suyashhchougule

> Do you follow the training instruction as shown in https://github.com/WongKinYiu/ScaledYOLOv4/tree/yolov4-tiny#training? yes I have added the details , please check

but as per https://github.com/AlexeyAB/darknet#:~:text=change%20line%20max_batches%20to%20(classes*2000%2C%20but%20not%20less%20than%20number%20of%20training%20images%20and%20not%20less%20than%206000)%2C%20f.e.%20max_batches%3D6000%20if%20you%20train%20for%203%20classes `max_batches = classes * 2000` which is in this case `80*2000 = 160000` , right ? or is it because for custom training we start training...

my understanding from paper is yolov4-tiny uses OSANet and yolov4-tiny-csp uses CSPOSANet . Is this interpretation correct ?

> Hi, @JackjackFan - how did you convert? I have a custom model Yolov5 5.0 and I am getting errors while running the code on my Jetson Xavier NX env...

@coder-xieshijie Uninstall the current version of the transformer and reinstall it from the source. i.e. `pip install git+https://github.com/huggingface/transformers.git `

try using NMS suppression

> I would like to express my gratitude for your hard work on the project. I came across a training script where you used the following code: > > ```python...

> you didn't specify the content of CSV, please provide that or explain how we can create our own. thanks! Did you get to know how to format custom dataset...