Hey everyone,Code: https://github.com/CuriousMonkey7/Bollworm-Counting-ChallengeBelow figure summarizes my approach. This approach is a bit similar to some of t... See more

It says 26 December but long time since them. Any update ?

First of all, I would like to thank Zindi, Wadhwani AI for this great competition.My solution is quite simple, just need a good understanding of the object dete... See more

First of all, I would like to thank Zindi, Wadhwani AI, FAIR Forward, and GIZ for this great competition.Congrats to all the winners!Since overfitting strategy... See more

Alhamdulillah , i survived from the shake-up ! here is my solution approach : ------------------------------------------------------------ -------------------... See more

Nothing special , just a yolov5l6 trained for 25 epoch with image size 1536. I split folds by mskfPart 2 i used a classifier which detects Images with no bollwo... See more

After the baseline, Every improvement I got was by analysing failing instances(Absolute difference >5) on the validation set. I also analysed failing cases o... See more

Shakeup is coming... Good luck to everyone

Hi guys,I am training an ensemble solution. Detectron2 + Custom part. At the moment, if calculated separately, score obtained from Detectron2 keeps to be around... See more

hello, my problem how to separate the training data and the test data. And also how we can match each image with his corresponding in the CSV file

When trying to submit results I am getting an error:Missing entries for IDs id_a93adfa0157cd5ac1ca7484f_pbw, id_7f59ebfcaab2aee756f446f8_abw, id_f8996520d67490e... See more

Does anyone still have the starter notebook from the Wadhwani AI Bollworm Classification Challenge by #ZindiWeekendz? If yes, I would really a link to the jupyt... See more

Hi all,If, like me, anyone wants to get the image annotations from the images_bboxes.csv file into .xml annotation files in the Pascal VOC format, have a look a... See more

https://colab.research.google.com/drive/1kL31xjofHI0l5uizFvrDsxpJC8pfIZOE?usp=sharingThis is a very nice technique to download and uncompress large files in Goo... See more

I am personally using MultilabelStratifiedKFold. It seems to be the be the most appropriate for this task. What are is your take on this ?

If you are in the top 10 at the time the leaderboard closes, we will email you to request your code. On receipt of email, you will have 48 hours to respond an... See more

Hello Zindians,Is there anyone who uploaded the dataset on a drive and could share the link with us ?

Hello guys. I found out that if we compare CSV files with bounding boxes and train_csv with worm count there are some discrepancies in the number of worms prese... See more

What is the prize? The video mentions 150 USD but the page mentions 1500 Euro. Can someone clarify?

Has anyone figured about incorrect annotations? The polygon co-ordinates are exceeding the height or width of the image. Example 1: Image - id_efa2d99456fa83bf... See more

Who has managed to convert the data into a coco dataset .... share the json please

For a dataset that's this large, I'm already out of disk space on google colab by just unzipping the images, Please what are some free platforms that allow user... See more

Why I am asking this is, Evaluation section of [Wadhwani AI Bollworm Counting Challenge] contains this staement "A single model MAE will be calculated using the... See more

CV : 2.63LB : 1.539833531

H guys, I am Akshay from India. I would like to team up with anyone with Leaderboard score above 3.0. I have lot of ideas but do not have good setup to implemen... See more