It’s been months since the competition ended, and as we all know, it didn’t end on the best note. We had hoped that the winners would open-source their solution... See more

First of all, I would like to congratulate the final winners. Your hard work really deserves to be appreciated.In principle, what I do is combine images and tab... See more

Dear Zindians,Well done on competiting in a particularly complex challenge!Zindi remains committed to delivering valuable solutions to our clients and partners.... See more

In my opinion, the best solution should consider both images and tabular data for estimating root volume. Quote 1:"Estimating root volume should involve both le... See more

Hello Zindian,An email was sent requesting everyone at positions 11 - 30 of the leaderboard to submit their code by Sunday midnight. So if you receive the email... See more

Hi everyone,I wanted to open up a discussion about the outcome of this competition and whether the winning solutions truly align with the original intent of the... See more

Hello, has anyone outside the top 10 received an email for code review? Is this a bug?

Hi Everyone, I share my solution with youFor this challenge I worked locally and didn’t use any GPU. The whole code (train and inference) runs in one minute.Giv... See more

My last submission has a score of HEXSnT4X ~7 hours ago Knowledge_Seeker101 sub19.csv lb 1.184581276 pb 1.18516145 — What's your best pb that you didn't sele... See more

Can any one explain me how do the ranking is madeBecause when the competition was closed, I was ranked 10th on private LB with the sub: - id : 6HqT23cL- 4 hour... See more

Congrats to the winners! When I review my sub, I found one submitted on day 1 that is really good. Let me know if it works for you. Public: 1.159004623 Private... See more

Anyways good competition, trust the CV

What a shakeup!!

Dear @jorgecasas118 as you mentioned in the webinar, the X axis (scan widths) are not constant mainly due to the scans being manual i.e. start and end positions... See more

I just changed my approach and got a really impressive CV score0.95xx CV 1.27xx LBMy old approach1.26xx CV 0.83xx LBNow I am even more confused 😅. Both are usi... See more

Has anyone tried dividing the image into 7 then working with the 7 parts as if they each were a plant. If so, how was the rmse

The characters in the pattern XXXXXXXX consist of random characters. This information is not relevant to you for this project. The S is the side of the scan. It... See more

https://youtu.be/rE-CVc8xjVsIf you like the video, please subscribe to my channel. Thanks!

Hi everyone,I hope you're all doing well. I have a couple of questions regarding our challenge: Segmentation Models: Did you use the provided segmentation mode... See more

i am using pretrained EfficientNet-B0 as the image encoder and 5 fold cross validation OOF RMSE: 1.50928179892321 LB 0.978123577Also any ideas for potential im... See more

On behalf of myself and all participants i ask Zindi @AJoel and @Amy_Bray to give a special prize for @snow for his/her contribution in this competion

https://youtu.be/8SXzC9SaGKI

can any one please explain the contant of train_labels folder

Do all image sets have 7 plants or some have less. And can i infer the number of plants from the test csv by looking at plant number

After merging all the image segments, I am getting empty train and test files. What could be the problem?