tapnet
tapnet copied to clipboard
google-deepmind
Tracking Any Point (TAP)
I downloaded tapir_checkpoint_panning.npy from the link provided, but it didn't load. I printed ckpt_state.keys() in the restore function in experiment_utils.py and found only 'params' and 'state' in the key of...
I am running [this notebook](https://github.com/google-deepmind/tapnet/blob/main/colabs/tapir_clustering.ipynb) for RoboTAP clustering. After computing the clusters, I am running the following cell: ```py separation_visibility_trim = clustered['separation_visibility'] separation_tracks_trim = clustered['separation_tracks'] pointtrack_video = viz_utils.plot_tracks_v2( (demo_videos[demo_episode_ids[0]]).astype(np.uint8), separation_tracks_trim[demo_episode_ids[0]],...
Is there any script for training TAPIR pytorch version?
I want to track points across many short horizon videos of, say, dimension (8, 256, 256, 3). Suppose I have B such videos and I want to track the same...
Hello, Thanks for the great work on BootsTAP and for releasing the pytorch version! Are there any plans on releasing the training dataset of real videos used in BootsTAP? Thanks...
Could you please upload the pretrained weights for the PyTorch version of online Tapir/BootsTapir, if available? or could you recommend how we can utilize the PyTorch implementation of Tapir/BootsTapir in...
I followed all of the instructions titled "Live Demo" of README.md, including the installation of dependencies, and updating the PYTHONPATH. However, I get the following error when I run `python3...
When I try to use lower version of Pytorch such as 2.0.0 ,1.13.0 and so on，the checkpoint "bootstapir_checkpoint.pt" doesn't work correctly. The error shows below： --------------------------------------------------------------------------- RuntimeError Traceback (most recent...
My configure of Python package is jax == 0.4.13 jaxlib == 0.4.13+cu12+cudnn89 My Hardware is Nvidia-H800 On Ubuntu20.04 LTS x86_64 When I try to run inference of TAPNET or TAPIR...
While making the torch TAPIR model compatible with _Torchscript tracing_ is easy by changing `TAPIR.forward()` in https://github.com/google-deepmind/tapnet/blob/main/torch/tapir_model.py#L196-L209 from ``` out = dict( occlusion=torch.mean( torch.stack(trajectories['occlusion'][p::p]), dim=0 ), tracks=torch.mean(torch.stack(trajectories['tracks'][p::p]), dim=0), expected_dist=torch.mean( torch.stack(trajectories['expected_dist'][p::p]),...
