It seems the competition deadline has passed days ago, but the Leaderboard wasn't finilized. Are there any issues preventing the organizers from finishing up th... See more

First of all, I would like to thank the organizers of this fantastic competition. This is my first time on Zindi. Hopefully it won't be the last! Main idea We c... See more

Preprocessing:- Delete images without annotations- Delete mal annoted images (3 images). bbox is [x,y,w,h], if the area of the bbox which is a rectangle is null... See more

Congratulations to all winners!!! This competition was amazingHere is my solution (PUBLIC 0.330434782 PRIVATE 0.322933643)Preprocessing:- Delete images without... See more

First of all, I joined the competition 10 days before the deadline and decided to go to with a segmentation approach. Fun data to play around with and was still... See more

The Arm UNICEF Disaster Vulnerability Challenge was a very interesting competition. I learnt a lot. Tried a lot of models; Yolo, Faster RCNN with several hyperp... See more

Hi everyone,I am just wondering if it is a mistake from my side or something else, but after splitting data to same split as train/test and calculating the MAE... See more

Hey, guys the data is too large for me upload, has anyone uploaded it as a private kaggle dataset? Thanks a lot

the current evaluation metric doesn't care about the type of house detected in the image, only about the count of houses in the image, how does this help in dif... See more

Can we provide the exact formula for the mean absolute error calculation used for the test score? It seems like it does not appear to be likely the same magnitu... See more

Hello, I am hoping someone can help advise me on handling the class imbalances. I am using DETR, but I am not sure how I can 'weight' the lesser classes to be h... See more

I'm busy with another competition now, but if anyone finds any use in my code I'd be glad to think it has been helpful. I was inspired initially by @rashid0784'... See more

Thank you for any help here! This is my first Object Detection contest and I am currently experimenting with a Pytorch Implimentation of RetinaNet.Can I treat t... See more

In the data there are images which are 500x500 and images 1000x1000. I normalized the bbox column by dividing it for 500 for 500x500 images and dividing it for... See more

Hello all,I do not fully understand the following rule: 'If the challenge is a computer vision challenge, image metadata (Image size, aspect ratio, pixel count,... See more

Wondering what CVs people are getting in this competition. Mine is CV = 0.4656 LB = 0.308695652

Hello everyone,I've created a notebook and uploaded it to Kaggle for your use. In this notebook, I used DETR for object detection and included code to convert t... See more

If someone interested I made a script that convert train.csv and images folder to yolo format. You can split train and validation with indexes: https://github.c... See more

Missing entries for IDs id_uawi0k5spci5_1, id_uawi0k5spci5_3, id_ba566jv4xzln_3, id_4lrqmvmmgier_2, and id_4lrqmvmmgier_3: I get this error when I upload a subm... See more

what's the minimum box loss value you ever got during training

Am I to label the data or those someone please have a labelled version of the dataset I can use , as I just recently joined

Hi!! Can i re-labeled this dataset? i wanna adjust the coordinate of the bounding box

I noticed on the rules that the use of other datasets is prohibited and using a pre-trained model does imply leveraging knowledge gained from another dataset, a... See more

Hello !I started using PyTorch to take part in more data science competitions and I was able to gather some tricks to make it run faster. I thought it may be of... See more

Hello everyone,I've experimented with YOLOV8 and YOLOV9, but I've found that YOLO struggles with detecting small objects effectively. I'm curious about the appr... See more