{ "id": 409455, "title": "Adjutant resources- Sorenson Dice co-efficient", "url": "/competitions/google-research-identify-contrails-reduce-global-warming/discussion/409455", "author_name": "Ravi Ramakrishnan", "post_date": "2023-05-11T05:25:12.329000", "votes": 5, "comment_count": 0, "views": 0, "content": "

Hello all,

\n

Wishing you the best for the challenge! The sheer size of the data and the nature of the competition (code requirements and the execution time limit) is a gargantuan challenge for the participants. I hope the below adjutant resources regarding the competition metric helps one and all to onboard quickly and effectively-

\n
    \n
  1. https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient -- wikipedia link, mentioned in the overview page as well
    2. \n
  2. https://rosettacode.org/wiki/Sorensen%E2%80%93Dice_coefficient -- good explanatory article, I liked the code snippets with several languages
    3. \n
  3. https://www.mathworks.com/help/images/ref/dice.html -- mathworks article on this topic, terse and useful in my opinion
    4. \n
  4. https://stats.stackexchange.com/questions/195006/is-the-dice-coefficient-the-same-as-accuracy -- very useful article for beginners looking at this measure
    5. \n
  5. https://towardsdatascience.com/similarity-measures-and-graph-adjacency-with-sets-a33d16e527e1v -- this is a well written article explaining this metric quite well
    6. \n
\n

Kaggle notebooks using the metric

\n
    \n
  1. https://www.kaggle.com/code/dschettler8845/uwm-gi-tract-image-segmentation-eda
    2. \n
  2. https://www.kaggle.com/code/yerramvarun/understanding-dice-coefficient
    3. \n
  3. https://www.kaggle.com/code/bigironsphere/loss-function-library-keras-pytorch
    4. \n
  4. https://www.kaggle.com/code/iafoss/unet34-dice-0-87
    5. \n
  5. https://www.kaggle.com/code/dschettler8845/eda-hubmap-hpa-organ-segmentation
    6. \n
  6. https://www.kaggle.com/code/ekhtiar/resunet-a-baseline-on-tensorflow
    7. \n
  7. https://www.kaggle.com/code/vineeth1999/hubmap-eda-pytorch-efficientunet-offline-training
    8. \n
\n

Hope these reference notebooks and adjutant resources help one and all to onboard effectively. All the best and regards!

", "messages": [ { "id": 2254591, "postDate": "2023-05-11T05:25:12.330Z", "content": "

Hello all,

\n

Wishing you the best for the challenge! The sheer size of the data and the nature of the competition (code requirements and the execution time limit) is a gargantuan challenge for the participants. I hope the below adjutant resources regarding the competition metric helps one and all to onboard quickly and effectively-

\n
    \n
  1. https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient -- wikipedia link, mentioned in the overview page as well
    2. \n
  2. https://rosettacode.org/wiki/Sorensen%E2%80%93Dice_coefficient -- good explanatory article, I liked the code snippets with several languages
    3. \n
  3. https://www.mathworks.com/help/images/ref/dice.html -- mathworks article on this topic, terse and useful in my opinion
    4. \n
  4. https://stats.stackexchange.com/questions/195006/is-the-dice-coefficient-the-same-as-accuracy -- very useful article for beginners looking at this measure
    5. \n
  5. https://towardsdatascience.com/similarity-measures-and-graph-adjacency-with-sets-a33d16e527e1v -- this is a well written article explaining this metric quite well
    6. \n
\n

Kaggle notebooks using the metric

\n
    \n
  1. https://www.kaggle.com/code/dschettler8845/uwm-gi-tract-image-segmentation-eda
    2. \n
  2. https://www.kaggle.com/code/yerramvarun/understanding-dice-coefficient
    3. \n
  3. https://www.kaggle.com/code/bigironsphere/loss-function-library-keras-pytorch
    4. \n
  4. https://www.kaggle.com/code/iafoss/unet34-dice-0-87
    5. \n
  5. https://www.kaggle.com/code/dschettler8845/eda-hubmap-hpa-organ-segmentation
    6. \n
  6. https://www.kaggle.com/code/ekhtiar/resunet-a-baseline-on-tensorflow
    7. \n
  7. https://www.kaggle.com/code/vineeth1999/hubmap-eda-pytorch-efficientunet-offline-training
    8. \n
\n

Hope these reference notebooks and adjutant resources help one and all to onboard effectively. All the best and regards!

", "rawMarkdown": "Hello all, \n\nWishing you the best for the challenge! The sheer size of the data and the nature of the competition (code requirements and the execution time limit) is a gargantuan challenge for the participants. I hope the below adjutant resources regarding the competition metric helps one and all to onboard quickly and effectively- \n\n1. https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient -- wikipedia link, mentioned in the overview page as well\n2. https://rosettacode.org/wiki/Sorensen%E2%80%93Dice_coefficient -- good explanatory article, I liked the code snippets with several languages \n3. https://www.mathworks.com/help/images/ref/dice.html -- mathworks article on this topic, terse and useful in my opinion\n4. https://stats.stackexchange.com/questions/195006/is-the-dice-coefficient-the-same-as-accuracy -- very useful article for beginners looking at this measure \n5. https://towardsdatascience.com/similarity-measures-and-graph-adjacency-with-sets-a33d16e527e1v -- this is a well written article explaining this metric quite well\n\n**Kaggle notebooks using the metric**\n1. https://www.kaggle.com/code/dschettler8845/uwm-gi-tract-image-segmentation-eda\n2. https://www.kaggle.com/code/yerramvarun/understanding-dice-coefficient\n3. https://www.kaggle.com/code/bigironsphere/loss-function-library-keras-pytorch\n4. https://www.kaggle.com/code/iafoss/unet34-dice-0-87\n5. https://www.kaggle.com/code/dschettler8845/eda-hubmap-hpa-organ-segmentation\n6. https://www.kaggle.com/code/ekhtiar/resunet-a-baseline-on-tensorflow\n7. https://www.kaggle.com/code/vineeth1999/hubmap-eda-pytorch-efficientunet-offline-training\n\nHope these reference notebooks and adjutant resources help one and all to onboard effectively. All the best and regards!", "votes": 4 } ], "comments": [], "raw_markdown_by_id": { "2254591": "Hello all, \n\nWishing you the best for the challenge! The sheer size of the data and the nature of the competition (code requirements and the execution time limit) is a gargantuan challenge for the participants. I hope the below adjutant resources regarding the competition metric helps one and all to onboard quickly and effectively- \n\n1. https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient -- wikipedia link, mentioned in the overview page as well\n2. https://rosettacode.org/wiki/Sorensen%E2%80%93Dice_coefficient -- good explanatory article, I liked the code snippets with several languages \n3. https://www.mathworks.com/help/images/ref/dice.html -- mathworks article on this topic, terse and useful in my opinion\n4. https://stats.stackexchange.com/questions/195006/is-the-dice-coefficient-the-same-as-accuracy -- very useful article for beginners looking at this measure \n5. https://towardsdatascience.com/similarity-measures-and-graph-adjacency-with-sets-a33d16e527e1v -- this is a well written article explaining this metric quite well\n\n**Kaggle notebooks using the metric**\n1. https://www.kaggle.com/code/dschettler8845/uwm-gi-tract-image-segmentation-eda\n2. https://www.kaggle.com/code/yerramvarun/understanding-dice-coefficient\n3. https://www.kaggle.com/code/bigironsphere/loss-function-library-keras-pytorch\n4. https://www.kaggle.com/code/iafoss/unet34-dice-0-87\n5. https://www.kaggle.com/code/dschettler8845/eda-hubmap-hpa-organ-segmentation\n6. https://www.kaggle.com/code/ekhtiar/resunet-a-baseline-on-tensorflow\n7. https://www.kaggle.com/code/vineeth1999/hubmap-eda-pytorch-efficientunet-offline-training\n\nHope these reference notebooks and adjutant resources help one and all to onboard effectively. All the best and regards!" } }