Last competition gave the number of test set files, and had the requirement \"Your model must also perform inference with less than 100 milliseconds of latency per video on average and use less than 40 MB of storage space. Expect to see approximately 40,000 videos in the test set. We allow an additional 10 minute buffer for loading the data and miscellaneous overhead.\"
\nFor this competition, around how many files? It just says \"Your model must also perform inference in less than 5 hours and use less than 40 MB of storage space. Expect to see approximately 35 hours of video in the test set.\" but hours of video doesn't really have much meaning in relation to landmark files.
\nAnyone have personal estimates based on train data inference time compared with total submission time by manually monitoring?
", "messages": [ { "id": 2295383, "postDate": "2023-06-10T21:33:12.700Z", "content": "Last competition gave the number of test set files, and had the requirement \"Your model must also perform inference with less than 100 milliseconds of latency per video on average and use less than 40 MB of storage space. Expect to see approximately 40,000 videos in the test set. We allow an additional 10 minute buffer for loading the data and miscellaneous overhead.\"
\nFor this competition, around how many files? It just says \"Your model must also perform inference in less than 5 hours and use less than 40 MB of storage space. Expect to see approximately 35 hours of video in the test set.\" but hours of video doesn't really have much meaning in relation to landmark files.
\nAnyone have personal estimates based on train data inference time compared with total submission time by manually monitoring?
", "rawMarkdown": "Last competition gave the number of test set files, and had the requirement \"Your model must also perform inference with less than 100 milliseconds of latency per video on average and use less than 40 MB of storage space. Expect to see approximately 40,000 videos in the test set. We allow an additional 10 minute buffer for loading the data and miscellaneous overhead.\"\n\nFor this competition, around how many files? It just says \"Your model must also perform inference in less than 5 hours and use less than 40 MB of storage space. Expect to see approximately 35 hours of video in the test set.\" but hours of video doesn't really have much meaning in relation to landmark files.\n\nAnyone have personal estimates based on train data inference time compared with total submission time by manually monitoring?", "votes": 1 }, { "id": 2295385, "postDate": "2023-06-10T21:46:30.743Z", "content": "\n~0.6-0.7 seconds
", "rawMarkdown": "[click me](https://www.kaggle.com/competitions/asl-fingerspelling/discussion/409722#2276907)\n\n~0.6-0.7 seconds", "votes": 2 } ], "comments": [ { "id": 2295385, "author_name": "Kolya Forrat", "author_url": "", "post_date": "2023-06-10T21:46:30.743000", "content": "\n~0.6-0.7 seconds
", "votes": 2, "replies": [] } ], "raw_markdown_by_id": { "2295383": "Last competition gave the number of test set files, and had the requirement \"Your model must also perform inference with less than 100 milliseconds of latency per video on average and use less than 40 MB of storage space. Expect to see approximately 40,000 videos in the test set. We allow an additional 10 minute buffer for loading the data and miscellaneous overhead.\"\n\nFor this competition, around how many files? It just says \"Your model must also perform inference in less than 5 hours and use less than 40 MB of storage space. Expect to see approximately 35 hours of video in the test set.\" but hours of video doesn't really have much meaning in relation to landmark files.\n\nAnyone have personal estimates based on train data inference time compared with total submission time by manually monitoring?", "2295385": "[click me](https://www.kaggle.com/competitions/asl-fingerspelling/discussion/409722#2276907)\n\n~0.6-0.7 seconds" } }