Hey Kagglers,
\n\nThe Bengali.AI Grapheme Translation competition has closed! We hope you were able to learn a lot, and use your machine learning skills on this interesting problem. This year we had 2,659 participants on over 2000 teams. We had 31,000 submissions from 77 countries! For 446 users (including 16 in the top 100!), this was their first competition. We also had 6 new Masters and 1 new Grandmaster (Congrats Dieter!) at the conclusion of this competition. Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking!
\n\nWe were excited to work with all the folks at Bengali AI like Tahsin, Imtiaz, and Sushmit. We're glad they choose Kaggle to be a platform to bring these types of research problems to the broader data science community. They've been a pleasure to work with, and we hope to work with them again in the future.
\n\nWe're also continually pleased to see how Kaggle Competitions serve as a great medium and vehicle through which the greater data science community can learn and develop their machine learning abilities and skills. Beginners and experts can come together to start, grow, and succeed. Further, in this competition, many can use their machine learning skills to help a great cause like this one.
\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, please contact compliance. Please fill in all the fields honestly.
\n\nThe top potential winning teams have been contacted via email to provide their winning solutions for host review. If you would like to self-nominate your team as being a top student team from Bangladesh, please see this post. Should we need to move down the leaderboard for any reason, we will do so and continue to make contact with subsequent teams.
\n\nYou should have already seen your points and medals awarded, however it may take a few hours to propagate through if yours are still missing.
\n\nIn the meantime, I've created this thread to be a curated list of your work. As you post your solutions, top kernels, and general discussion posts, I'll update this thread to keep track. If you write a paper, thesis, or present at a conference, and would like to share your work, please let us know so we can share with the Kaggle community! Additionally, if you performed any data manipulation, or used a new technique in this competition that you'd like to share to further the industry, please let us know and we'll post it here! That way, should you be looking for takeaways in the future, or if you've just now stumbled across the competition, you have a place to see what surfaced from the work performed.
\n\nHappy Modeling!\nKaggle Team
\n\nHey Kagglers,
\n\nThe Bengali.AI Grapheme Translation competition has closed! We hope you were able to learn a lot, and use your machine learning skills on this interesting problem. This year we had 2,659 participants on over 2000 teams. We had 31,000 submissions from 77 countries! For 446 users (including 16 in the top 100!), this was their first competition. We also had 6 new Masters and 1 new Grandmaster (Congrats Dieter!) at the conclusion of this competition. Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking!
\n\nWe were excited to work with all the folks at Bengali AI like Tahsin, Imtiaz, and Sushmit. We're glad they choose Kaggle to be a platform to bring these types of research problems to the broader data science community. They've been a pleasure to work with, and we hope to work with them again in the future.
\n\nWe're also continually pleased to see how Kaggle Competitions serve as a great medium and vehicle through which the greater data science community can learn and develop their machine learning abilities and skills. Beginners and experts can come together to start, grow, and succeed. Further, in this competition, many can use their machine learning skills to help a great cause like this one.
\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, please contact compliance. Please fill in all the fields honestly.
\n\nThe top potential winning teams have been contacted via email to provide their winning solutions for host review. If you would like to self-nominate your team as being a top student team from Bangladesh, please see this post. Should we need to move down the leaderboard for any reason, we will do so and continue to make contact with subsequent teams.
\n\nYou should have already seen your points and medals awarded, however it may take a few hours to propagate through if yours are still missing.
\n\nIn the meantime, I've created this thread to be a curated list of your work. As you post your solutions, top kernels, and general discussion posts, I'll update this thread to keep track. If you write a paper, thesis, or present at a conference, and would like to share your work, please let us know so we can share with the Kaggle community! Additionally, if you performed any data manipulation, or used a new technique in this competition that you'd like to share to further the industry, please let us know and we'll post it here! That way, should you be looking for takeaways in the future, or if you've just now stumbled across the competition, you have a place to see what surfaced from the work performed.
\n\nHappy Modeling!\nKaggle Team
\n\nHi everyone,
\n\nOne more follow up here - congrats to @inhoii on their top AutoML submission! Inhoii has been contacted with the Kaggle swag instructions.
\n\nThanks!
", "rawMarkdown": "Hi everyone,\n\nOne more follow up here - congrats to @inhoii on their top AutoML submission! Inhoii has been contacted with the Kaggle swag instructions.\n\nThanks!", "votes": 2 }, { "id": 777594, "postDate": "2020-03-17T19:58:21.353Z", "content": "@addisonhoward Thank you for an interesting competiton. I wonder how winning teams results compare to sota in this field and to Bengali.Ai own results ?
", "rawMarkdown": "@addisonhoward Thank you for an interesting competiton. I wonder how winning teams results compare to sota in this field and to Bengali.Ai own results ? ", "votes": 2 }, { "id": 777578, "postDate": "2020-03-17T19:34:32.937Z", "content": "@addisonhoward Congratulations to all winners. Missed participating in this challenge. Going through the posts I found it very overwhleming as I have never taken part in image competition before. Thanks for arranging the best solutions.
", "rawMarkdown": "@addisonhoward Congratulations to all winners. Missed participating in this challenge. Going through the posts I found it very overwhleming as I have never taken part in image competition before. Thanks for arranging the best solutions. " }, { "id": 778327, "postDate": "2020-03-18T10:50:57.730Z", "rawMarkdown": "", "isDeleted": true }, { "id": 780343, "postDate": "2020-03-20T07:09:16.600Z", "content": "thanks for the competition
", "rawMarkdown": "thanks for the competition" } ], "comments": [ { "id": 796530, "author_name": "Addison Howard", "author_url": "", "post_date": "2020-04-03T17:02:34.497000", "content": "Hi everyone,
\n\nOne more follow up here - congrats to @inhoii on their top AutoML submission! Inhoii has been contacted with the Kaggle swag instructions.
\n\nThanks!
", "votes": 2, "replies": [] }, { "id": 777594, "author_name": "Eek The Cat", "author_url": "", "post_date": "2020-03-17T19:58:21.353000", "content": "@addisonhoward Thank you for an interesting competiton. I wonder how winning teams results compare to sota in this field and to Bengali.Ai own results ?
", "votes": 2, "replies": [] }, { "id": 777578, "author_name": "Tensor Girl", "author_url": "", "post_date": "2020-03-17T19:34:32.937000", "content": "@addisonhoward Congratulations to all winners. Missed participating in this challenge. Going through the posts I found it very overwhleming as I have never taken part in image competition before. Thanks for arranging the best solutions.
", "votes": 0, "replies": [] }, { "id": 778327, "author_name": "", "author_url": "", "post_date": "2020-03-18T10:50:57.730000", "content": "", "votes": 0, "replies": [] }, { "id": 780343, "author_name": "Mihir Sharma", "author_url": "", "post_date": "2020-03-20T07:09:16.600000", "content": "thanks for the competition
", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "777573": "Hey Kagglers,\n\nThe Bengali.AI Grapheme Translation competition has closed! We hope you were able to learn a lot, and use your machine learning skills on this interesting problem. This year we had 2,659 participants on over 2000 teams. We had 31,000 submissions from 77 countries! For 446 users (including 16 in the top 100!), this was their first competition. We also had 6 new Masters and 1 new Grandmaster (Congrats Dieter!) at the conclusion of this competition. Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking! \n\nWe were excited to work with all the folks at Bengali AI like [Tahsin](https://www.kaggle.com/reasat), [Imtiaz](https://www.kaggle.com/imtiazprio), and [Sushmit](https://www.kaggle.com/sushmit0109). We're glad they choose Kaggle to be a platform to bring these types of research problems to the broader data science community. They've been a pleasure to work with, and we hope to work with them again in the future. \n\nWe're also continually pleased to see how Kaggle Competitions serve as a great medium and vehicle through which the greater data science community can learn and develop their machine learning abilities and skills. Beginners and experts can come together to start, grow, and succeed. Further, in this competition, many can use their machine learning skills to help a great cause like this one.\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, please contact [compliance](https://www.kaggle.com/compliance). Please fill in all the fields honestly.\n\nThe top potential winning teams have been contacted via email to provide their winning solutions for host review. If you would like to self-nominate your team as being a top student team from Bangladesh, please see [this post](https://www.kaggle.com/c/bengaliai-cv19/discussion/136762). Should we need to move down the leaderboard for any reason, we will do so and continue to make contact with subsequent teams.\n\nYou should have already seen your points and medals awarded, however it may take a few hours to propagate through if yours are still missing.\n\nIn the meantime, I've created this thread to be a curated list of your work. As you post your solutions, top kernels, and general discussion posts, I'll update this thread to keep track. If you write a paper, thesis, or present at a conference, and would like to share your work, please let us know so we can share with the Kaggle community! Additionally, if you performed any data manipulation, or used a new technique in this competition that you'd like to share to further the industry, please let us know and we'll post it here! That way, should you be looking for takeaways in the future, or if you've just now stumbled across the competition, you have a place to see what surfaced from the work performed.\n\nHappy Modeling!\nKaggle Team\n\n###Top Solutions\n* [1st Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/135984) \n* [2nd Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/135966)\n* [3rd Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/135982)\n* [4th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/136982)\n* [5th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/136129)\n* [6th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/136011)\n* [7th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/135960)\n* [8th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/135990)\n* [9th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/135985)\n* [10th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/136815)\n* [12th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/135998)\n* [13th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/136116)\n* [14th Place Solution part a](https://www.kaggle.com/c/bengaliai-cv19/discussion/136021)\n* [14th Place Solution part b](https://www.kaggle.com/c/bengaliai-cv19/discussion/136791)\n* [21st Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/136056)\n* [24th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/136064)\n* [38th Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/136075)\n* [41st Place Solution](https://www.kaggle.com/c/bengaliai-cv19/discussion/136084)\n\n###Top Notebooks\n- [Starter EDA Multi Output CNN](https://www.kaggle.com/kaushal2896/bengali-graphemes-starter-eda-multi-output-cnn)\n- [Image Preprocessing](https://www.kaggle.com/iafoss/image-preprocessing-128x128)\n- [Bengali SEResNeXt Training with PyTorch](https://www.kaggle.com/corochann/bengali-seresnext-training-with-pytorch)\n- [Grapheme fast.aI Starter](https://www.kaggle.com/iafoss/grapheme-fast-ai-starter-lb-0-964)\n- [Gridmask](https://www.kaggle.com/haqishen/gridmask)\n- [Keras EfficientNet B3 training + Inference](https://www.kaggle.com/rsmits/keras-efficientnet-b3-training-inference)\n\n\n###High Scoring Kernels\n- [0.9854](https://www.kaggle.com/haqishen/bengali-predict-with-seen-unseen-models)\n- [0.9777](https://www.kaggle.com/sachingarg1998/3-multi-model-inference-tpu)\n- [0.9754](https://www.kaggle.com/vagrawal/ensemble-efficientnet-b3-densenet161)\n\n###Other Top Discussions\n- [Worth Seeing Posts and Notebooks](https://www.kaggle.com/c/bengaliai-cv19/discussion/127976)\n- [Pytorch Starter Kit](https://www.kaggle.com/c/bengaliai-cv19/discussion/123757)\n- [Best Single Model](https://www.kaggle.com/c/bengaliai-cv19/discussion/123198)\n- [Mixup/cutmix is all you need](https://www.kaggle.com/c/bengaliai-cv19/discussion/126504)\n- [Inference within 20 minutes](https://www.kaggle.com/c/bengaliai-cv19/discussion/122993)\n- [Bengali on TPUs](https://www.kaggle.com/c/bengaliai-cv19/discussion/134161)", "796530": "Hi everyone,\n\nOne more follow up here - congrats to @inhoii on their top AutoML submission! Inhoii has been contacted with the Kaggle swag instructions.\n\nThanks!", "777594": "@addisonhoward Thank you for an interesting competiton. I wonder how winning teams results compare to sota in this field and to Bengali.Ai own results ? ", "777578": "@addisonhoward Congratulations to all winners. Missed participating in this challenge. Going through the posts I found it very overwhleming as I have never taken part in image competition before. Thanks for arranging the best solutions. ", "778327": "", "780343": "thanks for the competition" } }