Congrats to the winners!
\n\nFor the Best Intel Tools Usage award, we will announce separately.
\n\nWe've removed the cheaters that used multiple accounts to submit to this competition. If you think you are removed by mistake, please fill out this form to contact our compliance. Please note that if you or your teammate did use multiple accounts in any time during the competition, you have violated the rules, do NOT fill out this form, since you might lose your accounts completely.
", "messages": [ { "id": "195441", "postDate": "06/23/2017 16:05:34", "content": "Congrats to the winners!
\n\nFor the Best Intel Tools Usage award, we will announce separately.
\n\nWe've removed the cheaters that used multiple accounts to submit to this competition. If you think you are removed by mistake, please fill out this form to contact our compliance. Please note that if you or your teammate did use multiple accounts in any time during the competition, you have violated the rules, do NOT fill out this form, since you might lose your accounts completely.
", "rawMarkdown": "Congrats to the winners! \n\nFor the Best Intel Tools Usage award, we will announce separately. \n\nWe've removed the cheaters that used multiple accounts to submit to this competition. If you think you are removed by mistake, please fill out this [form][1] to contact our compliance. Please note that if you or your teammate did use multiple accounts in any time during the competition, you have violated the rules, do NOT fill out this form, since you might lose your accounts completely.\n\n [1]: https://www.kaggle.com/compliance", "votes": null }, { "id": "195508", "postDate": "06/23/2017 19:18:46", "content": "Can you verify whether or not it was acceptable to retrain the models in order to include the stage 1 test images of which the labels were published after stage 1 ended? \nFurther, was it acceptable to use stage 1 test data in training the models at all? (based on leaderboard mining) i.e. was it only allowable to train a model using the training and additional datasets?
", "rawMarkdown": "Can you verify whether or not it was acceptable to retrain the models in order to include the stage 1 test images of which the labels were published after stage 1 ended? \nFurther, was it acceptable to use stage 1 test data in training the models at all? (based on leaderboard mining) i.e. was it only allowable to train a model using the training and additional datasets?", "votes": null }, { "id": "195510", "postDate": "06/23/2017 19:24:02", "content": "Yes, in the FAQ, we specified that
\n\n\n", "rawMarkdown": "Yes, in the [FAQ][1], we specified that\n\n> You are allowed to re-train your model (including the stage one data),\n> but your code should not change.\n\n\n [1]: https://www.kaggle.com/c/intel-mobileodt-cervical-cancer-screening/discussion/32580", "votes": null }, { "id": "195629", "postDate": "06/24/2017 09:10:00", "content": "You are allowed to re-train your model (including the stage one data),\n but your code should not change.
\n
jee jee thanx... so maybe 52nd was not so bad for only using the first stage train data... :) [add facepalm here]... can't wait for the next image based challenge!
", "rawMarkdown": "jee jee thanx... so maybe 52nd was not so bad for only using the first stage train data... :) [add facepalm here]... can't wait for the next image based challenge!", "votes": null } ], "comments": [ { "id": 195508, "author_name": "monodavids", "author_url": "", "post_date": "06/23/2017 19:18:46", "content": "Can you verify whether or not it was acceptable to retrain the models in order to include the stage 1 test images of which the labels were published after stage 1 ended? \nFurther, was it acceptable to use stage 1 test data in training the models at all? (based on leaderboard mining) i.e. was it only allowable to train a model using the training and additional datasets?
", "votes": null, "replies": [ { "id": 195510, "author_name": "wendykan", "author_url": "", "post_date": "06/23/2017 19:24:02", "content": "Yes, in the FAQ, we specified that
\n\n\n", "votes": null, "replies": [] }, { "id": 195629, "author_name": "monodavids", "author_url": "", "post_date": "06/24/2017 09:10:00", "content": "You are allowed to re-train your model (including the stage one data),\n but your code should not change.
\n
jee jee thanx... so maybe 52nd was not so bad for only using the first stage train data... :) [add facepalm here]... can't wait for the next image based challenge!
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "195441": "Congrats to the winners! \n\nFor the Best Intel Tools Usage award, we will announce separately. \n\nWe've removed the cheaters that used multiple accounts to submit to this competition. If you think you are removed by mistake, please fill out this [form][1] to contact our compliance. Please note that if you or your teammate did use multiple accounts in any time during the competition, you have violated the rules, do NOT fill out this form, since you might lose your accounts completely.\n\n [1]: https://www.kaggle.com/compliance", "195508": "Can you verify whether or not it was acceptable to retrain the models in order to include the stage 1 test images of which the labels were published after stage 1 ended? \nFurther, was it acceptable to use stage 1 test data in training the models at all? (based on leaderboard mining) i.e. was it only allowable to train a model using the training and additional datasets?", "195510": "Yes, in the [FAQ][1], we specified that\n\n> You are allowed to re-train your model (including the stage one data),\n> but your code should not change.\n\n\n [1]: https://www.kaggle.com/c/intel-mobileodt-cervical-cancer-screening/discussion/32580", "195629": "jee jee thanx... so maybe 52nd was not so bad for only using the first stage train data... :) [add facepalm here]... can't wait for the next image based challenge!" }, "source": "meta" }