{ "id": 219375, "title": "Complete detail of predictionstring of sample_submission.csv with example.", "url": "/competitions/hpa-single-cell-image-classification/discussion/219375", "author_name": "satvik patel", "post_date": "2021-02-14T17:17:57.378000", "votes": 1, "comment_count": 5, "views": 0, "content": "

Hello All,

\n

I am not understanding what is the predictionstring of sample_submission.csv.
\nCan any one describe what is the predictionstring : \"0 1 eNoLCAgIMAEABJkBdQ==\" include with example?
\nIs this string is encripted?
\nWhat is the \"0 1\" , \"eNoLCAgIMAEABJkBdQ==\"?

", "messages": [ { "id": 1201520, "postDate": "2021-02-15T13:09:26.840Z", "content": "

In addition to the comments by Kaizaburo. Please find my answer below which I also shared in replying to your comment on the Welcome to the 2nd HPA discussion post.

\n
\n

Please see this page for more information on the submission format details.

\n
\n

0 is the predicted class-label corresponding to Nucleoplasm

\n1 is the confidence of the predicted class label Nucleoplasm

\neNoLCAgIMA...EABJkBdQ== is the RLE, ZLIB compressed and Base64 encoded segmentation mask for the cell we are predicting on (that we are saying has the Nucleoplasm class).

\n
\n

FROM THE LINK ABOVE

\n

For each image in the test set, you must predict a list of instance segmentation masks and their associated detection score (Confidence)

\n

The binary segmentation masks are run-length encoded (RLE), zlib compressed, and base64 encoded to be used in text format as EncodedMask. Specifically, we use the Coco masks RLE encoding/decoding (see the encode method of COCO’s mask API), the zlib compression/decompression (RFC1950), and vanilla base64 encoding.

\n
\n
", "rawMarkdown": "In addition to the comments by *Kaizaburo*. Please find my answer below which I also shared in replying to your comment on the *Welcome to the 2nd HPA* discussion post.\n\n---\n\nPlease see [**this page**](https://www.kaggle.com/c/hpa-single-cell-image-classification/overview/evaluation) for more information on the submission format details.\n\n---\n\n**`0`** is the predicted class-label corresponding to **`Nucleoplasm`**
\n**`1`** is the **confidence** of the predicted class label **`Nucleoplasm`**
\n**`eNoLCAgIMA...EABJkBdQ==`** is the RLE, ZLIB compressed and Base64 encoded segmentation mask for the cell we are predicting on (that we are saying has the **`Nucleoplasm`** class).\n\n> ***FROM THE LINK ABOVE***\n>\n>*For each image in the test set, you must predict a list of instance segmentation masks and their associated detection score (Confidence)*\n>\n>*The binary segmentation masks are run-length encoded (RLE), zlib compressed, and base64 encoded to be used in text format as EncodedMask. Specifically, we use the Coco masks RLE encoding/decoding (see the encode method of COCO’s mask API), the zlib compression/decompression (RFC1950), and vanilla base64 encoding.*\n\n---", "votes": 3, "replies": [ { "id": 1213360, "postDate": "2021-02-22T04:41:47.343Z", "content": "

Thank you so much @dschettler8845 for your informative comment.

", "rawMarkdown": "Thank you so much @dschettler8845 for your informative comment. " } ] }, { "id": 1200449, "postDate": "2021-02-14T17:17:57.380Z", "content": "

Hello All,

\n

I am not understanding what is the predictionstring of sample_submission.csv.
\nCan any one describe what is the predictionstring : \"0 1 eNoLCAgIMAEABJkBdQ==\" include with example?
\nIs this string is encripted?
\nWhat is the \"0 1\" , \"eNoLCAgIMAEABJkBdQ==\"?

", "rawMarkdown": "Hello All,\n\nI am not understanding what is the predictionstring of sample_submission.csv. \nCan any one describe what is the predictionstring : \"0 1 eNoLCAgIMAEABJkBdQ==\" include with example?\nIs this string is encripted?\nWhat is the \"0 1\" , \"eNoLCAgIMAEABJkBdQ==\"?", "votes": 1 }, { "id": 1201150, "postDate": "2021-02-15T07:43:27.383Z", "content": "

See https://www.kaggle.com/c/hpa-single-cell-image-classification/overview/evaluation

\n
\n

The binary segmentation masks are run-length encoded (RLE), zlib compressed, and base64 encoded to be used in text format as EncodedMask. Specifically, we use the Coco masks RLE encoding/decoding (see the encode method of COCO’s mask API), the zlib compression/decompression (RFC1950), and vanilla base64 encoding.

\n
", "rawMarkdown": "See https://www.kaggle.com/c/hpa-single-cell-image-classification/overview/evaluation\n> The binary segmentation masks are run-length encoded (RLE), zlib compressed, and base64 encoded to be used in text format as EncodedMask. Specifically, we use the Coco masks RLE encoding/decoding (see the encode method of COCO’s mask API), the zlib compression/decompression (RFC1950), and vanilla base64 encoding.\n", "votes": 2, "replies": [ { "id": 1213423, "postDate": "2021-02-22T05:36:28.437Z", "content": "

Thank you very much @zaburo for your additional information.

", "rawMarkdown": "Thank you very much @zaburo for your additional information." } ] }, { "id": 1230206, "postDate": "2021-03-07T22:02:07.470Z", "content": "

Hi, I have shared a notebook showing decoding from the predictionstring:
\nhttps://www.kaggle.com/philiphucklesby/decoding-masks-from-the-rle-string

", "rawMarkdown": "Hi, I have shared a notebook showing decoding from the predictionstring:\nhttps://www.kaggle.com/philiphucklesby/decoding-masks-from-the-rle-string" } ], "comments": [ { "id": 1201520, "author_name": "Darien Schettler", "author_url": "", "post_date": "2021-02-15T13:09:26.840000", "content": "

In addition to the comments by Kaizaburo. Please find my answer below which I also shared in replying to your comment on the Welcome to the 2nd HPA discussion post.

\n
\n

Please see this page for more information on the submission format details.

\n
\n

0 is the predicted class-label corresponding to Nucleoplasm

\n1 is the confidence of the predicted class label Nucleoplasm

\neNoLCAgIMA...EABJkBdQ== is the RLE, ZLIB compressed and Base64 encoded segmentation mask for the cell we are predicting on (that we are saying has the Nucleoplasm class).

\n
\n

FROM THE LINK ABOVE

\n

For each image in the test set, you must predict a list of instance segmentation masks and their associated detection score (Confidence)

\n

The binary segmentation masks are run-length encoded (RLE), zlib compressed, and base64 encoded to be used in text format as EncodedMask. Specifically, we use the Coco masks RLE encoding/decoding (see the encode method of COCO’s mask API), the zlib compression/decompression (RFC1950), and vanilla base64 encoding.

\n
\n
", "votes": 3, "replies": [ { "id": 1213360, "author_name": "satvik patel", "author_url": "", "post_date": "2021-02-22T04:41:47.343000", "content": "

Thank you so much @dschettler8845 for your informative comment.

", "votes": 0, "replies": [] } ] }, { "id": 1201150, "author_name": "KaizaburoChubachi", "author_url": "", "post_date": "2021-02-15T07:43:27.383000", "content": "

See https://www.kaggle.com/c/hpa-single-cell-image-classification/overview/evaluation

\n
\n

The binary segmentation masks are run-length encoded (RLE), zlib compressed, and base64 encoded to be used in text format as EncodedMask. Specifically, we use the Coco masks RLE encoding/decoding (see the encode method of COCO’s mask API), the zlib compression/decompression (RFC1950), and vanilla base64 encoding.

\n
", "votes": 2, "replies": [ { "id": 1213423, "author_name": "satvik patel", "author_url": "", "post_date": "2021-02-22T05:36:28.437000", "content": "

Thank you very much @zaburo for your additional information.

", "votes": 0, "replies": [] } ] }, { "id": 1230206, "author_name": "Philip Hucklesby", "author_url": "", "post_date": "2021-03-07T22:02:07.470000", "content": "

Hi, I have shared a notebook showing decoding from the predictionstring:
\nhttps://www.kaggle.com/philiphucklesby/decoding-masks-from-the-rle-string

", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "1201520": "In addition to the comments by *Kaizaburo*. Please find my answer below which I also shared in replying to your comment on the *Welcome to the 2nd HPA* discussion post.\n\n---\n\nPlease see [**this page**](https://www.kaggle.com/c/hpa-single-cell-image-classification/overview/evaluation) for more information on the submission format details.\n\n---\n\n**`0`** is the predicted class-label corresponding to **`Nucleoplasm`**
\n**`1`** is the **confidence** of the predicted class label **`Nucleoplasm`**
\n**`eNoLCAgIMA...EABJkBdQ==`** is the RLE, ZLIB compressed and Base64 encoded segmentation mask for the cell we are predicting on (that we are saying has the **`Nucleoplasm`** class).\n\n> ***FROM THE LINK ABOVE***\n>\n>*For each image in the test set, you must predict a list of instance segmentation masks and their associated detection score (Confidence)*\n>\n>*The binary segmentation masks are run-length encoded (RLE), zlib compressed, and base64 encoded to be used in text format as EncodedMask. Specifically, we use the Coco masks RLE encoding/decoding (see the encode method of COCO’s mask API), the zlib compression/decompression (RFC1950), and vanilla base64 encoding.*\n\n---", "1200449": "Hello All,\n\nI am not understanding what is the predictionstring of sample_submission.csv. \nCan any one describe what is the predictionstring : \"0 1 eNoLCAgIMAEABJkBdQ==\" include with example?\nIs this string is encripted?\nWhat is the \"0 1\" , \"eNoLCAgIMAEABJkBdQ==\"?", "1201150": "See https://www.kaggle.com/c/hpa-single-cell-image-classification/overview/evaluation\n> The binary segmentation masks are run-length encoded (RLE), zlib compressed, and base64 encoded to be used in text format as EncodedMask. Specifically, we use the Coco masks RLE encoding/decoding (see the encode method of COCO’s mask API), the zlib compression/decompression (RFC1950), and vanilla base64 encoding.\n", "1230206": "Hi, I have shared a notebook showing decoding from the predictionstring:\nhttps://www.kaggle.com/philiphucklesby/decoding-masks-from-the-rle-string" } }