MooreManor
MooreManor
When I'm switching to the previous tabs, I'll stop for a little time to check whether the page is what I want. And when the check time is over 750ms,...
 Hello! @panchul @maudzung I notice in the ball_xy annotations, it seems that not all of them are annotated because the len(ball_annots) is smaller than the actual frames. But some...
@zhihaolee I tried training CLIFF res50 from scratch. Here is my exp setting. I used 4 GPUS with syncbatchnorm, and the batch size for per GPU is 64. The dataset...
> To predict bounce points machine learning library for time series [sktime](https://www.sktime.org/en/stable/index.html) was used. Specifically, [TimeSeriesForestClassifier](https://github.com/ArtLabss/tennis-tracking/blob/90652b4547311423ea49c4195dde9da9a81f1893/clf.pkl) was trained on 3 variables: x, y coordinates of the ball and V for...
Hello! @mks0601 I am trying to reproduce three recipes based on Pose2Pose. I am not quite sure about the loss implementation. Is that the same as NeuralAnnot (i.e. same as...