![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F3880742%2F66d1444118f1e0f796d2900185a4e2cf%2Fffe.png?generation=1681402215661324&alt=media\")
I am modifying the sample notebook and trying to make submissions. The changes mainly include the hyperparameter experiments. But when I submit the notebook, despite the notebook running fine, I get the above error.
\nThe logs tail as follows:
\n4599.6s 16 Wall time: 4min 51s\n4650.0s 17 /opt/conda/lib/python3.7/site-packages/traitlets/traitlets.py:2935: FutureWarning: --Exporter.preprocessors=[\"remove_papermill_header.RemovePapermillHeader\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n4650.0s 18 FutureWarning,\n4650.0s 19 [NbConvertApp] Converting notebook __notebook__.ipynb to notebook\n4673.4s 20 [NbConvertApp] Writing 332315 bytes to __notebook__.ipynb\n4685.7s 21 /opt/conda/lib/python3.7/site-packages/traitlets/traitlets.py:2935: FutureWarning: --Exporter.preprocessors=[\"nbconvert.preprocessors.ExtractOutputPreprocessor\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n4685.7s 22 FutureWarning,\n4685.7s 23 [NbConvertApp] Converting notebook __notebook__.ipynb to html\n4686.9s 24 /opt/conda/lib/python3.7/site-packages/bleach/sanitizer.py:168: NoCssSanitizerWarning: 'style' attribute specified, but css_sanitizer not set.\n4686.9s 25 category=NoCssSanitizerWarning,\n4686.9s 26 [NbConvertApp] Support files will be in __results___files/\n4686.9s 27 [NbConvertApp] Making directory __results___files\n4686.9s 28 [NbConvertApp] Making directory __results___files\n4686.9s 29 [NbConvertApp] Making directory __results___files\n4686.9s 30 [NbConvertApp] Writing 364462 bytes to __results__.html\nAlso, I suspect that the rle values written to the csv are duplicates (apparently)…
\nHas someone experienced this issue?
I am modifying the sample notebook and trying to make submissions. The changes mainly include the hyperparameter experiments. But when I submit the notebook, despite the notebook running fine, I get the above error.
\nThe logs tail as follows:
\n4599.6s 16 Wall time: 4min 51s\n4650.0s 17 /opt/conda/lib/python3.7/site-packages/traitlets/traitlets.py:2935: FutureWarning: --Exporter.preprocessors=[\"remove_papermill_header.RemovePapermillHeader\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n4650.0s 18 FutureWarning,\n4650.0s 19 [NbConvertApp] Converting notebook __notebook__.ipynb to notebook\n4673.4s 20 [NbConvertApp] Writing 332315 bytes to __notebook__.ipynb\n4685.7s 21 /opt/conda/lib/python3.7/site-packages/traitlets/traitlets.py:2935: FutureWarning: --Exporter.preprocessors=[\"nbconvert.preprocessors.ExtractOutputPreprocessor\"] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\n4685.7s 22 FutureWarning,\n4685.7s 23 [NbConvertApp] Converting notebook __notebook__.ipynb to html\n4686.9s 24 /opt/conda/lib/python3.7/site-packages/bleach/sanitizer.py:168: NoCssSanitizerWarning: 'style' attribute specified, but css_sanitizer not set.\n4686.9s 25 category=NoCssSanitizerWarning,\n4686.9s 26 [NbConvertApp] Support files will be in __results___files/\n4686.9s 27 [NbConvertApp] Making directory __results___files\n4686.9s 28 [NbConvertApp] Making directory __results___files\n4686.9s 29 [NbConvertApp] Making directory __results___files\n4686.9s 30 [NbConvertApp] Writing 364462 bytes to __results__.html\nAlso, I suspect that the rle values written to the csv are duplicates (apparently)…
\nHas someone experienced this issue?
Your RLE needs to be sorted, positive and not-duplicated. So yes, that seems to be the source of your problem. You can debug that in your training environment and fix it before submitting again.
", "rawMarkdown": "Your RLE needs to be [sorted, positive and not-duplicated](https://www.kaggle.com/competitions/vesuvius-challenge-ink-detection/overview/evaluation). So yes, that seems to be the source of your problem. You can debug that in your training environment and fix it before submitting again.", "votes": null }, { "id": "2251069", "postDate": "05/09/2023 03:43:09", "content": "Hello, have you solved this problem now? I have been also encountering this problem, how did you haddle it? I am participating in such competition for the first time, and I would greatly appreciate it if could tell me how to solve this problem. Thank you!
", "rawMarkdown": "Hello, have you solved this problem now? I have been also encountering this problem, how did you haddle it? I am participating in such competition for the first time, and I would greatly appreciate it if could tell me how to solve this problem. Thank you!", "votes": null }, { "id": "2270134", "postDate": "05/23/2023 03:19:00", "content": "Now its ur turn, did you find a way?
\ndef rle(output):\n flat_img = np.where(output > 0.5, 1, 0).astype(np.uint8)\n starts = np.array((flat_img[:-1] == 0) & (flat_img[1:] == 1))\n ends = np.array((flat_img[:-1] == 1) & (flat_img[1:] == 0))\n starts_ix = np.where(starts)[0] + 2\n ends_ix = np.where(ends)[0] + 2\n lengths = ends_ix - starts_ix\n return \" \".join(map(str, sum(zip(starts_ix, lengths), ())))\n this is the used rle which is as the one provined by thhttps://gist.github.com/janpaul123/ca3477c1db6de4346affca37e0e3d5b0is
This page written by host actually directs us to which RLE implementation to use:
\nhttps://www.kaggle.com/competitions/vesuvius-challenge-ink-detection/overview/evaluation
Your RLE needs to be sorted, positive and not-duplicated. So yes, that seems to be the source of your problem. You can debug that in your training environment and fix it before submitting again.
", "votes": null, "replies": [] }, { "id": 2251069, "author_name": "luojohn", "author_url": "", "post_date": "05/09/2023 03:43:09", "content": "Hello, have you solved this problem now? I have been also encountering this problem, how did you haddle it? I am participating in such competition for the first time, and I would greatly appreciate it if could tell me how to solve this problem. Thank you!
", "votes": null, "replies": [ { "id": 2270134, "author_name": "salaheldinelnabarawy", "author_url": "", "post_date": "05/23/2023 03:19:00", "content": "Now its ur turn, did you find a way?
\ndef rle(output):\n flat_img = np.where(output > 0.5, 1, 0).astype(np.uint8)\n starts = np.array((flat_img[:-1] == 0) & (flat_img[1:] == 1))\n ends = np.array((flat_img[:-1] == 1) & (flat_img[1:] == 0))\n starts_ix = np.where(starts)[0] + 2\n ends_ix = np.where(ends)[0] + 2\n lengths = ends_ix - starts_ix\n return \" \".join(map(str, sum(zip(starts_ix, lengths), ())))\n this is the used rle which is as the one provined by thhttps://gist.github.com/janpaul123/ca3477c1db6de4346affca37e0e3d5b0is
This page written by host actually directs us to which RLE implementation to use:
\nhttps://www.kaggle.com/competitions/vesuvius-challenge-ink-detection/overview/evaluation