![\"Reminder\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5540301%2Facfa0ae8a7bb5e7fa7f2cfcdcdf756e1%2FcountdownFinal-01.jpg?generation=1691079193357462&alt=media\")
After almost one and a half months, Phase 1 of DL Sprint 2.0 is finally coming to an end on the 5th of August (11.59 pm, GMT +06). Congratulations from the organizers for your journey with Deep Learning so far. However, the final submission of Phase 1 remains due yet. Please go through this discussion topic below carefully to learn how to submit both your predictions and solutions.
\nThe current Kaggle competition will end on 5th August at 11.59 pm. Participants are advised to submit their final predictions on Kaggle even before 5th August to avoid late submissions. This will mark the end of Phase 1 of our competition.
\nAll participants will have to submit their solutions to dlsprint2.0@buetcsefest2023.com. Check the Submission Format section below for more details. This solution submission deadline is on 6th August (11.59 pm, GMT +06). Participants are advised to submit their solutions even before 6th August to avoid any issues. Do note that late submission will result in immediate disqualification. Furthermore, if you do not submit your solution in the described format, you will not be eligible for any Phase 2 prize (excluding the Best Notebooks Prize). You can always contact us if you have any questions regarding the format.
\nWe will run your notebooks on the given test dataset but calculate the mAP scores as well to generate a new leaderboard. Please take a look at the Overview section for the detailed scoring criteria and marks distribution. The top 15 teams from this hidden dataset leaderboard will be invited to present their solutions at the Department of CSE, BUET premises on 11th August 2023. The time and location will be announced soon. The promoted teams must deliver a presentation before a panel of our judges. The prize-giving ceremony will also be held on the same day. Do note that the onsite presentation from at least one member of the team is mandatory to be eligible for the prizes.
\nAs a part of the presentation before the judges, the top 15 teams will also be asked to submit a simple 4-page paper based on the IEEE Conference paper template before the Phase 2 round and the paper should contain Introduction, Methodology, Results & Discussions, and Conclusion sections. This write-up is needed for a better understanding of your solution and thought process.
\nInclude the following information in a .pdf / .docx file and send it to dlsprint2.0@buetcsefest2023.com. Mention your Kaggle team name in the email subject.
\nTeam Name (the one on the Kaggle leaderboard)
Team Members
\na. Name, Contact Number, Email Address, Institution, T-shirt size (M/L/XL/2XL/3XL).
\nb. Specify which members are undergraduate students (their student ID + institution)
\nc. Specify which one of the members is the leader
Does your team qualify as a BUET rising team? (Does a clear majority of your team belong to the 19/20/21 batch from BUET)
Public Github repository with training and inference codes (If any). Please update the README section with appropriate instructions to run the code.
Kaggle Notebooks Links (Please ensure they can be executed correctly. Notebook submission is mandatory):
\na. Training notebooks
\nb. Test/Inference notebooks. Additionally, include your trained model weights in this notebook and ensure it is running correctly. Test/Inference notebook must run on Kaggle Notebooks
\nc. Link to your trained model weights
\nd. Share your notebooks and relevant datasets to these ids: @sameen53, @salmankhondker, @nazmuddhohaansary, @reasat (Be sure to give EDITOR ACCESS)
If you have any questions you can comment on this discussion or reach out to us at dlsprint2.0@buetcsefest2023.com.
\n
After almost one and a half months, Phase 1 of DL Sprint 2.0 is finally coming to an end on the 5th of August (11.59 pm, GMT +06). Congratulations from the organizers for your journey with Deep Learning so far. However, the final submission of Phase 1 remains due yet. Please go through this discussion topic below carefully to learn how to submit both your predictions and solutions.
\nThe current Kaggle competition will end on 5th August at 11.59 pm. Participants are advised to submit their final predictions on Kaggle even before 5th August to avoid late submissions. This will mark the end of Phase 1 of our competition.
\nAll participants will have to submit their solutions to dlsprint2.0@buetcsefest2023.com. Check the Submission Format section below for more details. This solution submission deadline is on 6th August (11.59 pm, GMT +06). Participants are advised to submit their solutions even before 6th August to avoid any issues. Do note that late submission will result in immediate disqualification. Furthermore, if you do not submit your solution in the described format, you will not be eligible for any Phase 2 prize (excluding the Best Notebooks Prize). You can always contact us if you have any questions regarding the format.
\nWe will run your notebooks on the given test dataset but calculate the mAP scores as well to generate a new leaderboard. Please take a look at the Overview section for the detailed scoring criteria and marks distribution. The top 15 teams from this hidden dataset leaderboard will be invited to present their solutions at the Department of CSE, BUET premises on 11th August 2023. The time and location will be announced soon. The promoted teams must deliver a presentation before a panel of our judges. The prize-giving ceremony will also be held on the same day. Do note that the onsite presentation from at least one member of the team is mandatory to be eligible for the prizes.
\nAs a part of the presentation before the judges, the top 15 teams will also be asked to submit a simple 4-page paper based on the IEEE Conference paper template before the Phase 2 round and the paper should contain Introduction, Methodology, Results & Discussions, and Conclusion sections. This write-up is needed for a better understanding of your solution and thought process.
\nInclude the following information in a .pdf / .docx file and send it to dlsprint2.0@buetcsefest2023.com. Mention your Kaggle team name in the email subject.
\nTeam Name (the one on the Kaggle leaderboard)
Team Members
\na. Name, Contact Number, Email Address, Institution, T-shirt size (M/L/XL/2XL/3XL).
\nb. Specify which members are undergraduate students (their student ID + institution)
\nc. Specify which one of the members is the leader
Does your team qualify as a BUET rising team? (Does a clear majority of your team belong to the 19/20/21 batch from BUET)
Public Github repository with training and inference codes (If any). Please update the README section with appropriate instructions to run the code.
Kaggle Notebooks Links (Please ensure they can be executed correctly. Notebook submission is mandatory):
\na. Training notebooks
\nb. Test/Inference notebooks. Additionally, include your trained model weights in this notebook and ensure it is running correctly. Test/Inference notebook must run on Kaggle Notebooks
\nc. Link to your trained model weights
\nd. Share your notebooks and relevant datasets to these ids: @sameen53, @salmankhondker, @nazmuddhohaansary, @reasat (Be sure to give EDITOR ACCESS)
If you have any questions you can comment on this discussion or reach out to us at dlsprint2.0@buetcsefest2023.com.
\n
When the private leaderboard will be released?
", "rawMarkdown": "When the private leaderboard will be released?", "votes": 1, "replies": [ { "id": 2379148, "postDate": "2023-08-08T03:09:31.903Z", "content": "11 August
", "rawMarkdown": "11 August ", "votes": 1 } ] }, { "id": 2376599, "postDate": "2023-08-06T13:48:45.997Z", "content": "@sameen53 In the Solution inference notebook should detectron2 and other libraries have to be installed offline? Can we use pip install and other libraries?
", "rawMarkdown": "@sameen53 In the Solution inference notebook should detectron2 and other libraries have to be installed offline? Can we use pip install and other libraries?", "replies": [ { "id": 2376628, "postDate": "2023-08-06T14:19:33.693Z", "content": "You can install online. The notebook doesn't have to be offline.
", "rawMarkdown": "You can install online. The notebook doesn't have to be offline.", "replies": [ { "id": 2376661, "postDate": "2023-08-06T15:01:01.630Z", "content": "Thanks for the clarification.
", "rawMarkdown": "Thanks for the clarification." } ] } ] }, { "id": 2372434, "postDate": "2023-08-03T17:06:18.720Z", "content": "Quick correction, there isn't another hidden dataset. We will run your notebooks on the given test dataset but calculate the mAP scores as well.
", "rawMarkdown": "Quick correction, there isn't another hidden dataset. We will run your notebooks on the given test dataset but calculate the mAP scores as well.", "replies": [ { "id": 2379180, "postDate": "2023-08-08T04:10:24.967Z", "content": "@sameen53 Could you please clarify what it means to have a 35% weight on the private Dice score? Does this imply that you will evaluate our notebooks for both Dice and MAP scores right? Means the scoring criteria will be same as overview section? Additionally, if the private leaderboard is scheduled to be released on August 11th, can we expect the top 15 participants to be notified via email?
\nThanks
", "rawMarkdown": "@sameen53 Could you please clarify what it means to have a 35% weight on the private Dice score? Does this imply that you will evaluate our notebooks for both Dice and MAP scores right? Means the scoring criteria will be same as overview section? Additionally, if the private leaderboard is scheduled to be released on August 11th, can we expect the top 15 participants to be notified via email?\n\nThanks", "replies": [ { "id": 2380071, "postDate": "2023-08-08T12:04:46.057Z", "content": "Basically the score on Kaggle will account for 50% of the total. The private leaderboard (which is 70% of the test set) accounts for 35% within this 50%. We are going to run and submit your notebooks and make sure that your scores on the leaderboards are legit. So we expect the performance of your notebooks to match your leaderboard scores. And yes, we will notify the top 15 via email.
", "rawMarkdown": "Basically the score on Kaggle will account for 50% of the total. The private leaderboard (which is 70% of the test set) accounts for 35% within this 50%. We are going to run and submit your notebooks and make sure that your scores on the leaderboards are legit. So we expect the performance of your notebooks to match your leaderboard scores. And yes, we will notify the top 15 via email." }, { "id": 2380167, "postDate": "2023-08-08T12:51:50.020Z", "content": "Thanks for the clarification
", "rawMarkdown": "Thanks for the clarification " }, { "id": 2382101, "postDate": "2023-08-09T15:15:12.223Z", "content": "The notebook we submitted might underperform our best submission by 0.0004 to 0.00015, as we didn't submit the best scoring notebook due to it being very messy. Is that going to cause any issue?
", "rawMarkdown": "The notebook we submitted might underperform our best submission by 0.0004 to 0.00015, as we didn't submit the best scoring notebook due to it being very messy. Is that going to cause any issue?" }, { "id": 2382137, "postDate": "2023-08-09T15:35:03.457Z", "content": "Since multiple teams made the same error, we will neither disqualify your team nor invalidate your leaderboard submissions. We will take consider your leaderboard scores. But should you be a winning team, you absolutely must make public the notebook with the leaderboard score no matter how messy it is.
", "rawMarkdown": "Since multiple teams made the same error, we will neither disqualify your team nor invalidate your leaderboard submissions. We will take consider your leaderboard scores. But should you be a winning team, you **absolutely must make public** the notebook with the leaderboard score no matter how messy it is. " } ] } ] }, { "id": 2377436, "postDate": "2023-08-07T06:35:05.617Z", "rawMarkdown": "", "isDeleted": true } ], "comments": [ { "id": 2376846, "author_name": "Asib Rahman", "author_url": "", "post_date": "2023-08-06T17:39:27.367000", "content": "When the private leaderboard will be released?
", "votes": 1, "replies": [ { "id": 2379148, "author_name": "Sameen53", "author_url": "", "post_date": "2023-08-08T03:09:31.903000", "content": "11 August
", "votes": 1, "replies": [] } ] }, { "id": 2376599, "author_name": "Mirza Nihal Baig", "author_url": "", "post_date": "2023-08-06T13:48:45.997000", "content": "@sameen53 In the Solution inference notebook should detectron2 and other libraries have to be installed offline? Can we use pip install and other libraries?
", "votes": 0, "replies": [ { "id": 2376628, "author_name": "Sameen53", "author_url": "", "post_date": "2023-08-06T14:19:33.693000", "content": "You can install online. The notebook doesn't have to be offline.
", "votes": 0, "replies": [ { "id": 2376661, "author_name": "Mirza Nihal Baig", "author_url": "", "post_date": "2023-08-06T15:01:01.630000", "content": "Thanks for the clarification.
", "votes": 0, "replies": [] } ] } ] }, { "id": 2372434, "author_name": "Sameen53", "author_url": "", "post_date": "2023-08-03T17:06:18.720000", "content": "Quick correction, there isn't another hidden dataset. We will run your notebooks on the given test dataset but calculate the mAP scores as well.
", "votes": 0, "replies": [ { "id": 2379180, "author_name": "RadAlienware", "author_url": "", "post_date": "2023-08-08T04:10:24.967000", "content": "@sameen53 Could you please clarify what it means to have a 35% weight on the private Dice score? Does this imply that you will evaluate our notebooks for both Dice and MAP scores right? Means the scoring criteria will be same as overview section? Additionally, if the private leaderboard is scheduled to be released on August 11th, can we expect the top 15 participants to be notified via email?
\nThanks
", "votes": 0, "replies": [ { "id": 2380071, "author_name": "Sameen53", "author_url": "", "post_date": "2023-08-08T12:04:46.057000", "content": "Basically the score on Kaggle will account for 50% of the total. The private leaderboard (which is 70% of the test set) accounts for 35% within this 50%. We are going to run and submit your notebooks and make sure that your scores on the leaderboards are legit. So we expect the performance of your notebooks to match your leaderboard scores. And yes, we will notify the top 15 via email.
", "votes": 0, "replies": [] }, { "id": 2380167, "author_name": "RadAlienware", "author_url": "", "post_date": "2023-08-08T12:51:50.020000", "content": "Thanks for the clarification
", "votes": 0, "replies": [] }, { "id": 2382101, "author_name": "saad noor", "author_url": "", "post_date": "2023-08-09T15:15:12.223000", "content": "The notebook we submitted might underperform our best submission by 0.0004 to 0.00015, as we didn't submit the best scoring notebook due to it being very messy. Is that going to cause any issue?
", "votes": 0, "replies": [] }, { "id": 2382137, "author_name": "Sameen53", "author_url": "", "post_date": "2023-08-09T15:35:03.457000", "content": "Since multiple teams made the same error, we will neither disqualify your team nor invalidate your leaderboard submissions. We will take consider your leaderboard scores. But should you be a winning team, you absolutely must make public the notebook with the leaderboard score no matter how messy it is.
", "votes": 0, "replies": [] } ] } ] }, { "id": 2377436, "author_name": "", "author_url": "", "post_date": "2023-08-07T06:35:05.617000", "content": "", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "2372370": "After almost one and a half months, Phase 1 of DL Sprint 2.0 is finally coming to an end on the **5th of August (11.59 pm, GMT +06)**. Congratulations from the organizers for your journey with Deep Learning so far. However, the final submission of Phase 1 remains due yet. Please go through this discussion topic below carefully to learn how to submit both your predictions and solutions. \n\n# Phase 1 Kaggle Submission\n\nThe current Kaggle competition will end on 5th August at 11.59 pm. Participants are advised to submit their final predictions on Kaggle even before 5th August to avoid late submissions. This will mark the end of Phase 1 of our competition.\n\nAll participants will have to submit their solutions to **dlsprint2.0@buetcsefest2023.com**. Check the **Submission Format** section below for more details. This solution submission deadline is on **6th August (11.59 pm, GMT +06)**. Participants are advised to submit their solutions even before 6th August to avoid any issues. Do note that **late submission will result in immediate disqualification**. Furthermore, if you do not submit your solution in the described format, you will not be eligible for any Phase 2 prize (excluding the Best Notebooks Prize). You can always contact us if you have any questions regarding the format.\n\n# Phase 2 Onsite Event\n\nWe will run your notebooks on the given test dataset but calculate the **mAP scores** as well to generate a new leaderboard. Please take a look at the **Overview** section for the detailed scoring criteria and marks distribution. The top 15 teams from this hidden dataset leaderboard will be invited to present their solutions at the **Department of CSE, BUET premises on 11th August 2023**. The time and location will be announced soon. The promoted teams must deliver a presentation before a panel of our judges. The prize-giving ceremony will also be held on the same day. Do note that **the onsite presentation from at least one member of the team is mandatory to be eligible for the prizes**.\n\nAs a part of the presentation before the judges, **the top 15 teams will also be asked to submit a simple 4-page paper** based on the IEEE Conference paper template before the Phase 2 round and the paper should contain Introduction, Methodology, Results & Discussions, and Conclusion sections. This write-up is needed for a better understanding of your solution and thought process.\n\n# Submission Format\n\nInclude the following information in a .pdf / .docx file and send it to **dlsprint2.0@buetcsefest2023.com**. Mention your Kaggle team name in the email subject.\n\n1. Team Name (the one on the Kaggle leaderboard)\n\n2. Team Members\n a. Name, Contact Number, Email Address, Institution, T-shirt size (M/L/XL/2XL/3XL).\n b. Specify which members are undergraduate students (their student ID + institution)\n c. Specify which one of the members is the leader\n\n3. Does your team qualify as a BUET rising team? (Does a clear majority of your team belong to the 19/20/21 batch from BUET)\n\n4. Public Github repository with training and inference codes (If any). Please update the README section with appropriate instructions to run the code.\n\n5. Kaggle Notebooks Links (Please ensure they can be executed correctly. Notebook submission is mandatory):\n a. Training notebooks\n b. Test/Inference notebooks. Additionally, include your trained model weights in this notebook and ensure it is running correctly. Test/Inference notebook must run on Kaggle Notebooks\n c. Link to your trained model weights\n d. Share your notebooks and relevant datasets to these ids: @sameen53, @salmankhondker, @nazmuddhohaansary, @reasat (Be sure to give EDITOR ACCESS)\n\nIf you have any questions you can comment on this discussion or reach out to us at **dlsprint2.0@buetcsefest2023.com**.\n\n", "2376846": "When the private leaderboard will be released?", "2376599": "@sameen53 In the Solution inference notebook should detectron2 and other libraries have to be installed offline? Can we use pip install and other libraries?", "2372434": "Quick correction, there isn't another hidden dataset. We will run your notebooks on the given test dataset but calculate the mAP scores as well.", "2377436": "" } }