Hello!
\n\nWelcome to Petals to the Metal: Flower Classification on TPU!
\n\nIn this competition, you'll learn how to use TPUs to do flower classification on a dataset including more than 100 types of flowers. The dataset is small and comes from many disparate sources, so there are plenty of opportunities to learn about data cleaning and image augmentation as well.
\n\nThis is a Getting Started competition. (What is a Getting Started competition?) We've provided some great starter notebooks, both for learning how to submit to the competition, and for a detailed walkthrough of building models on TPU. More content will be added over time, and this contest will run indefinitely so that people can continue to learn from it!
\n\nPlease let us know if you have any questions or feedback - we're here to help!
\n\nGood luck!
", "messages": [ { "id": 2658248, "postDate": "2024-02-19T05:14:04.893Z", "content": "Great work
", "rawMarkdown": "Great work", "votes": 1 }, { "id": 2558959, "postDate": "2023-12-12T13:36:42.030Z", "content": "Great work!!
", "rawMarkdown": "Great work!!", "votes": 1 }, { "id": 892488, "postDate": "2020-06-18T23:28:51.910Z", "content": "Hello!
\n\nWelcome to Petals to the Metal: Flower Classification on TPU!
\n\nIn this competition, you'll learn how to use TPUs to do flower classification on a dataset including more than 100 types of flowers. The dataset is small and comes from many disparate sources, so there are plenty of opportunities to learn about data cleaning and image augmentation as well.
\n\nThis is a Getting Started competition. (What is a Getting Started competition?) We've provided some great starter notebooks, both for learning how to submit to the competition, and for a detailed walkthrough of building models on TPU. More content will be added over time, and this contest will run indefinitely so that people can continue to learn from it!
\n\nPlease let us know if you have any questions or feedback - we're here to help!
\n\nGood luck!
", "rawMarkdown": "Hello!\n\nWelcome to Petals to the Metal: Flower Classification on TPU!\n\nIn this competition, you'll learn how to use TPUs to do flower classification on a dataset including more than 100 types of flowers. The dataset is small and comes from many disparate sources, so there are plenty of opportunities to learn about data cleaning and image augmentation as well.\n\nThis is a Getting Started competition. ([What is a Getting Started competition?](https://www.kaggle.com/c/tpu-getting-started/overview/faq)) We've provided some great starter notebooks, both for [learning how to submit to the competition](https://www.kaggle.com/ryanholbrook/create-your-first-submission), and for [a detailed walkthrough of building models on TPU](https://www.kaggle.com/kernels/fork/10204702). More content will be added over time, and this contest will run indefinitely so that people can continue to learn from it!\n\nPlease let us know if you have any questions or feedback - we're here to help!\n\nGood luck!", "votes": 29 }, { "id": 897273, "postDate": "2020-06-22T18:40:17.810Z", "content": "@philculliton You've got a formatting typo in your post win \"a detailed walkthrough of building models on TPU\" link.
", "rawMarkdown": "@philculliton You've got a formatting typo in your post win \"a detailed walkthrough of building models on TPU\" link.", "votes": 1, "replies": [ { "id": 897506, "postDate": "2020-06-22T23:07:52.857Z", "content": "Thanks very much!
", "rawMarkdown": "Thanks very much!" } ] }, { "id": 3078823, "postDate": "2024-12-22T22:00:35.407Z", "content": "Hi, I am new here, I hope yo have fun and learn many things!
", "rawMarkdown": "Hi, I am new here, I hope yo have fun and learn many things!\n\n" }, { "id": 2956007, "postDate": "2024-08-11T17:00:29.670Z", "content": "I am a beginner ,it’s a great material for me to learn.Thanks for sharing
", "rawMarkdown": "I am a beginner ,it’s a great material for me to learn.Thanks for sharing " }, { "id": 2853189, "postDate": "2024-06-03T16:30:22.833Z", "content": "Great Work
", "rawMarkdown": "Great Work" }, { "id": 2684694, "postDate": "2024-03-06T18:37:14.620Z", "content": "I am getting the error below at cell # 6 (Build a model on TPU (or GPU, or CPU…)….) while running the notebook. I appreciate your help on this. Thanks
\nRuntimeError: Mixing different tf.distribute.Strategy objects: is not
", "rawMarkdown": "I am getting the error below at cell # 6 (Build a model on TPU (or GPU, or CPU...)....) while running the notebook. I appreciate your help on this. Thanks\n\nRuntimeError: Mixing different tf.distribute.Strategy objects:Great Work! Nice place to get started
", "rawMarkdown": "Great Work! Nice place to get started" }, { "id": 2335183, "postDate": "2023-07-08T10:46:58.383Z", "content": "Great work!!
", "rawMarkdown": "Great work!!" }, { "id": 2327809, "postDate": "2023-07-03T07:24:23.953Z", "content": "I am a newbie here where shall i start from
", "rawMarkdown": "I am a newbie here where shall i start from\n" }, { "id": 2268989, "postDate": "2023-05-22T06:40:18.197Z", "content": "I love learning with these sources :D
", "rawMarkdown": "I love learning with these sources :D" }, { "id": 2214042, "postDate": "2023-04-08T05:22:41.670Z", "content": "Hi, i'm beginner , machine learning and deep learning, and i'm Japanese and not good at English…
\ni want to make some submission, but I can't use TPU.
\nSo, i use CPU in my local space. please help me by some advise.
Cool, Good place to get started.
", "rawMarkdown": "Cool, Good place to get started." }, { "id": 1559556, "postDate": "2021-10-27T05:21:04.440Z", "content": "Great work!
", "rawMarkdown": "Great work!" }, { "id": 1075141, "postDate": "2020-11-11T12:37:30.887Z", "content": "When Loading the Competition Data, I've got: AttributeError: Cannot set the property experimental_daterministic on Options.
", "rawMarkdown": "When Loading the Competition Data, I've got: AttributeError: Cannot set the property experimental_daterministic on Options." }, { "id": 1005231, "postDate": "2020-09-10T10:43:58.443Z", "content": "Not Sure why i am getting this error while saving my notebook..
\nAn error occurred while committing kernel: Unexpected end of JSON input…
I dont know if this is right place to ask but asking anyway so u can guid.
\nHow can i convert tfrec to jpeg or png ?
\nI am unable to finf this answer.
Hello @philculliton, \nThe link a detailed walkthrough of building models on TPU is not working (giving \"404 We can't find that page.\").\nThanks for the flowers :)
", "rawMarkdown": "Hello @philculliton, \nThe link [a detailed walkthrough of building models on TPU](https://www.kaggle.com/ryanholbrook/exercise-getting-started-with-tpus-testing) is not working (giving \"404 We can't find that page.\").\nThanks for the flowers :)", "replies": [ { "id": 898632, "postDate": "2020-06-23T16:35:36.330Z", "content": "Thank you! Fixed now.
", "rawMarkdown": "Thank you! Fixed now." } ] }, { "id": 896471, "postDate": "2020-06-22T07:50:14.733Z", "content": "Why are external datasets not allowed for this competition?
\n\n", "rawMarkdown": "Why are external datasets not allowed for this competition?\n\n@philculliton ", "replies": [ { "id": 897507, "postDate": "2020-06-22T23:09:28.053Z", "content": "Great question! They are allowed per the rules.
\n\nFrom the rules:\n> C. External Data. You may use data other than the Competition Data (“External Data”) to develop and test your models and Submissions. However, you will (i) ensure the External Data is available to use by all participants of the competition for purposes of the competition at no cost to the other participants and (ii) post such access to the External Data for the participants to the official competition forum prior to the Entry Deadline.
", "rawMarkdown": "Great question! They are allowed per the rules.\n\nFrom the rules:\n> C. External Data. You may use data other than the Competition Data (“External Data”) to develop and test your models and Submissions. However, you will (i) ensure the External Data is available to use by all participants of the competition for purposes of the competition at no cost to the other participants and (ii) post such access to the External Data for the participants to the official competition forum prior to the Entry Deadline." } ] }, { "id": 892882, "postDate": "2020-06-19T08:24:03.523Z", "content": "Dear @philculliton, I know it is infinitely improbable, but will there be a bowl of petunias?
\n\nMore seriously, I think this competition is an excellent addition to the Getting Started series. Great work!
", "rawMarkdown": "Dear @philculliton, I know it is infinitely improbable, but will there be a bowl of [petunias](https://en.wikipedia.org/wiki/Petunia)?\n\nMore seriously, I think this competition is an excellent addition to the *Getting Started* series. Great work!", "replies": [ { "id": 893392, "postDate": "2020-06-19T15:16:49.793Z", "content": "On behalf of the whole team, thank you! Every competition is a big team effort, and this one (and its predecessor, Flower Classification with TPUs) was bigger than most.
\nMuch more likely the whale, honestly. Every problem is a source of wonder and eventual blubber explosions. If I ever get to the place where I'm saying \"oh no, not again\" I'll know I've come too far. :-)
", "rawMarkdown": "On behalf of the whole team, thank you! Every competition is a big team effort, and this one (and its predecessor, [Flower Classification with TPUs](https://www.kaggle.com/c/flower-classification-with-tpus/overview)) was bigger than most.\n\nMuch more likely the whale, honestly. Every problem is a source of wonder and eventual blubber explosions. If I ever get to the place where I'm saying \"oh no, not again\" I'll know I've come too far. :-)", "votes": 2 } ] }, { "id": 2268208, "postDate": "2023-05-21T14:50:34.560Z", "rawMarkdown": "", "isDeleted": true }, { "id": 2461182, "postDate": "2023-09-29T10:34:39.113Z", "content": "Thanks, for sharing.
", "rawMarkdown": "Thanks, for sharing." }, { "id": 2085458, "postDate": "2023-01-04T07:08:27.467Z", "content": "Thanks for sharing.
", "rawMarkdown": "Thanks for sharing. " }, { "id": 1649710, "postDate": "2022-01-14T14:32:20.680Z", "content": "Thanks for sharing. 👍
", "rawMarkdown": "Thanks for sharing. 👍" } ], "comments": [ { "id": 2658248, "author_name": "Riya Raizada", "author_url": "", "post_date": "2024-02-19T05:14:04.893000", "content": "Great work
", "votes": 1, "replies": [] }, { "id": 2558959, "author_name": "qiuzhongxiang", "author_url": "", "post_date": "2023-12-12T13:36:42.030000", "content": "Great work!!
", "votes": 1, "replies": [] }, { "id": 897273, "author_name": "Araik Tamazian", "author_url": "", "post_date": "2020-06-22T18:40:17.810000", "content": "@philculliton You've got a formatting typo in your post win \"a detailed walkthrough of building models on TPU\" link.
", "votes": 1, "replies": [ { "id": 897506, "author_name": "Phil Culliton", "author_url": "", "post_date": "2020-06-22T23:07:52.857000", "content": "Thanks very much!
", "votes": 0, "replies": [] } ] }, { "id": 3078823, "author_name": "Ross1994", "author_url": "", "post_date": "2024-12-22T22:00:35.407000", "content": "Hi, I am new here, I hope yo have fun and learn many things!
", "votes": 0, "replies": [] }, { "id": 2956007, "author_name": "Vincy", "author_url": "", "post_date": "2024-08-11T17:00:29.670000", "content": "I am a beginner ,it’s a great material for me to learn.Thanks for sharing
", "votes": 0, "replies": [] }, { "id": 2853189, "author_name": "Emre Tutay", "author_url": "", "post_date": "2024-06-03T16:30:22.833000", "content": "Great Work
", "votes": 0, "replies": [] }, { "id": 2684694, "author_name": "MRahibe", "author_url": "", "post_date": "2024-03-06T18:37:14.620000", "content": "I am getting the error below at cell # 6 (Build a model on TPU (or GPU, or CPU…)….) while running the notebook. I appreciate your help on this. Thanks
\nRuntimeError: Mixing different tf.distribute.Strategy objects: is not
", "votes": 0, "replies": [] }, { "id": 2460152, "author_name": "Gilad Aharoni", "author_url": "", "post_date": "2023-09-28T15:43:34.533000", "content": "Great Work! Nice place to get started
", "votes": 0, "replies": [] }, { "id": 2335183, "author_name": "Delikan Sapmaz", "author_url": "", "post_date": "2023-07-08T10:46:58.383000", "content": "Great work!!
", "votes": 0, "replies": [] }, { "id": 2327809, "author_name": "", "author_url": "", "post_date": "2023-07-03T07:24:23.953000", "content": "I am a newbie here where shall i start from
", "votes": 0, "replies": [] }, { "id": 2268989, "author_name": "Ludwig Alvarado Becerra", "author_url": "", "post_date": "2023-05-22T06:40:18.197000", "content": "I love learning with these sources :D
", "votes": 0, "replies": [] }, { "id": 2214042, "author_name": "NaojiroUeno", "author_url": "", "post_date": "2023-04-08T05:22:41.670000", "content": "Hi, i'm beginner , machine learning and deep learning, and i'm Japanese and not good at English…
\ni want to make some submission, but I can't use TPU.
\nSo, i use CPU in my local space. please help me by some advise.
Cool, Good place to get started.
", "votes": 0, "replies": [] }, { "id": 1559556, "author_name": "Ms. Nancy Al Aswad", "author_url": "", "post_date": "2021-10-27T05:21:04.440000", "content": "Great work!
", "votes": 0, "replies": [] }, { "id": 1075141, "author_name": "Mirena Angelova", "author_url": "", "post_date": "2020-11-11T12:37:30.887000", "content": "When Loading the Competition Data, I've got: AttributeError: Cannot set the property experimental_daterministic on Options.
", "votes": 0, "replies": [] }, { "id": 1005231, "author_name": "Shivendra Verma", "author_url": "", "post_date": "2020-09-10T10:43:58.443000", "content": "Not Sure why i am getting this error while saving my notebook..
\nAn error occurred while committing kernel: Unexpected end of JSON input…
I dont know if this is right place to ask but asking anyway so u can guid.
\nHow can i convert tfrec to jpeg or png ?
\nI am unable to finf this answer.
Hello @philculliton, \nThe link a detailed walkthrough of building models on TPU is not working (giving \"404 We can't find that page.\").\nThanks for the flowers :)
", "votes": 0, "replies": [ { "id": 898632, "author_name": "Phil Culliton", "author_url": "", "post_date": "2020-06-23T16:35:36.330000", "content": "Thank you! Fixed now.
", "votes": 0, "replies": [] } ] }, { "id": 896471, "author_name": "Kurian Benoy", "author_url": "", "post_date": "2020-06-22T07:50:14.733000", "content": "Why are external datasets not allowed for this competition?
\n\n", "votes": 0, "replies": [ { "id": 897507, "author_name": "Phil Culliton", "author_url": "", "post_date": "2020-06-22T23:09:28.053000", "content": "Great question! They are allowed per the rules.
\n\nFrom the rules:\n> C. External Data. You may use data other than the Competition Data (“External Data”) to develop and test your models and Submissions. However, you will (i) ensure the External Data is available to use by all participants of the competition for purposes of the competition at no cost to the other participants and (ii) post such access to the External Data for the participants to the official competition forum prior to the Entry Deadline.
", "votes": 0, "replies": [] } ] }, { "id": 892882, "author_name": "Carl McBride Ellis", "author_url": "", "post_date": "2020-06-19T08:24:03.523000", "content": "Dear @philculliton, I know it is infinitely improbable, but will there be a bowl of petunias?
\n\nMore seriously, I think this competition is an excellent addition to the Getting Started series. Great work!
", "votes": 0, "replies": [ { "id": 893392, "author_name": "Phil Culliton", "author_url": "", "post_date": "2020-06-19T15:16:49.793000", "content": "On behalf of the whole team, thank you! Every competition is a big team effort, and this one (and its predecessor, Flower Classification with TPUs) was bigger than most.
\nMuch more likely the whale, honestly. Every problem is a source of wonder and eventual blubber explosions. If I ever get to the place where I'm saying \"oh no, not again\" I'll know I've come too far. :-)
", "votes": 2, "replies": [] } ] }, { "id": 2268208, "author_name": "", "author_url": "", "post_date": "2023-05-21T14:50:34.560000", "content": "", "votes": 0, "replies": [] }, { "id": 2461182, "author_name": "Rahul Solanki", "author_url": "", "post_date": "2023-09-29T10:34:39.113000", "content": "Thanks, for sharing.
", "votes": 0, "replies": [] }, { "id": 2085458, "author_name": "Prabha", "author_url": "", "post_date": "2023-01-04T07:08:27.467000", "content": "Thanks for sharing.
", "votes": 0, "replies": [] }, { "id": 1649710, "author_name": "Hussain Alkhalaf", "author_url": "", "post_date": "2022-01-14T14:32:20.680000", "content": "Thanks for sharing. 👍
", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "2658248": "Great work", "2558959": "Great work!!", "892488": "Hello!\n\nWelcome to Petals to the Metal: Flower Classification on TPU!\n\nIn this competition, you'll learn how to use TPUs to do flower classification on a dataset including more than 100 types of flowers. The dataset is small and comes from many disparate sources, so there are plenty of opportunities to learn about data cleaning and image augmentation as well.\n\nThis is a Getting Started competition. ([What is a Getting Started competition?](https://www.kaggle.com/c/tpu-getting-started/overview/faq)) We've provided some great starter notebooks, both for [learning how to submit to the competition](https://www.kaggle.com/ryanholbrook/create-your-first-submission), and for [a detailed walkthrough of building models on TPU](https://www.kaggle.com/kernels/fork/10204702). More content will be added over time, and this contest will run indefinitely so that people can continue to learn from it!\n\nPlease let us know if you have any questions or feedback - we're here to help!\n\nGood luck!", "897273": "@philculliton You've got a formatting typo in your post win \"a detailed walkthrough of building models on TPU\" link.", "3078823": "Hi, I am new here, I hope yo have fun and learn many things!\n\n", "2956007": "I am a beginner ,it’s a great material for me to learn.Thanks for sharing ", "2853189": "Great Work", "2684694": "I am getting the error below at cell # 6 (Build a model on TPU (or GPU, or CPU...)....) while running the notebook. I appreciate your help on this. Thanks\n\nRuntimeError: Mixing different tf.distribute.Strategy objects: