Closed ankuPRK closed 4 years ago
Hi Prakhar, The ground truth for train and val was not released explicitly, but it should be fairly easy to generate that. Just preprocess the raw csv files or the generated features file to have ground truth in the format:
gt: Dict[int, np.ndarray] = {seq_id: traj_for_future_3_secs}
Eg. gt = {1: np.array([[1,2],[1,3],[1,4],....]), 2: np.ndarray([100, 200], [101, 200], ...)}
Okay got it, thanks!
I was able to find the raw ground truth, but not the ground truth pkl file for the validation set to run the simple evaluator given in readme:
$ python eval_forecasting_helper.py --metrics --gt <path/to/ground/truth/pkl/file> --forecast <path/to/forecasted/trajectories/pkl/file> --horizon 30 --obs_len 20 --miss_threshold 2 --features <path/to/test/features> --max_n_guesses 6
Could you please share a link to the same, or guide to how to generate it with raw data, without generating features.