_PlOwtJg=s64","userId":"08059846138458314824"}},"outputId":"cf11e763-f26f-4ef9-9bac-6db1e434b59d"},"source":["!ls /content/image_4166.png\t"],"execution_count":11,"outputs":[{"output_type":"stream","text":["ls: cannot access '/content/image_4166.png': No such file or directory\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"V3uVTfxycHCp"},"source":[""],"execution_count":null,"outputs":[]}]}