Hello, thanks for the competition!
\nLink to solution https://github.com/lRomul/ranzcr-clip
\nKey points:
\nThe progress of the solution during the competition can be seen in the laboratory journal (link).
\nIt describes all the single models and ensembles and shows CV, Public/Private LB scores.
Hello, thanks for the competition!
\nLink to solution https://github.com/lRomul/ranzcr-clip
\nKey points:
\nThe progress of the solution during the competition can be seen in the laboratory journal (link).
\nIt describes all the single models and ensembles and shows CV, Public/Private LB scores.
Congratz !
\nThanks for sharing your code, and for using docker. I hope this will be useful to people :)
Thank you!
\nI hope too. Meanwhile, I maintain a collection of Docker images for ML/DL and video processing. One of the images was used in the solution ;)
Congrats on strongly finish and thanks for sharing your solution @romul0212
", "rawMarkdown": "Congrats on strongly finish and thanks for sharing your solution @romul0212 ", "votes": 1, "replies": [ { "id": 1242271, "postDate": "2021-03-17T14:05:57.153Z", "content": "Thanks, Khanh!
", "rawMarkdown": "Thanks, Khanh!" } ] }, { "id": 1242138, "postDate": "2021-03-17T12:30:57.353Z", "content": "Congrats on your silver and thanks for the code of your solution.
\nI wonder that, what is the private LB rank section in your progress sheet. How should we interpret it? Thanks.
\nCongrats again!
", "rawMarkdown": "Congrats on your silver and thanks for the code of your solution. \n\nI wonder that, what is the private LB rank section in your progress sheet. How should we interpret it? Thanks.\n\nCongrats again!", "votes": 1, "replies": [ { "id": 1242149, "postDate": "2021-03-17T12:41:33.563Z", "content": "Thanks, Sinan!
\nMaybe there are leaks on my CV. But I didn't use external data or model weights in the selected submissions. I use stratified folds without patient id overlap in the ensemble with the highest CV score (Blend 16).
\nMaybe it's just a random ¯_(ツ)_/¯
Sorry, I didn't answer the question. \"Private LB rank\" section is an order of my submissions sorted by private LB score. You can find your order on \"My Submissions\" page using \"Sort by - Private Score\".
", "rawMarkdown": "Sorry, I didn't answer the question. \"Private LB rank\" section is an order of my submissions sorted by private LB score. You can find your order on \"My Submissions\" page using \"Sort by - Private Score\".", "votes": 1 }, { "id": 1242222, "postDate": "2021-03-17T13:36:50.743Z", "content": "Ooh, I see. It was 0.973 and saying would be the #1 in the private LB. Since the current score is 0.976, I just got confused.
\nAlso thanks for the information on your code :) Great work!
\nEdit: Ooh, I guess it's your #1. Sorry 😅
", "rawMarkdown": "Ooh, I see. It was 0.973 and saying would be the #1 in the private LB. Since the current score is 0.976, I just got confused. \n\nAlso thanks for the information on your code :) Great work!\n\nEdit: Ooh, I guess it's your #1. Sorry 😅", "votes": 1 } ] }, { "id": 1242082, "postDate": "2021-03-17T11:47:11.763Z", "content": "@romul0212 Congratulations on Silver Finish Ruslan . Thanks for sharing the writeup
", "rawMarkdown": "@romul0212 Congratulations on Silver Finish Ruslan . Thanks for sharing the writeup", "votes": 1, "replies": [ { "id": 1242100, "postDate": "2021-03-17T11:57:47.977Z", "content": "Thanks, Usha!
", "rawMarkdown": "Thanks, Usha! " } ] }, { "id": 1246825, "postDate": "2021-03-21T06:22:24.503Z", "rawMarkdown": "", "isDeleted": true, "replies": [ { "id": 1246986, "postDate": "2021-03-21T09:53:40.313Z", "content": "Thank you!
", "rawMarkdown": "Thank you!" } ] } ], "comments": [ { "id": 1242704, "author_name": "Theo Viel", "author_url": "", "post_date": "2021-03-17T18:45:52.593000", "content": "Congratz !
\nThanks for sharing your code, and for using docker. I hope this will be useful to people :)
Thank you!
\nI hope too. Meanwhile, I maintain a collection of Docker images for ML/DL and video processing. One of the images was used in the solution ;)
Congrats on strongly finish and thanks for sharing your solution @romul0212
", "votes": 1, "replies": [ { "id": 1242271, "author_name": "Ruslan Baikulov", "author_url": "", "post_date": "2021-03-17T14:05:57.153000", "content": "Thanks, Khanh!
", "votes": 0, "replies": [] } ] }, { "id": 1242138, "author_name": "Sinan Calisir", "author_url": "", "post_date": "2021-03-17T12:30:57.353000", "content": "Congrats on your silver and thanks for the code of your solution.
\nI wonder that, what is the private LB rank section in your progress sheet. How should we interpret it? Thanks.
\nCongrats again!
", "votes": 1, "replies": [ { "id": 1242149, "author_name": "Ruslan Baikulov", "author_url": "", "post_date": "2021-03-17T12:41:33.563000", "content": "Thanks, Sinan!
\nMaybe there are leaks on my CV. But I didn't use external data or model weights in the selected submissions. I use stratified folds without patient id overlap in the ensemble with the highest CV score (Blend 16).
\nMaybe it's just a random ¯_(ツ)_/¯
Sorry, I didn't answer the question. \"Private LB rank\" section is an order of my submissions sorted by private LB score. You can find your order on \"My Submissions\" page using \"Sort by - Private Score\".
", "votes": 1, "replies": [] }, { "id": 1242222, "author_name": "Sinan Calisir", "author_url": "", "post_date": "2021-03-17T13:36:50.743000", "content": "Ooh, I see. It was 0.973 and saying would be the #1 in the private LB. Since the current score is 0.976, I just got confused.
\nAlso thanks for the information on your code :) Great work!
\nEdit: Ooh, I guess it's your #1. Sorry 😅
", "votes": 1, "replies": [] } ] }, { "id": 1242082, "author_name": "Tensor Girl", "author_url": "", "post_date": "2021-03-17T11:47:11.763000", "content": "@romul0212 Congratulations on Silver Finish Ruslan . Thanks for sharing the writeup
", "votes": 1, "replies": [ { "id": 1242100, "author_name": "Ruslan Baikulov", "author_url": "", "post_date": "2021-03-17T11:57:47.977000", "content": "Thanks, Usha!
", "votes": 0, "replies": [] } ] }, { "id": 1246825, "author_name": "", "author_url": "", "post_date": "2021-03-21T06:22:24.503000", "content": "", "votes": 0, "replies": [ { "id": 1246986, "author_name": "Ruslan Baikulov", "author_url": "", "post_date": "2021-03-21T09:53:40.313000", "content": "Thank you!
", "votes": 0, "replies": [] } ] } ], "raw_markdown_by_id": { "1242015": "Hello, thanks for the competition!\n\nLink to solution https://github.com/lRomul/ranzcr-clip\n\nKey points: \n* EfficientNet\n* 1024x1024 image resolution\n* Soft pseudo labels\n* Some MLOps for training and making a submission\n\nThe progress of the solution during the competition can be seen in the laboratory journal ([link](https://docs.google.com/spreadsheets/d/112wrfuQjNXEFyqQLVhu79Vf0uOabnZ1MaayEts2Gvto/edit?usp=sharing)).\nIt describes all the single models and ensembles and shows CV, Public/Private LB scores.\n", "1242704": "Congratz ! \nThanks for sharing your code, and for using docker. I hope this will be useful to people :)", "1242235": "Congrats on strongly finish and thanks for sharing your solution @romul0212 ", "1242138": "Congrats on your silver and thanks for the code of your solution. \n\nI wonder that, what is the private LB rank section in your progress sheet. How should we interpret it? Thanks.\n\nCongrats again!", "1242082": "@romul0212 Congratulations on Silver Finish Ruslan . Thanks for sharing the writeup", "1246825": "" } }