New to machine learning and data science? No question is too basic or too simple. Feel free to start your own thread, or use this thread as a place to post any first-timer clarifying questions for the Kaggle community to help you with!
\nIf you would consider yourself a beginner but don't know where to get started, let other Kagglers help you take your first steps here!
\nNew to Kaggle? Take a look at a few videos Dr. Rachael Tatman has put together to learn a bit more about site etiquette, or Kaggle lingo.
\nRemember: Kaggle is for everyone. Whether you're teaming up or sharing tips in the competition forum, we expect everyone to follow our Kaggle community guidelines.
\nA tip on sharing content - Kaggle is a collaborative community, whereby sharing techniques, starter notebooks, and ideas in the discussion forums are highly encouraged throughout the competition. However, as the competition draws closer to the final deadline it's customary to keep high-scoring notebooks withheld until after the competition has concluded. This maintains the spirit of the competition, while also allowing individuals to submit their own creative work without jeopardy of a higher-scoring notebook being available for an automatic higher rank (through copy/submit). We disable publishing of public notebooks within the final week of the competition, but encourage you to use your best judgment prior to that deadline.
\nHappy Modeling!
", "messages": [ { "id": 2428391, "postDate": "2023-09-07T20:16:50.910Z", "content": "New to machine learning and data science? No question is too basic or too simple. Feel free to start your own thread, or use this thread as a place to post any first-timer clarifying questions for the Kaggle community to help you with!
\nIf you would consider yourself a beginner but don't know where to get started, let other Kagglers help you take your first steps here!
\nNew to Kaggle? Take a look at a few videos Dr. Rachael Tatman has put together to learn a bit more about site etiquette, or Kaggle lingo.
\nRemember: Kaggle is for everyone. Whether you're teaming up or sharing tips in the competition forum, we expect everyone to follow our Kaggle community guidelines.
\nA tip on sharing content - Kaggle is a collaborative community, whereby sharing techniques, starter notebooks, and ideas in the discussion forums are highly encouraged throughout the competition. However, as the competition draws closer to the final deadline it's customary to keep high-scoring notebooks withheld until after the competition has concluded. This maintains the spirit of the competition, while also allowing individuals to submit their own creative work without jeopardy of a higher-scoring notebook being available for an automatic higher rank (through copy/submit). We disable publishing of public notebooks within the final week of the competition, but encourage you to use your best judgment prior to that deadline.
\nHappy Modeling!
", "rawMarkdown": "New to machine learning and data science? No question is too basic or too simple. Feel free to start your own thread, or use this thread as a place to post any first-timer clarifying questions for the Kaggle community to help you with!\n\nIf you would consider yourself a beginner but don't know where to get started, let other Kagglers help you take your first steps here!\n\nNew to Kaggle? Take a look at a few videos Dr. Rachael Tatman has put together to learn a bit more about [site etiquette](https://www.youtube.com/watch?v=aIus8si_Et0), or [Kaggle lingo](https://www.youtube.com/watch?v=sEJHyuWKd-s).\n\nRemember: Kaggle is for everyone. Whether you're teaming up or sharing tips in the competition forum, we expect everyone to follow our [Kaggle community guidelines](https://www.kaggle.com/community-guidelines).\n\nA tip on sharing content - Kaggle is a collaborative community, whereby sharing techniques, starter notebooks, and ideas in the discussion forums are highly encouraged throughout the competition. However, as the competition draws closer to the final deadline it's customary to keep high-scoring notebooks withheld until after the competition has concluded. This maintains the spirit of the competition, while also allowing individuals to submit their own creative work without jeopardy of a higher-scoring notebook being available for an automatic higher rank (through copy/submit). We disable publishing of public notebooks within the final week of the competition, but encourage you to use your best judgment prior to that deadline.\n\n \n\nHappy Modeling!\n", "votes": 6 }, { "id": 2434972, "postDate": "2023-09-12T16:13:57.713Z", "content": "Yeah,alright
", "rawMarkdown": "Yeah,alright\n", "votes": 1 }, { "id": 2551475, "postDate": "2023-12-06T17:53:21.690Z", "content": "People. Hi all. I'm taking my first steps in mastering the transformer. I get the following error:
\nFor unbatched (2-D) query, expected key_padding_mask to be None or 1-D but found 2-D tensor instead
As a mask I use a Boolean array, the size of the [size of the batch x sequence] (transposing didn't help).
", "rawMarkdown": "People. Hi all. I'm taking my first steps in mastering the transformer. I get the following error: \n\n*For unbatched (2-D) `query`, expected `key_padding_mask` to be `None` or 1-D but found 2-D tensor instead*\n\nAs a mask I use a Boolean array, the size of the [size of the batch x sequence] (transposing didn't help)." }, { "id": 2548847, "postDate": "2023-12-04T18:46:13.677Z", "content": "Hi. I have a question about Kaggle datasets. I understand that if you make a public dataset, this automatically has a gcs path so then you can use this dataset with google colab TPU, but there is some way to make this with a private dataset? thank you!
", "rawMarkdown": "Hi. I have a question about Kaggle datasets. I understand that if you make a public dataset, this automatically has a gcs path so then you can use this dataset with google colab TPU, but there is some way to make this with a private dataset? thank you!", "replies": [ { "id": 2549707, "postDate": "2023-12-05T13:26:38.770Z", "content": "I found it here, if somebody else had the same question https://www.kaggle.com/docs/tpu#tpu3pt5
", "rawMarkdown": "I found it here, if somebody else had the same question https://www.kaggle.com/docs/tpu#tpu3pt5 ", "votes": 1, "replies": [ { "id": 2549729, "postDate": "2023-12-05T13:43:23.560Z", "content": "I would be happy to see an update if it worked for you.
", "rawMarkdown": "I would be happy to see an update if it worked for you." }, { "id": 2550098, "postDate": "2023-12-05T19:02:36.383Z", "content": "Sadly, didn't worked actuallly 🫠Seems like that the only way is using directly gcs.
", "rawMarkdown": "Sadly, didn't worked actuallly 🫠Seems like that the only way is using directly gcs.", "votes": 1 } ] } ] }, { "id": 2518113, "postDate": "2023-11-09T04:12:31.663Z", "rawMarkdown": "", "isDeleted": true }, { "id": 2506318, "postDate": "2023-10-31T08:05:17.400Z", "content": "thank you 👉👈
", "rawMarkdown": "thank you 👉👈" }, { "id": 2467595, "postDate": "2023-10-04T16:58:53.430Z", "content": "Thank you for the information
", "rawMarkdown": "Thank you for the information " }, { "id": 2436904, "postDate": "2023-09-13T20:46:36.720Z", "content": "Alright, thank you.
", "rawMarkdown": "Alright, thank you." } ], "comments": [ { "id": 2434972, "author_name": "ADABALA RAJAPPA", "author_url": "", "post_date": "2023-09-12T16:13:57.713000", "content": "Yeah,alright
", "votes": 1, "replies": [] }, { "id": 2551475, "author_name": "BorisNiels", "author_url": "", "post_date": "2023-12-06T17:53:21.690000", "content": "People. Hi all. I'm taking my first steps in mastering the transformer. I get the following error:
\nFor unbatched (2-D) query, expected key_padding_mask to be None or 1-D but found 2-D tensor instead
As a mask I use a Boolean array, the size of the [size of the batch x sequence] (transposing didn't help).
", "votes": 0, "replies": [] }, { "id": 2548847, "author_name": "Nico Sandoval", "author_url": "", "post_date": "2023-12-04T18:46:13.677000", "content": "Hi. I have a question about Kaggle datasets. I understand that if you make a public dataset, this automatically has a gcs path so then you can use this dataset with google colab TPU, but there is some way to make this with a private dataset? thank you!
", "votes": 0, "replies": [ { "id": 2549707, "author_name": "Nico Sandoval", "author_url": "", "post_date": "2023-12-05T13:26:38.770000", "content": "I found it here, if somebody else had the same question https://www.kaggle.com/docs/tpu#tpu3pt5
", "votes": 1, "replies": [ { "id": 2549729, "author_name": "greySnow", "author_url": "", "post_date": "2023-12-05T13:43:23.560000", "content": "I would be happy to see an update if it worked for you.
", "votes": 0, "replies": [] }, { "id": 2550098, "author_name": "Nico Sandoval", "author_url": "", "post_date": "2023-12-05T19:02:36.383000", "content": "Sadly, didn't worked actuallly 🫠Seems like that the only way is using directly gcs.
", "votes": 1, "replies": [] } ] } ] }, { "id": 2518113, "author_name": "", "author_url": "", "post_date": "2023-11-09T04:12:31.663000", "content": "", "votes": 0, "replies": [] }, { "id": 2506318, "author_name": "Dolmachii", "author_url": "", "post_date": "2023-10-31T08:05:17.400000", "content": "thank you 👉👈
", "votes": 0, "replies": [] }, { "id": 2467595, "author_name": "Mazimum", "author_url": "", "post_date": "2023-10-04T16:58:53.430000", "content": "Thank you for the information
", "votes": 0, "replies": [] }, { "id": 2436904, "author_name": "Abiola Oyegun", "author_url": "", "post_date": "2023-09-13T20:46:36.720000", "content": "Alright, thank you.
", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "2428391": "New to machine learning and data science? No question is too basic or too simple. Feel free to start your own thread, or use this thread as a place to post any first-timer clarifying questions for the Kaggle community to help you with!\n\nIf you would consider yourself a beginner but don't know where to get started, let other Kagglers help you take your first steps here!\n\nNew to Kaggle? Take a look at a few videos Dr. Rachael Tatman has put together to learn a bit more about [site etiquette](https://www.youtube.com/watch?v=aIus8si_Et0), or [Kaggle lingo](https://www.youtube.com/watch?v=sEJHyuWKd-s).\n\nRemember: Kaggle is for everyone. Whether you're teaming up or sharing tips in the competition forum, we expect everyone to follow our [Kaggle community guidelines](https://www.kaggle.com/community-guidelines).\n\nA tip on sharing content - Kaggle is a collaborative community, whereby sharing techniques, starter notebooks, and ideas in the discussion forums are highly encouraged throughout the competition. However, as the competition draws closer to the final deadline it's customary to keep high-scoring notebooks withheld until after the competition has concluded. This maintains the spirit of the competition, while also allowing individuals to submit their own creative work without jeopardy of a higher-scoring notebook being available for an automatic higher rank (through copy/submit). We disable publishing of public notebooks within the final week of the competition, but encourage you to use your best judgment prior to that deadline.\n\n \n\nHappy Modeling!\n", "2434972": "Yeah,alright\n", "2551475": "People. Hi all. I'm taking my first steps in mastering the transformer. I get the following error: \n\n*For unbatched (2-D) `query`, expected `key_padding_mask` to be `None` or 1-D but found 2-D tensor instead*\n\nAs a mask I use a Boolean array, the size of the [size of the batch x sequence] (transposing didn't help).", "2548847": "Hi. I have a question about Kaggle datasets. I understand that if you make a public dataset, this automatically has a gcs path so then you can use this dataset with google colab TPU, but there is some way to make this with a private dataset? thank you!", "2518113": "", "2506318": "thank you 👉👈", "2467595": "Thank you for the information ", "2436904": "Alright, thank you." } }