In addition to this competition forum, you can continue the discussion in our official Kaggle Discord Server here: discord.gg/kaggle
\nThe Discord is a great place to ask getting started questions, chat about the nuances of this competition, and connect with potential team mates. Learn more about Discord at our announcement here. Here are a few things to keep in mind though:
\nDiscord Competition Channels are 'Public'
\nDiscord channels for specific competitions are considered 'public' spaces where you are allowed to talk about competition details (it will not count as private sharing).
Discord Competition Channels are Not Monitored by Staff
\nKaggle Staff and Hosts running competitions will not monitor Discord or be available to answer questions in Discord. Always post important questions in the forums.
Keep the Good Stuff on the Forums
\nPlease keep important questions, insights, writeups, and other valuable conversation on the Kaggle forums. Discord is intended to be a more casual space to discuss competitions and help each other, we want to keep all the best information on the forums.
Remember to never privately share competition code or data
\nPlease remember that private sharing of competition code or data is, as always, not permitted. Code sharing must always be done publicly through the Kaggle forums/notebooks.
I hope you’ll join us to chat on Discord soon!
", "messages": [ { "id": 2472022, "postDate": "2023-10-06T21:34:27.300Z", "content": "In addition to this competition forum, you can continue the discussion in our official Kaggle Discord Server here: discord.gg/kaggle
\nThe Discord is a great place to ask getting started questions, chat about the nuances of this competition, and connect with potential team mates. Learn more about Discord at our announcement here. Here are a few things to keep in mind though:
\nDiscord Competition Channels are 'Public'
\nDiscord channels for specific competitions are considered 'public' spaces where you are allowed to talk about competition details (it will not count as private sharing).
Discord Competition Channels are Not Monitored by Staff
\nKaggle Staff and Hosts running competitions will not monitor Discord or be available to answer questions in Discord. Always post important questions in the forums.
Keep the Good Stuff on the Forums
\nPlease keep important questions, insights, writeups, and other valuable conversation on the Kaggle forums. Discord is intended to be a more casual space to discuss competitions and help each other, we want to keep all the best information on the forums.
Remember to never privately share competition code or data
\nPlease remember that private sharing of competition code or data is, as always, not permitted. Code sharing must always be done publicly through the Kaggle forums/notebooks.
I hope you’ll join us to chat on Discord soon!
", "rawMarkdown": "In addition to this competition forum, you can continue the discussion in our official Kaggle Discord Server here: [discord.gg/kaggle](http://discord.gg/kaggle)\n\nThe Discord is a great place to ask getting started questions, chat about the nuances of this competition, and connect with potential team mates. Learn more about Discord at our [announcement here](https://www.kaggle.com/discussions/general/429933). Here are a few things to keep in mind though:\n\nDiscord Competition Channels are 'Public'\nDiscord channels for specific competitions are considered 'public' spaces where you are allowed to talk about competition details (it will not count as private sharing).\n\nDiscord Competition Channels are Not Monitored by Staff\nKaggle Staff and Hosts running competitions will not monitor Discord or be available to answer questions in Discord. Always post important questions in the forums.\n\nKeep the Good Stuff on the Forums\nPlease keep important questions, insights, writeups, and other valuable conversation on the Kaggle forums. Discord is intended to be a more casual space to discuss competitions and help each other, we want to keep all the best information on the forums.\n\nRemember to never privately share competition code or data\nPlease remember that private sharing of competition code or data is, as always, not permitted. Code sharing must always be done publicly through the Kaggle forums/notebooks.\n\nI hope you’ll join us to chat on Discord soon!", "votes": 7 }, { "id": 2480139, "postDate": "2023-10-13T06:15:06.940Z", "content": "Hi, I need help. I have make seven submission. Before I make submission all my notebooks are run successfully for the save version. But after make submission it just keep stated notebook threw exception for all my notebook. I even change my model structure, change the model type, change the code for each notebook, I even download the save model and use new book to make prediction, but ended up all stated the same error. Could please explain to me what is going wrong and I so frustrated. Thanks.
", "rawMarkdown": "Hi, I need help. I have make seven submission. Before I make submission all my notebooks are run successfully for the save version. But after make submission it just keep stated notebook threw exception for all my notebook. I even change my model structure, change the model type, change the code for each notebook, I even download the save model and use new book to make prediction, but ended up all stated the same error. Could please explain to me what is going wrong and I so frustrated. Thanks.", "votes": 2, "replies": [ { "id": 2516064, "postDate": "2023-11-07T12:51:00.803Z", "content": "Hello Natalie. Were you able to figure it out? I am having the same issue.
", "rawMarkdown": "Hello Natalie. Were you able to figure it out? I am having the same issue.", "replies": [ { "id": 2516149, "postDate": "2023-11-07T14:03:47.263Z", "content": "Hi nemo, Nope. I still unable to make submission and still figuring out the issue. I even try to trained the model in a notebook, after that save the model, then used a new notebook and upload the model that I save to make prediction and submission, but is failed.
", "rawMarkdown": "Hi nemo, Nope. I still unable to make submission and still figuring out the issue. I even try to trained the model in a notebook, after that save the model, then used a new notebook and upload the model that I save to make prediction and submission, but is failed. " }, { "id": 2516523, "postDate": "2023-11-07T18:45:06.310Z", "content": "In the notebook that you do the prediction, you may need to handle each test image separately instead of reading in all the test images and looping through them. In other words, you would take an image, load it, and make a prediction on it before processing the next image. Python can garbage collect memory in between load-predict cycles. This way you won't use up a lot memory holding the images before you start making predictions.
\nAfter 10 failed submissions, I was able get a notebook to submit successfully using this approach.
", "rawMarkdown": "In the notebook that you do the prediction, you may need to handle each test image separately instead of reading in all the test images and looping through them. In other words, you would take an image, load it, and make a prediction on it before processing the next image. Python can garbage collect memory in between load-predict cycles. This way you won't use up a lot memory holding the images before you start making predictions.\n\nAfter 10 failed submissions, I was able get a notebook to submit successfully using this approach.", "votes": 1 }, { "id": 2516718, "postDate": "2023-11-07T22:26:35.223Z", "content": "Hi Russ,
\nThank you for your guidance.
Hello Natalie, did that work? I was able to make a submission after creating a new notebook that included only the test dataset and model prediction code. I imported the best model as a dataset and loaded the weights.
", "rawMarkdown": "Hello Natalie, did that work? I was able to make a submission after creating a new notebook that included only the test dataset and model prediction code. I imported the best model as a dataset and loaded the weights. " }, { "id": 2517161, "postDate": "2023-11-08T09:02:38.380Z", "content": "Hi nemo, Glad to hear that you make it. Yes, it is work for me too. Finally I make it.
", "rawMarkdown": "Hi nemo, Glad to hear that you make it. Yes, it is work for me too. Finally I make it." }, { "id": 2517164, "postDate": "2023-11-08T09:03:48.773Z", "content": "Hi nemo, my ranking is just behind of you.😂
", "rawMarkdown": "Hi nemo, my ranking is just behind of you.😂" }, { "id": 2518106, "postDate": "2023-11-09T04:02:43.420Z", "content": "Great news! Good luck on the next steps of data prep and refining your models.
", "rawMarkdown": "Great news! Good luck on the next steps of data prep and refining your models." }, { "id": 2518233, "postDate": "2023-11-09T06:44:47.343Z", "content": "Hi Russ, sure. Need to improve my model😅
", "rawMarkdown": "Hi Russ, sure. Need to improve my model😅" } ] } ] }, { "id": 2472169, "postDate": "2023-10-07T05:00:28.207Z", "content": "I am just seeing this and looking forward to winning
", "rawMarkdown": "I am just seeing this and looking forward to winning ", "votes": 2 } ], "comments": [ { "id": 2480139, "author_name": "Natalie Cheong", "author_url": "", "post_date": "2023-10-13T06:15:06.940000", "content": "Hi, I need help. I have make seven submission. Before I make submission all my notebooks are run successfully for the save version. But after make submission it just keep stated notebook threw exception for all my notebook. I even change my model structure, change the model type, change the code for each notebook, I even download the save model and use new book to make prediction, but ended up all stated the same error. Could please explain to me what is going wrong and I so frustrated. Thanks.
", "votes": 2, "replies": [ { "id": 2516064, "author_name": "nemo", "author_url": "", "post_date": "2023-11-07T12:51:00.803000", "content": "Hello Natalie. Were you able to figure it out? I am having the same issue.
", "votes": 0, "replies": [ { "id": 2516149, "author_name": "Natalie Cheong", "author_url": "", "post_date": "2023-11-07T14:03:47.263000", "content": "Hi nemo, Nope. I still unable to make submission and still figuring out the issue. I even try to trained the model in a notebook, after that save the model, then used a new notebook and upload the model that I save to make prediction and submission, but is failed.
", "votes": 0, "replies": [] }, { "id": 2516523, "author_name": "Russ Tokuyama", "author_url": "", "post_date": "2023-11-07T18:45:06.310000", "content": "In the notebook that you do the prediction, you may need to handle each test image separately instead of reading in all the test images and looping through them. In other words, you would take an image, load it, and make a prediction on it before processing the next image. Python can garbage collect memory in between load-predict cycles. This way you won't use up a lot memory holding the images before you start making predictions.
\nAfter 10 failed submissions, I was able get a notebook to submit successfully using this approach.
", "votes": 1, "replies": [] }, { "id": 2516718, "author_name": "Natalie Cheong", "author_url": "", "post_date": "2023-11-07T22:26:35.223000", "content": "Hi Russ,
\nThank you for your guidance.
Hello Natalie, did that work? I was able to make a submission after creating a new notebook that included only the test dataset and model prediction code. I imported the best model as a dataset and loaded the weights.
", "votes": 0, "replies": [] }, { "id": 2517161, "author_name": "Natalie Cheong", "author_url": "", "post_date": "2023-11-08T09:02:38.380000", "content": "Hi nemo, Glad to hear that you make it. Yes, it is work for me too. Finally I make it.
", "votes": 0, "replies": [] }, { "id": 2517164, "author_name": "Natalie Cheong", "author_url": "", "post_date": "2023-11-08T09:03:48.773000", "content": "Hi nemo, my ranking is just behind of you.😂
", "votes": 0, "replies": [] }, { "id": 2518106, "author_name": "Russ Tokuyama", "author_url": "", "post_date": "2023-11-09T04:02:43.420000", "content": "Great news! Good luck on the next steps of data prep and refining your models.
", "votes": 0, "replies": [] }, { "id": 2518233, "author_name": "Natalie Cheong", "author_url": "", "post_date": "2023-11-09T06:44:47.343000", "content": "Hi Russ, sure. Need to improve my model😅
", "votes": 0, "replies": [] } ] } ] }, { "id": 2472169, "author_name": "IDRIS ADEDAMOLA ABDULHAMEED", "author_url": "", "post_date": "2023-10-07T05:00:28.207000", "content": "I am just seeing this and looking forward to winning
", "votes": 2, "replies": [] } ], "raw_markdown_by_id": { "2472022": "In addition to this competition forum, you can continue the discussion in our official Kaggle Discord Server here: [discord.gg/kaggle](http://discord.gg/kaggle)\n\nThe Discord is a great place to ask getting started questions, chat about the nuances of this competition, and connect with potential team mates. Learn more about Discord at our [announcement here](https://www.kaggle.com/discussions/general/429933). Here are a few things to keep in mind though:\n\nDiscord Competition Channels are 'Public'\nDiscord channels for specific competitions are considered 'public' spaces where you are allowed to talk about competition details (it will not count as private sharing).\n\nDiscord Competition Channels are Not Monitored by Staff\nKaggle Staff and Hosts running competitions will not monitor Discord or be available to answer questions in Discord. Always post important questions in the forums.\n\nKeep the Good Stuff on the Forums\nPlease keep important questions, insights, writeups, and other valuable conversation on the Kaggle forums. Discord is intended to be a more casual space to discuss competitions and help each other, we want to keep all the best information on the forums.\n\nRemember to never privately share competition code or data\nPlease remember that private sharing of competition code or data is, as always, not permitted. Code sharing must always be done publicly through the Kaggle forums/notebooks.\n\nI hope you’ll join us to chat on Discord soon!", "2480139": "Hi, I need help. I have make seven submission. Before I make submission all my notebooks are run successfully for the save version. But after make submission it just keep stated notebook threw exception for all my notebook. I even change my model structure, change the model type, change the code for each notebook, I even download the save model and use new book to make prediction, but ended up all stated the same error. Could please explain to me what is going wrong and I so frustrated. Thanks.", "2472169": "I am just seeing this and looking forward to winning " } }