This function returns the best GPU (with maximum GFLOPS)

This function returns the best GPU (with maximum GFLOPS)

General check for CUDA GPU SM Capabilities

/ General initialization call to pick the best CUDA Device inline int cutilChooseCudaDevice(int argc, char **argv) { cudaDeviceProp deviceProp; int de

database file containing information about preproscessed dataset

database file containing information about preproscessed dataset

database file containing information about preproscessed dataset

Compute the DICE loss, similar to generalized IOU for masks Args: inputs: A float tensor of arbitrary shape. The pred

Generic functions to compute precision/recall for object detection for multiple classes. Input: pred_all: map of {img_id:

input: xyz: (n, 3), offset: (b), new_offset: (b) output: idx: (m)

input: xyz: (n, 3), new_xyz: (m, 3), offset: (b), new_offset: (b) output: idx: (m, nsample), dist2: (m, nsample)

input: input: (n, c), idx : (m, nsample) output: (m, nsample, c)

input: input1: (n, c), input2: (n, c), idx: (n, nsample) output: (n, nsample, c)

input: input: (n, c), position: (n, nsample, c), weight : (n, nsample, c'), idx: (n, nsample) output: (n, c)

input: xyz: (m, 3), new_xyz: (n, 3), input: (m, c), offset: (b), new_offset: (b) output: (n, c)

input: xyz: (n, 3), offset: (b), new_offset: (b) output: idx: (m)

input: xyz: (n, 3), new_xyz: (m, 3), offset: (b), new_offset: (b) output: idx: (m, nsample), dist2: (m, nsample)

input: input: (n, c), idx : (m, nsample) output: (m, nsample, c)

input: input1: (n, c), input2: (n, c), idx: (n, nsample) output: (n, nsample, c)

input: input: (n, c), position: (n, nsample, c), weight : (n, nsample, c'), idx: (n, nsample) output: (n, c)

input: xyz: (m, 3), new_xyz: (n, 3), input: (m, c), offset: (b), new_offset: (b) output: (n, c)

input: xyz: (n, 3), offset: (b), new_offset: (b) output: idx: (m)

input: xyz: (n, 3), new_xyz: (m, 3), offset: (b), new_offset: (b) output: idx: (m, nsample), dist2: (m, nsample)

input: input: (n, c), idx : (m, nsample) output: (m, nsample, c)

input: q: (N, h, C//h), k: (N, h, C//h), index0: (M), index1: (M) output: output: [N, h, C//h]

input: q: (N, h, C//h), k: (N, h, C//h), index0: (M), index1: (M) output: output: [N, h, C//h]

input: attn: (M, h), v: (N, h, C//h), index0: (M), index1: (M) output: output: [N, h, C//h]

input: attn: (M, h), v: (N, h, C//h), index0: (M), index1: (M) output: output: [L, h, C//h]

input: q: (N, h, hdim), index: (M), table: (L, h, hdim, 3), rel_idx: (M, 3) output: output: [M, h]

input: q: (N, h, hdim), index_q: (M), k: (N, h, hdim), index_k: (M), table_q: (L, h, hdim, 3), table_k: (L, h, hdim, 3), rel_idx: (M, 3)

input: q: (N, h, hdim), index_q: (M), k: (N, h, hdim), index_k: (M), table_q: (L, h, hdim, 3), table_k: (L, h, hdim, 3), rel_idx: (M, 3)

input: attn: (M, h), v: (N, h, hdim), index0: (M), index1: (M), table: (L, h, hdim, 3), rel_idx: (M, 3) output: output: [N, h, hdim]

input: attn: (M, h), v: (N, h, hdim), index0_offsets: (M), index1: (M), table: (L, h, hdim, 3), rel_idx: (M, 3) output: output: [N, h

input: input1: (n, c), input2: (n, c), idx: (n, nsample) output: (n, nsample, c)

input: input: (n, c), position: (n, nsample, c), weight : (n, nsample, c'), idx: (n, nsample) output: (n, c)

input: xyz: (m, 3), new_xyz: (n, 3), input: (m, c), offset: (b), new_offset: (b) output: (n, c)

:param all_mask_preds: Dense mask predictions by all grids in a single batch :param all_mask_targets: Dense mask targets for all grid

Performs the matching Params: outputs: This is a dict that contains at least these entries: "pred_logits": Tenso