The goal of this competition is to automatically recognize sounds from audio clips. This competition is similar to last year, but has a new metric, is multi-label, and has the requirement that inference be performed in Kernels.
\n\nHave Fun and Happy Kaggling!
", "messages": [ { "id": "507361", "postDate": "04/04/2019 15:36:50", "content": "The goal of this competition is to automatically recognize sounds from audio clips. This competition is similar to last year, but has a new metric, is multi-label, and has the requirement that inference be performed in Kernels.
\n\nHave Fun and Happy Kaggling!
", "rawMarkdown": "The goal of this competition is to automatically recognize sounds from audio clips. This competition is similar to [last year](https://www.kaggle.com/c/freesound-audio-tagging), but has a new metric, is multi-label, and has the requirement that inference be performed in Kernels.\n\nHave Fun and Happy Kaggling!", "votes": null }, { "id": "508807", "postDate": "04/06/2019 20:14:37", "content": "My first time, I'll try not to be the last. Anyway, I just sent a random output to check that everything was fine and I get 0.057. Not bad for random.
", "rawMarkdown": "My first time, I'll try not to be the last. Anyway, I just sent a random output to check that everything was fine and I get 0.057. Not bad for random.", "votes": null }, { "id": "514751", "postDate": "04/11/2019 22:13:33", "content": "Hi,\nwill the the stage 2 test set be smaller than the stage 1 test set?\nI am asking, in order to ensure that the kernel will not run longer than 4 hours for cpu and 1 hour for gpu on stage 2
", "rawMarkdown": "Hi,\nwill the the stage 2 test set be smaller than the stage 1 test set?\nI am asking, in order to ensure that the kernel will not run longer than 4 hours for cpu and 1 hour for gpu on stage 2", "votes": null }, { "id": "514752", "postDate": "04/11/2019 22:19:04", "content": "As described on the Data page https://www.kaggle.com/c/freesound-audio-tagging-2019/data \"The second-stage test set is approximately three times the size of the first. You should plan your kernel's memory, disk, and runtime footprint accordingly.\"
", "rawMarkdown": "As described on the Data page https://www.kaggle.com/c/freesound-audio-tagging-2019/data \"**The second-stage test set is approximately three times the size of the first**. You should plan your kernel's memory, disk, and runtime footprint accordingly.\"", "votes": null }, { "id": "524377", "postDate": "04/28/2019 16:09:13", "content": "One more question here - can we expect that duration of files in private LB set will be between 0.3-30 seconds?
", "rawMarkdown": "One more question here - can we expect that duration of files in private LB set will be between 0.3-30 seconds?", "votes": null }, { "id": "524498", "postDate": "04/29/2019 01:01:50", "content": "File size distribution should be similar in the private and public test sets (since they were randomly split from the same original test dataset)
", "rawMarkdown": "File size distribution should be similar in the private and public test sets (since they were randomly split from the same original test dataset)", "votes": null }, { "id": "524731", "postDate": "04/29/2019 12:33:46", "content": "I think it's important to know the length of the longest example because of GPU memory etc.
", "rawMarkdown": "I think it's important to know the length of the longest example because of GPU memory etc.", "votes": null }, { "id": "524808", "postDate": "04/29/2019 15:11:22", "content": "I believe the maximum length is the same (30 sec) as in the curated train set @fredericfont @eduardofonseca
", "rawMarkdown": "I believe the maximum length is the same (30 sec) as in the curated train set @fredericfont @eduardofonseca", "votes": null }, { "id": "526232", "postDate": "05/02/2019 16:36:21", "content": "Does any team need an additional member? This is my first competition, so I'll try to contribute whatever I can.
", "rawMarkdown": "Does any team need an additional member? This is my first competition, so I'll try to contribute whatever I can.", "votes": null }, { "id": "665688", "postDate": "11/05/2019 09:33:40", "content": "it will be fun idk i m late or not but seems quite interesting
", "rawMarkdown": "it will be fun idk i m late or not but seems quite interesting", "votes": null } ], "comments": [ { "id": 508807, "author_name": "hugoamorim", "author_url": "", "post_date": "04/06/2019 20:14:37", "content": "My first time, I'll try not to be the last. Anyway, I just sent a random output to check that everything was fine and I get 0.057. Not bad for random.
", "votes": null, "replies": [] }, { "id": 514751, "author_name": "dkaraflos", "author_url": "", "post_date": "04/11/2019 22:13:33", "content": "Hi,\nwill the the stage 2 test set be smaller than the stage 1 test set?\nI am asking, in order to ensure that the kernel will not run longer than 4 hours for cpu and 1 hour for gpu on stage 2
", "votes": null, "replies": [ { "id": 514752, "author_name": "plakal", "author_url": "", "post_date": "04/11/2019 22:19:04", "content": "As described on the Data page https://www.kaggle.com/c/freesound-audio-tagging-2019/data \"The second-stage test set is approximately three times the size of the first. You should plan your kernel's memory, disk, and runtime footprint accordingly.\"
", "votes": null, "replies": [] }, { "id": 524377, "author_name": "davids1992", "author_url": "", "post_date": "04/28/2019 16:09:13", "content": "One more question here - can we expect that duration of files in private LB set will be between 0.3-30 seconds?
", "votes": null, "replies": [] }, { "id": 524498, "author_name": "plakal", "author_url": "", "post_date": "04/29/2019 01:01:50", "content": "File size distribution should be similar in the private and public test sets (since they were randomly split from the same original test dataset)
", "votes": null, "replies": [] }, { "id": 524731, "author_name": "davids1992", "author_url": "", "post_date": "04/29/2019 12:33:46", "content": "I think it's important to know the length of the longest example because of GPU memory etc.
", "votes": null, "replies": [] }, { "id": 524808, "author_name": "plakal", "author_url": "", "post_date": "04/29/2019 15:11:22", "content": "I believe the maximum length is the same (30 sec) as in the curated train set @fredericfont @eduardofonseca
", "votes": null, "replies": [] } ] }, { "id": 526232, "author_name": "nsash1993gmailcom", "author_url": "", "post_date": "05/02/2019 16:36:21", "content": "Does any team need an additional member? This is my first competition, so I'll try to contribute whatever I can.
", "votes": null, "replies": [] }, { "id": 665688, "author_name": "kapiltiwari", "author_url": "", "post_date": "11/05/2019 09:33:40", "content": "it will be fun idk i m late or not but seems quite interesting
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "507361": "The goal of this competition is to automatically recognize sounds from audio clips. This competition is similar to [last year](https://www.kaggle.com/c/freesound-audio-tagging), but has a new metric, is multi-label, and has the requirement that inference be performed in Kernels.\n\nHave Fun and Happy Kaggling!", "508807": "My first time, I'll try not to be the last. Anyway, I just sent a random output to check that everything was fine and I get 0.057. Not bad for random.", "514751": "Hi,\nwill the the stage 2 test set be smaller than the stage 1 test set?\nI am asking, in order to ensure that the kernel will not run longer than 4 hours for cpu and 1 hour for gpu on stage 2", "514752": "As described on the Data page https://www.kaggle.com/c/freesound-audio-tagging-2019/data \"**The second-stage test set is approximately three times the size of the first**. You should plan your kernel's memory, disk, and runtime footprint accordingly.\"", "524377": "One more question here - can we expect that duration of files in private LB set will be between 0.3-30 seconds?", "524498": "File size distribution should be similar in the private and public test sets (since they were randomly split from the same original test dataset)", "524731": "I think it's important to know the length of the longest example because of GPU memory etc.", "524808": "I believe the maximum length is the same (30 sec) as in the curated train set @fredericfont @eduardofonseca", "526232": "Does any team need an additional member? This is my first competition, so I'll try to contribute whatever I can.", "665688": "it will be fun idk i m late or not but seems quite interesting" }, "source": "meta" }