vis_root (string): Root directory of images (e.g. coco/images/) ann_root (string): directory to store the annotation file

Resume from a checkpoint.

An inner training loop compatible with both epoch-based and iter-based training. When using epoch-based, training stops after one ep

compute distance between box corners to replace iou Args: crnr1, crnr2: Nx3 points of box corners in camera axis (y points down)

Concatenates multiple datasets into a single dataset. It supports may-style datasets and DataPipeline from WebDataset. Currently, does not s

Convert applicable model parameters to fp16

Create dataloaders for training and validation.

Args: clip (torch.tensor): Video clip to be cropped. Size is (C, T, H, W)

Generic functions to compute precision/recall for object detection for a single class. Input: pred: map of {img_id: [(bbo

points are XYZ RGB (RGB in 0-255), semantic label as nyu40 ids, instance label as 1-#instance, box as (cx,cy,cz,dx,dy,dz,semantic_label)

Get question ids that satisfy given filter conditions. default skips that filter :param imgIds (int array) : get question ids f

box_size is array(l,w,h), heading_angle is radius clockwise from pos x axis, center is xyz of box center output (8,3) array for 3D box cornde

Compute min and max coordinates for 3D bounding box Note: only for axis-aligned bounding boxes Input: corners: numpy array (8,3)

Compute min and max coordinates for 3D bounding box Note: only for axis-aligned bounding boxes Input: corners: numpy array (N,8,

Load from a finetuned checkpoint. This should expect no mismatch in the model keys and the checkpoint keys.

return a mask that is True for zero values and False for other values.

gt_pos: [N, 3]; ground truth position, in xyz (unit is meter) gt_rot: [N, 4]; ground truth roation, in xyzw (quaternion) pred_pos: [N, 3]

Normalize a numpy array of 3 component vectors shape=(n,3)

Extract the axis aligned box from a pcl or batch of pcls Args: points: Nx3 points or BxNx3 output is 6 dim: xyz pos of center and

Input is NxC, output is num_samplexC

Numpy function for softmax

r'''Given coordinates, and features (optionally labels), the function generates quantized (voxelized) coordinates. Args: coords (:att

Warmup the learning rate

Checks that `replacement`, which is intended to replace `original` is of the right type. The type is correct if it matches exactly or is one of a

Decodes a raw config value (e.g., from a yaml config files or command line argument) into a Python object.

Download annotation files if necessary. All the vision-language datasets should have annotations of unified format. storage_

Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.