![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2474293%2F1340f26f3960f8b5c43e2fd37b042453%2FScreenshot_2020-10-07-03-40-45-310_com.android.chrome.jpg?generation=1602032469125436&alt=media\")
We'd like to first thank Open Source Imaging Consortium (OSIC) and Kaggle for providing us with an interesting, real-world dataset of decline in lung function based on a CT scan of their lungs to play with!
\nWe are very happy to get our first silver medal in Kaggle from this competition.
\nIt was really difficult to select the best model. We trusted our CV score and selected our model for the submission, which allowed us to win a silver medal.
\nHowever, the fact that we had a first-place solution, it shows how difficult to select the best model for this competition.
We shared our first-place solution (didn't select) in the notebook below. I think the embedding layer helped improve the score.
\nhttps://www.kaggle.com/lhagiimn/solution-for-the-first-place-but-we-didn-t-select
", "messages": [ { "id": 1040045, "postDate": "2020-10-07T00:52:43.483Z", "content": "We'd like to first thank Open Source Imaging Consortium (OSIC) and Kaggle for providing us with an interesting, real-world dataset of decline in lung function based on a CT scan of their lungs to play with!
\nWe are very happy to get our first silver medal in Kaggle from this competition.
\nIt was really difficult to select the best model. We trusted our CV score and selected our model for the submission, which allowed us to win a silver medal.
\nHowever, the fact that we had a first-place solution, it shows how difficult to select the best model for this competition.
We shared our first-place solution (didn't select) in the notebook below. I think the embedding layer helped improve the score.
\nhttps://www.kaggle.com/lhagiimn/solution-for-the-first-place-but-we-didn-t-select
", "rawMarkdown": "We'd like to first thank Open Source Imaging Consortium (OSIC) and Kaggle for providing us with an interesting, real-world dataset of decline in lung function based on a CT scan of their lungs to play with!\n\nWe are very happy to get our first silver medal in Kaggle from this competition.\n\nIt was really difficult to select the best model. We trusted our CV score and selected our model for the submission, which allowed us to win a silver medal.\nHowever, the fact that we had a first-place solution, it shows how difficult to select the best model for this competition.\n\nWe shared our first-place solution (didn't select) in the notebook below. I think the embedding layer helped improve the score.\n\nhttps://www.kaggle.com/lhagiimn/solution-for-the-first-place-but-we-didn-t-select", "votes": 9 }, { "id": 1040064, "postDate": "2020-10-07T01:01:15.277Z", "content": "Well. Then I had the winning kernel.
I don't think so :)
", "rawMarkdown": "I don't think so :)\n" }, { "id": 1040072, "postDate": "2020-10-07T01:09:35.757Z", "content": "I had a not selected submission score -6.8256. That beats yours. I am guessing quite a few people will have a similar best scoring submission, not selected.
", "rawMarkdown": "I had a not selected submission score -6.8256. That beats yours. I am guessing quite a few people will have a similar best scoring submission, not selected." }, { "id": 1040078, "postDate": "2020-10-07T01:11:58.940Z", "content": "I couldn't upload the image. Our actual notebook that submitted before the deadline was -6.8250, I prepared this notebook for sharing. But the score was decreased :D
", "rawMarkdown": "I couldn't upload the image. Our actual notebook that submitted before the deadline was -6.8250, I prepared this notebook for sharing. But the score was decreased :D " }, { "id": 1040083, "postDate": "2020-10-07T01:15:38.633Z", "content": "Either way congrats. Your solution looks elegant and unique. Mine was an ensemble of bits and pieces. My best selected submission ended up being a hierarchical Bayesian regression model as taken by Carlos Suza
", "rawMarkdown": "Either way congrats. Your solution looks elegant and unique. Mine was an ensemble of bits and pieces. My best selected submission ended up being a hierarchical Bayesian regression model as taken by Carlos Suza", "votes": 1 } ] }, { "id": 1040259, "postDate": "2020-10-07T04:03:59.903Z", "content": "this happened to me too . my best score was capable for rank 14(-6.8409) but ended up being rank 63 (-6.8474) because didn't select the correct submission . well , congrats to everyone who won !!
", "rawMarkdown": "this happened to me too . my best score was capable for rank 14(-6.8409) but ended up being rank 63 (-6.8474) because didn't select the correct submission . well , congrats to everyone who won !!" }, { "id": 1040062, "postDate": "2020-10-07T01:00:25.253Z", "rawMarkdown": "", "isDeleted": true } ], "comments": [ { "id": 1040064, "author_name": "Tsakalis Pantelis", "author_url": "", "post_date": "2020-10-07T01:01:15.277000", "content": "Well. Then I had the winning kernel.
I don't think so :)
", "votes": 0, "replies": [] }, { "id": 1040072, "author_name": "Tsakalis Pantelis", "author_url": "", "post_date": "2020-10-07T01:09:35.757000", "content": "I had a not selected submission score -6.8256. That beats yours. I am guessing quite a few people will have a similar best scoring submission, not selected.
", "votes": 0, "replies": [] }, { "id": 1040078, "author_name": "lhagiimn", "author_url": "", "post_date": "2020-10-07T01:11:58.940000", "content": "I couldn't upload the image. Our actual notebook that submitted before the deadline was -6.8250, I prepared this notebook for sharing. But the score was decreased :D
", "votes": 0, "replies": [] }, { "id": 1040083, "author_name": "Tsakalis Pantelis", "author_url": "", "post_date": "2020-10-07T01:15:38.633000", "content": "Either way congrats. Your solution looks elegant and unique. Mine was an ensemble of bits and pieces. My best selected submission ended up being a hierarchical Bayesian regression model as taken by Carlos Suza
", "votes": 1, "replies": [] } ] }, { "id": 1040259, "author_name": "ARJUN TANDON", "author_url": "", "post_date": "2020-10-07T04:03:59.903000", "content": "this happened to me too . my best score was capable for rank 14(-6.8409) but ended up being rank 63 (-6.8474) because didn't select the correct submission . well , congrats to everyone who won !!
", "votes": 0, "replies": [] }, { "id": 1040062, "author_name": "", "author_url": "", "post_date": "2020-10-07T01:00:25.253000", "content": "", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "1040045": "We'd like to first thank Open Source Imaging Consortium (OSIC) and Kaggle for providing us with an interesting, real-world dataset of decline in lung function based on a CT scan of their lungs to play with!\n\nWe are very happy to get our first silver medal in Kaggle from this competition.\n\nIt was really difficult to select the best model. We trusted our CV score and selected our model for the submission, which allowed us to win a silver medal.\nHowever, the fact that we had a first-place solution, it shows how difficult to select the best model for this competition.\n\nWe shared our first-place solution (didn't select) in the notebook below. I think the embedding layer helped improve the score.\n\nhttps://www.kaggle.com/lhagiimn/solution-for-the-first-place-but-we-didn-t-select", "1040064": "Well. Then I had the winning kernel.", "1040259": "this happened to me too . my best score was capable for rank 14(-6.8409) but ended up being rank 63 (-6.8474) because didn't select the correct submission . well , congrats to everyone who won !!", "1040062": "" } }