I have met several submission scoring errors，and I have try to delete variable to reduce memory.I change test set to train set to check oof ,it didn't make mistakes.I check my submission.csv,it is totally meet the requirements of the competition.And the range of boxes is[0,1023].\nI hope someone could give me some advice about it.\nIf someone meet the same error with me ,maybe you can borwse links below to figure it out.\nhttps://www.kaggle.com/c/bengaliai-cv19/discussion/134618\nhttps://www.kaggle.com/c/bengaliai-cv19/discussion/134618
\n\nBelow are some tips from deep fake competition\nTips for successful submissions:
\n\nTrain your models outside of Kaggle. The training set is intentionally not available as a competition data source directly through Kaggle’s notebooks. It is not practical to train a model on Kaggle within the time constraints imposed.\nYour code must output a submission.csv that predicts on any set of test_videos.zip that it is fed as an input. We’ve designed the Public Validation/Test Sets to aid in ensuring your code is robust enough for the Private Test Set. The Public Validation Set gives an example of what you can expect your model should handle while working in an interactive notebook session. The Public Test Set allows you to test your code’s performance on a withheld test set.\nEnsure your code can be re-run on any unseen test set. Do not hard-code your submissions based on the public validation set. This will result in failure when your code runs against the public test set. You will not benefit from probing the Public Validation/Test Sets, because your code must perform honestly on the host’s fully Private Test Set.\nYou are limited to 9 hours of GPU compute time. This constraint is also imposed on the Public Test Set re-run. You should anticipate the Public Test set to be 10 times the size of the Public Validation Set and budget accordingly. The 9 hour compute constraint will be applied to the submission in Kaggle, when evaluated against the Public Test Set. So if you are able to make a successful submission that posts a score to the public leaderboard without an error, then it has met the 9 hour constraint on the Public Test Set. Review the full set of Code Requirements.\nYou are still limited to Kaggle’s global weekly per user GPU time constraints.\nDon’t make the mistake of creating multiple accounts or private sharing. Any user who submits from multiple accounts will be removed at the end of the competition, without exception. This includes entire teams where only 1 member has created a multiple account. It also includes teams who are found to have shared privately with other teams or colluded with other teams to make any submissions. It also includes teams who engaged in private sharing prior to forming as a team. We will complete these removals at the end of the competition. If you have knowledge of any teams who have committed rules violations, please submit a claim to Kaggle Compliance with your specific evidence.\nResolving Submission Errors: Below is a quick rundown of the some errors that users may receive on submission. Note that we are not in a position to share more granular details of any precise exceptions/errors, as doing so would make the competition vulnerable to error-probing by savvy participants.\n Notebook Timeout: Your submission notebook exceeded the allowed runtime cap for the competition. Review the competition's Code Requirements for details, and note that the privately held rerun test set could be orders of magnitude larger than the publicly shared validation set.\n Submission Scoring Error: Your notebook generated a submission.csv file with incorrect format. Some examples causing this are having the wrong number of rows or columns, empty values, an incorrect datatype for a value, or invalid submission values from what is expected for the privately rerun test set.\n Notebook Threw Exception: While rerunning your code on the public test set (privately held), your notebook hit an error.\n Submission CSV Not Found: Your Notebook did not output a submission.csv file. Some examples causing this are if your Notebook times out, or if it runs into an error. There is a chance this will be the error returned instead of \"Notebook Timeout\" depending on error sequencing.\n No Submit to Competition button on my notebook's output: This indicates that you have enabled something that is prohibited for the submissions on that competition. Review the competition's Code Requirements for details\n Notebook Exceeded Allowed Compute: This indicates you have violated a Code Requirement constraint during the rerun.\n Kaggle Error: A rare system error. Please try resubmitting to resolve the error and contact Kaggle Support if it persists.\nI have met several submission scoring errors，and I have try to delete variable to reduce memory.I change test set to train set to check oof ,it didn't make mistakes.I check my submission.csv,it is totally meet the requirements of the competition.And the range of boxes is[0,1023].\nI hope someone could give me some advice about it.\nIf someone meet the same error with me ,maybe you can borwse links below to figure it out.\nhttps://www.kaggle.com/c/bengaliai-cv19/discussion/134618\nhttps://www.kaggle.com/c/bengaliai-cv19/discussion/134618
\n\nBelow are some tips from deep fake competition\nTips for successful submissions:
\n\nTrain your models outside of Kaggle. The training set is intentionally not available as a competition data source directly through Kaggle’s notebooks. It is not practical to train a model on Kaggle within the time constraints imposed.\nYour code must output a submission.csv that predicts on any set of test_videos.zip that it is fed as an input. We’ve designed the Public Validation/Test Sets to aid in ensuring your code is robust enough for the Private Test Set. The Public Validation Set gives an example of what you can expect your model should handle while working in an interactive notebook session. The Public Test Set allows you to test your code’s performance on a withheld test set.\nEnsure your code can be re-run on any unseen test set. Do not hard-code your submissions based on the public validation set. This will result in failure when your code runs against the public test set. You will not benefit from probing the Public Validation/Test Sets, because your code must perform honestly on the host’s fully Private Test Set.\nYou are limited to 9 hours of GPU compute time. This constraint is also imposed on the Public Test Set re-run. You should anticipate the Public Test set to be 10 times the size of the Public Validation Set and budget accordingly. The 9 hour compute constraint will be applied to the submission in Kaggle, when evaluated against the Public Test Set. So if you are able to make a successful submission that posts a score to the public leaderboard without an error, then it has met the 9 hour constraint on the Public Test Set. Review the full set of Code Requirements.\nYou are still limited to Kaggle’s global weekly per user GPU time constraints.\nDon’t make the mistake of creating multiple accounts or private sharing. Any user who submits from multiple accounts will be removed at the end of the competition, without exception. This includes entire teams where only 1 member has created a multiple account. It also includes teams who are found to have shared privately with other teams or colluded with other teams to make any submissions. It also includes teams who engaged in private sharing prior to forming as a team. We will complete these removals at the end of the competition. If you have knowledge of any teams who have committed rules violations, please submit a claim to Kaggle Compliance with your specific evidence.\nResolving Submission Errors: Below is a quick rundown of the some errors that users may receive on submission. Note that we are not in a position to share more granular details of any precise exceptions/errors, as doing so would make the competition vulnerable to error-probing by savvy participants.\n Notebook Timeout: Your submission notebook exceeded the allowed runtime cap for the competition. Review the competition's Code Requirements for details, and note that the privately held rerun test set could be orders of magnitude larger than the publicly shared validation set.\n Submission Scoring Error: Your notebook generated a submission.csv file with incorrect format. Some examples causing this are having the wrong number of rows or columns, empty values, an incorrect datatype for a value, or invalid submission values from what is expected for the privately rerun test set.\n Notebook Threw Exception: While rerunning your code on the public test set (privately held), your notebook hit an error.\n Submission CSV Not Found: Your Notebook did not output a submission.csv file. Some examples causing this are if your Notebook times out, or if it runs into an error. There is a chance this will be the error returned instead of \"Notebook Timeout\" depending on error sequencing.\n No Submit to Competition button on my notebook's output: This indicates that you have enabled something that is prohibited for the submissions on that competition. Review the competition's Code Requirements for details\n Notebook Exceeded Allowed Compute: This indicates you have violated a Code Requirement constraint during the rerun.\n Kaggle Error: A rare system error. Please try resubmitting to resolve the error and contact Kaggle Support if it persists.\nDo you resize images / check that they are 1024^2? This was one common issue that caused submissions to crash since at least one test image is not 1024^2
", "rawMarkdown": "Do you resize images / check that they are 1024^2? This was one common issue that caused submissions to crash since at least one test image is not 1024^2", "votes": null }, { "id": "868567", "postDate": "05/31/2020 10:39:10", "content": "I change the image size to (512,512,3) during load dataset,when should I check weather they are 1024^2?
", "rawMarkdown": "I change the image size to (512,512,3) during load dataset,when should I check weather they are 1024^2?", "votes": null }, { "id": "868568", "postDate": "05/31/2020 10:41:56", "content": "When you first load them. Though, your resizing probably handles the issue I mentioned. I'm not really sure what else could be causing it so I'd just recommend looking at some of the public notebooks with working submissions and try to adapt from that.
", "rawMarkdown": "When you first load them. Though, your resizing probably handles the issue I mentioned. I'm not really sure what else could be causing it so I'd just recommend looking at some of the public notebooks with working submissions and try to adapt from that.", "votes": null }, { "id": "868596", "postDate": "05/31/2020 11:10:42", "content": "Thank you for your advice,I will try some other ways to figure it.
", "rawMarkdown": "Thank you for your advice,I will try some other ways to figure it.", "votes": null }, { "id": "873557", "postDate": "06/04/2020 09:08:38", "content": "Hi, have you solved it? @thefatcat
", "rawMarkdown": "Hi, have you solved it? @thefatcat", "votes": null }, { "id": "873564", "postDate": "06/04/2020 09:15:13", "content": "I try lots of ways,but I couldn't figure it out.Finally,I choose a notebook publishes in kernel,and I change it according to my config.Then this issue didn't appear.So if you can't solve it ,maybe you can have a try by changing other notebook according to yours.
", "rawMarkdown": "I try lots of ways,but I couldn't figure it out.Finally,I choose a notebook publishes in kernel,and I change it according to my config.Then this issue didn't appear.So if you can't solve it ,maybe you can have a try by changing other notebook according to yours.", "votes": null }, { "id": "873674", "postDate": "06/04/2020 10:54:48", "content": "Ok, thanks
", "rawMarkdown": "Ok, thanks", "votes": null } ], "comments": [ { "id": 868558, "author_name": "matthewmasters", "author_url": "", "post_date": "05/31/2020 10:30:37", "content": "Do you resize images / check that they are 1024^2? This was one common issue that caused submissions to crash since at least one test image is not 1024^2
", "votes": null, "replies": [ { "id": 868567, "author_name": "thefatcat", "author_url": "", "post_date": "05/31/2020 10:39:10", "content": "I change the image size to (512,512,3) during load dataset,when should I check weather they are 1024^2?
", "votes": null, "replies": [] }, { "id": 868568, "author_name": "matthewmasters", "author_url": "", "post_date": "05/31/2020 10:41:56", "content": "When you first load them. Though, your resizing probably handles the issue I mentioned. I'm not really sure what else could be causing it so I'd just recommend looking at some of the public notebooks with working submissions and try to adapt from that.
", "votes": null, "replies": [] }, { "id": 868596, "author_name": "thefatcat", "author_url": "", "post_date": "05/31/2020 11:10:42", "content": "Thank you for your advice,I will try some other ways to figure it.
", "votes": null, "replies": [] }, { "id": 873557, "author_name": "cswwp347724", "author_url": "", "post_date": "06/04/2020 09:08:38", "content": "Hi, have you solved it? @thefatcat
", "votes": null, "replies": [] }, { "id": 873564, "author_name": "thefatcat", "author_url": "", "post_date": "06/04/2020 09:15:13", "content": "I try lots of ways,but I couldn't figure it out.Finally,I choose a notebook publishes in kernel,and I change it according to my config.Then this issue didn't appear.So if you can't solve it ,maybe you can have a try by changing other notebook according to yours.
", "votes": null, "replies": [] }, { "id": 873674, "author_name": "cswwp347724", "author_url": "", "post_date": "06/04/2020 10:54:48", "content": "Ok, thanks
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "868551": "I have met several submission scoring errors，and I have try to delete variable to reduce memory.I change test set to train set to check oof ,it didn't make mistakes.I check my submission.csv,it is totally meet the requirements of the competition.And the range of boxes is[0,1023].\nI hope someone could give me some advice about it.\nIf someone meet the same error with me ,maybe you can borwse links below to figure it out.\nhttps://www.kaggle.com/c/bengaliai-cv19/discussion/134618\nhttps://www.kaggle.com/c/bengaliai-cv19/discussion/134618\n\nBelow are some tips from deep fake competition\nTips for successful submissions:\n\n Train your models outside of Kaggle. The training set is intentionally not available as a competition data source directly through Kaggle’s notebooks. It is not practical to train a model on Kaggle within the time constraints imposed.\n Your code must output a submission.csv that predicts on any set of test_videos.zip that it is fed as an input. We’ve designed the Public Validation/Test Sets to aid in ensuring your code is robust enough for the Private Test Set. The Public Validation Set gives an example of what you can expect your model should handle while working in an interactive notebook session. The Public Test Set allows you to test your code’s performance on a withheld test set.\n Ensure your code can be re-run on any unseen test set. Do not hard-code your submissions based on the public validation set. This will result in failure when your code runs against the public test set. You will not benefit from probing the Public Validation/Test Sets, because your code must perform honestly on the host’s fully Private Test Set.\n You are limited to 9 hours of GPU compute time. This constraint is also imposed on the Public Test Set re-run. You should anticipate the Public Test set to be 10 times the size of the Public Validation Set and budget accordingly. The 9 hour compute constraint will be applied to the submission in Kaggle, when evaluated against the Public Test Set. So if you are able to make a successful submission that posts a score to the public leaderboard without an error, then it has met the 9 hour constraint on the Public Test Set. Review the full set of Code Requirements.\n You are still limited to Kaggle’s global weekly per user GPU time constraints.\n Don’t make the mistake of creating multiple accounts or private sharing. Any user who submits from multiple accounts will be removed at the end of the competition, without exception. This includes entire teams where only 1 member has created a multiple account. It also includes teams who are found to have shared privately with other teams or colluded with other teams to make any submissions. It also includes teams who engaged in private sharing prior to forming as a team. We will complete these removals at the end of the competition. If you have knowledge of any teams who have committed rules violations, please submit a claim to Kaggle Compliance with your specific evidence.\n Resolving Submission Errors: Below is a quick rundown of the some errors that users may receive on submission. Note that we are not in a position to share more granular details of any precise exceptions/errors, as doing so would make the competition vulnerable to error-probing by savvy participants.\n Notebook Timeout: Your submission notebook exceeded the allowed runtime cap for the competition. Review the competition's Code Requirements for details, and note that the privately held rerun test set could be orders of magnitude larger than the publicly shared validation set.\n Submission Scoring Error: Your notebook generated a submission.csv file with incorrect format. Some examples causing this are having the wrong number of rows or columns, empty values, an incorrect datatype for a value, or invalid submission values from what is expected for the privately rerun test set.\n Notebook Threw Exception: While rerunning your code on the public test set (privately held), your notebook hit an error.\n Submission CSV Not Found: Your Notebook did not output a submission.csv file. Some examples causing this are if your Notebook times out, or if it runs into an error. There is a chance this will be the error returned instead of \"Notebook Timeout\" depending on error sequencing.\n No Submit to Competition button on my notebook's output: This indicates that you have enabled something that is prohibited for the submissions on that competition. Review the competition's Code Requirements for details\n Notebook Exceeded Allowed Compute: This indicates you have violated a Code Requirement constraint during the rerun.\n Kaggle Error: A rare system error. Please try resubmitting to resolve the error and contact Kaggle Support if it persists.", "868558": "Do you resize images / check that they are 1024^2? This was one common issue that caused submissions to crash since at least one test image is not 1024^2", "868567": "I change the image size to (512,512,3) during load dataset,when should I check weather they are 1024^2?", "868568": "When you first load them. Though, your resizing probably handles the issue I mentioned. I'm not really sure what else could be causing it so I'd just recommend looking at some of the public notebooks with working submissions and try to adapt from that.", "868596": "Thank you for your advice,I will try some other ways to figure it.", "873557": "Hi, have you solved it? @thefatcat", "873564": "I try lots of ways,but I couldn't figure it out.Finally,I choose a notebook publishes in kernel,and I change it according to my config.Then this issue didn't appear.So if you can't solve it ,maybe you can have a try by changing other notebook according to yours.", "873674": "Ok, thanks" }, "source": "meta" }