Assaf Singer
Assaf Singer
Here are two example visualization of predictions vs ground-truth trajectories for videos 2 & 3 in TAP-Vid Kinetics (I changed `plt.scatter` from diamond shape to plus sign for ground-truth trajectories,...
``` I1020 17:06:48.536417 47193737840832 supervised_point_prediction.py:972] eval batch: 115 I1020 17:06:48.542387 47193737840832 supervised_point_prediction.py:983] {'average_jaccard': Array(0.22719689, dtype=float32), 'average_pts_within_thresh': Array(0.3231358, dtype=float32), 'jaccard_1': Array(0.05189561, dtype=float32), 'jaccard_16': Array(0.40190077, dtype=float32), 'jaccard_2': Array(0.13956638, dtype=float32), 'jaccard_4': Array(0.23128213, dtype=float32),...
For each TAP-Vid DAVIS video I apply the following: - Place the frames (which are in 256x256 resolution) under color dir, as described in the preprocessing instructions. - Run `python...
Thinking of this situation, I wanted to ask , **would it be possible for you to provide the pre-trained weights for TAP-Vid DAVIS?** I think that would be the optimal...