The final submission is against 12 images. Anyone with Bengali knowledge can populate the graheme, consonant and vowel diacritics manually in the submission file against these 12 images. How does the competition ensure that the results our outcome of model prediction. Shall we be provided with more test data for final submission?
", "messages": [ { "id": "731944", "postDate": "01/29/2020 09:29:09", "content": "The final submission is against 12 images. Anyone with Bengali knowledge can populate the graheme, consonant and vowel diacritics manually in the submission file against these 12 images. How does the competition ensure that the results our outcome of model prediction. Shall we be provided with more test data for final submission?
", "rawMarkdown": "The final submission is against 12 images. Anyone with Bengali knowledge can populate the graheme, consonant and vowel diacritics manually in the submission file against these 12 images. How does the competition ensure that the results our outcome of model prediction. Shall we be provided with more test data for final submission?", "votes": null }, { "id": "731949", "postDate": "01/29/2020 09:40:28", "content": "Please refer to https://www.kaggle.com/c/bengaliai-cv19/data
\n\n\n", "rawMarkdown": "Please refer to https://www.kaggle.com/c/bengaliai-cv19/data\n\n> This is a synchronous rerun code competition, you can assume that the complete test set will contain essentially the same size and number of images as the training set. Consider performing inference on just one batch at a time to avoid memory errors. Only the first few rows/images in the test set and sample submission files can be downloaded. These samples provided so you can review the basic structure of the files and to ensure consistency between the publicly available set of file names and those your code will have access to while it is being rerun for scoring.", "votes": null }, { "id": "732065", "postDate": "01/29/2020 13:01:03", "content": "This is a synchronous rerun code competition, you can assume that the complete test set will contain essentially the same size and number of images as the training set. Consider performing inference on just one batch at a time to avoid memory errors. Only the first few rows/images in the test set and sample submission files can be downloaded. These samples provided so you can review the basic structure of the files and to ensure consistency between the publicly available set of file names and those your code will have access to while it is being rerun for scoring.
\n
No this is not the case in final submission the test images are replaced with 2 lack images. So you will be tested on 2 lack images rather than 12 images.
", "rawMarkdown": "No this is not the case in final submission the test images are replaced with 2 lack images. So you will be tested on 2 lack images rather than 12 images.", "votes": null } ], "comments": [ { "id": 731949, "author_name": "appian", "author_url": "", "post_date": "01/29/2020 09:40:28", "content": "Please refer to https://www.kaggle.com/c/bengaliai-cv19/data
\n\n\n", "votes": null, "replies": [] }, { "id": 732065, "author_name": "amit9484", "author_url": "", "post_date": "01/29/2020 13:01:03", "content": "This is a synchronous rerun code competition, you can assume that the complete test set will contain essentially the same size and number of images as the training set. Consider performing inference on just one batch at a time to avoid memory errors. Only the first few rows/images in the test set and sample submission files can be downloaded. These samples provided so you can review the basic structure of the files and to ensure consistency between the publicly available set of file names and those your code will have access to while it is being rerun for scoring.
\n
No this is not the case in final submission the test images are replaced with 2 lack images. So you will be tested on 2 lack images rather than 12 images.
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "731944": "The final submission is against 12 images. Anyone with Bengali knowledge can populate the graheme, consonant and vowel diacritics manually in the submission file against these 12 images. How does the competition ensure that the results our outcome of model prediction. Shall we be provided with more test data for final submission?", "731949": "Please refer to https://www.kaggle.com/c/bengaliai-cv19/data\n\n> This is a synchronous rerun code competition, you can assume that the complete test set will contain essentially the same size and number of images as the training set. Consider performing inference on just one batch at a time to avoid memory errors. Only the first few rows/images in the test set and sample submission files can be downloaded. These samples provided so you can review the basic structure of the files and to ensure consistency between the publicly available set of file names and those your code will have access to while it is being rerun for scoring.", "732065": "No this is not the case in final submission the test images are replaced with 2 lack images. So you will be tested on 2 lack images rather than 12 images." }, "source": "meta" }