![\"Upgrade](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F42168%2Fc11d113e60f8399e0454d1865af0a65e%2FScreenshot%202023-03-24%20at%2012.04.06%20PM.png?generation=1679673879863640&alt=media\")
I looked through all the rules but I can't see an answer.
\nI got an upsell to \"Upgrade to Google Cloud AI Platform Notebooks\" when I ran out of memory.
\nI'm happy to do that, but is it allowed?
\n
I looked through all the rules but I can't see an answer.
\nI got an upsell to \"Upgrade to Google Cloud AI Platform Notebooks\" when I ran out of memory.
\nI'm happy to do that, but is it allowed?
\n
Actual submissions still need to fit in Kaggle notebooks (https://www.kaggle.com/competitions/vesuvius-challenge-ink-detection/overview/code-requirements), but for exploratory work anything goes.
", "rawMarkdown": "Actual submissions still need to fit in Kaggle notebooks (https://www.kaggle.com/competitions/vesuvius-challenge-ink-detection/overview/code-requirements), but for exploratory work anything goes.", "votes": null }, { "id": "2195419", "postDate": "03/24/2023 16:18:12", "content": "Got it—thanks!
", "rawMarkdown": "Got it—thanks!", "votes": null }, { "id": "2195420", "postDate": "03/24/2023 16:20:34", "content": "Yeah I'd looked at that page (nit: the close paren got pulled into your link URL) but it wasn't clear that \"Notebooks\" meant \"Kaggle Notebooks\" and not \"any Notebooks.\"
", "rawMarkdown": "Yeah I'd looked at that page (nit: the close paren got pulled into your link URL) but it wasn't clear that \"Notebooks\" meant \"Kaggle Notebooks\" and not \"any Notebooks.\"", "votes": null }, { "id": "2195426", "postDate": "03/24/2023 16:24:53", "content": "Another question: so the notebook that is executed on the real test fragments must be in a Kaggle Notebook, but the training can be done on another system and the model loaded in through a dataset (provided that you guys can reproduce that without too much hassle and it fulfills the license requirements, etc.)? Or everything needs to be done from the Kaggle Notebook?
", "rawMarkdown": "Another question: so the notebook that is executed on the real test fragments must be in a Kaggle Notebook, but the training can be done on another system and the model loaded in through a dataset (provided that you guys can reproduce that without too much hassle and it fulfills the license requirements, etc.)? Or everything needs to be done from the Kaggle Notebook?", "votes": null }, { "id": "2195449", "postDate": "03/24/2023 16:41:49", "content": "You can use whatever system you want for offline data processing (eg training), though we have to be able to reproduce your methods if you end up winning. (In that case we'd contact you and ask how we can run the offline data processing ourselves.)
", "rawMarkdown": "You can use whatever system you want for offline data processing (eg training), though we have to be able to reproduce your methods if you end up winning. (In that case we'd contact you and ask how we can run the offline data processing ourselves.)", "votes": null }, { "id": "2195478", "postDate": "03/24/2023 17:07:50", "content": "Thanks JP!
", "rawMarkdown": "Thanks JP!", "votes": null }, { "id": "2292670", "postDate": "06/08/2023 14:46:06", "content": "When I click upgrade to google cloud notebook, there's a cell that says \"Run this to get the data imported\", but when I run it I get a permission denied error: PermissionError: [Errno 13] Permission denied: '/home/kaggle' on line 18. Any ideas how to fix?
", "rawMarkdown": "When I click upgrade to google cloud notebook, there's a cell that says \"Run this to get the data imported\", but when I run it I get a permission denied error: PermissionError: [Errno 13] Permission denied: '/home/kaggle' on line 18. Any ideas how to fix?", "votes": null } ], "comments": [ { "id": 2195417, "author_name": "wcukierski", "author_url": "", "post_date": "03/24/2023 16:15:50", "content": "Actual submissions still need to fit in Kaggle notebooks (https://www.kaggle.com/competitions/vesuvius-challenge-ink-detection/overview/code-requirements), but for exploratory work anything goes.
", "votes": null, "replies": [ { "id": 2195419, "author_name": "costella", "author_url": "", "post_date": "03/24/2023 16:18:12", "content": "Got it—thanks!
", "votes": null, "replies": [ { "id": 2195420, "author_name": "costella", "author_url": "", "post_date": "03/24/2023 16:20:34", "content": "Yeah I'd looked at that page (nit: the close paren got pulled into your link URL) but it wasn't clear that \"Notebooks\" meant \"Kaggle Notebooks\" and not \"any Notebooks.\"
", "votes": null, "replies": [] } ] }, { "id": 2195426, "author_name": "costella", "author_url": "", "post_date": "03/24/2023 16:24:53", "content": "Another question: so the notebook that is executed on the real test fragments must be in a Kaggle Notebook, but the training can be done on another system and the model loaded in through a dataset (provided that you guys can reproduce that without too much hassle and it fulfills the license requirements, etc.)? Or everything needs to be done from the Kaggle Notebook?
", "votes": null, "replies": [ { "id": 2195449, "author_name": "jpposma", "author_url": "", "post_date": "03/24/2023 16:41:49", "content": "You can use whatever system you want for offline data processing (eg training), though we have to be able to reproduce your methods if you end up winning. (In that case we'd contact you and ask how we can run the offline data processing ourselves.)
", "votes": null, "replies": [ { "id": 2195478, "author_name": "costella", "author_url": "", "post_date": "03/24/2023 17:07:50", "content": "Thanks JP!
", "votes": null, "replies": [] } ] } ] } ] }, { "id": 2292670, "author_name": "wesleystevens", "author_url": "", "post_date": "06/08/2023 14:46:06", "content": "When I click upgrade to google cloud notebook, there's a cell that says \"Run this to get the data imported\", but when I run it I get a permission denied error: PermissionError: [Errno 13] Permission denied: '/home/kaggle' on line 18. Any ideas how to fix?
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "2195410": "I looked through all the rules but I can't see an answer.\n\nI got an upsell to \"Upgrade to Google Cloud AI Platform Notebooks\" when I ran out of memory.\n\nI'm happy to do that, but is it allowed?\n\n", "2195417": "Actual submissions still need to fit in Kaggle notebooks (https://www.kaggle.com/competitions/vesuvius-challenge-ink-detection/overview/code-requirements), but for exploratory work anything goes.", "2195419": "Got it—thanks!", "2195420": "Yeah I'd looked at that page (nit: the close paren got pulled into your link URL) but it wasn't clear that \"Notebooks\" meant \"Kaggle Notebooks\" and not \"any Notebooks.\"", "2195426": "Another question: so the notebook that is executed on the real test fragments must be in a Kaggle Notebook, but the training can be done on another system and the model loaded in through a dataset (provided that you guys can reproduce that without too much hassle and it fulfills the license requirements, etc.)? Or everything needs to be done from the Kaggle Notebook?", "2195449": "You can use whatever system you want for offline data processing (eg training), though we have to be able to reproduce your methods if you end up winning. (In that case we'd contact you and ask how we can run the offline data processing ourselves.)", "2195478": "Thanks JP!", "2292670": "When I click upgrade to google cloud notebook, there's a cell that says \"Run this to get the data imported\", but when I run it I get a permission denied error: PermissionError: [Errno 13] Permission denied: '/home/kaggle' on line 18. Any ideas how to fix?" }, "source": "meta" }