valentin-fngr

> I solved it by adding "**kwargs" to the forward() function in the TransformerBatchNormEncoderLayer class.. this solves the issue that the argument 'is_casual' is no longer expected in the function...

if you know where the ball was hit and where the ball fell after the hit, given the dimension of the court, you can estimate the ball speed.

Not an active contributor but here is how I would deal with it for now (as you can see, it can take up to weeks before getting an answer from...

@sirrtt @PopGreen69 HI both. I gave up on that because it was way too complex to setup. I instead went for using a classic TSN recognition network with a sliding...

Yes but you will likely need to create a Yolov8 API under /detector. You can simply train a yolov8 from ultralytics, write a similar code as the yolo API in...

Author needs to confirm but from my understanding, the 0 and 1 are between [-1, 1] and the 2 is the keypoint confidence score.