Customized static method to create an instance of the model wrapper from command line arguments. Decorated by `click.command()`

Split the input into small patches with sliding window.

Return a normalization layer.

Return file-like object for 'name'. name is a string for the file name within the ZIP file, or a ZipInfo object. mode should

Load model from file. Args: path (str): file path

Transform 2d or 3d points @pts: (...,N_pts,3) @tf: (...,4,4)

Load a pretrained model.

Load a model from a checkpoint file. ### Parameters: - `pretrained_model_name_or_path`: path to the checkpoint file or repo

xyz can be (B T N 3) or (B T 3 H W) or (B N 3)

Encode the image. Args: image (Union[torch.Tensor, list[Image.Image]]): The image to encode Returns:

xyz can be (B T N 3) or (B T 3 H W) or (B N 3)

Copmute pose from given pts to self.pcd @pts: (N,3) np array, downsampled scene points

Apply scaled dot product attention. Args: qkv (torch.Tensor): A [N, L, 3, H, C] tensor containing Qs, Ks, and Vs.

Create configs and perform basic setups.

Extract some coefficients at specified timesteps, then reshape to [batch_size, 1, 1, 1, 1, ...] for broadcasting purposes.

Wrapper for grid_sample, uses pixel coordinates

Get a spatial cache.

Get a spatial cache.

Links the output of the source node to the input of the destination node. If the source or destination node is None, the pipeline's i

Merge the patched input into a image with sliding window.

Preprocess image tensor(s) to target size with crop or pad mode. Args: img_tensor (torch.Tensor): Image tensor of shape (C, H, W) or