Evaluate the box proposals in predictions. Fill self._results with the metrics for "box_proposals" task.

Evaluate predictions. Fill self._results with the metrics of the tasks.

Uses the given `dataset_name` argument (instead of the names in cfg), because the standard practice is to evaluate each test set individually

Accumulate per image evaluation results and store the result in self.eval. Does not support changing parameter settings from those used by s

Convert annotation which can be polygons, uncompressed RLE, or RLE to binary mask. :return: binary mask (numpy 2D array)

input: grad_out: (m, c, nsample) output: (n, c), None

input: grad_out: (n, nsample, c) output: grad_input1: (n, c), grad_input2: (n, c)

input: grad_out: (n, c) output: grad_input: (n, c), grad_position: (n, nsample, c), grad_weight : (n, nsample, c')

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

input: grad_out: (m, c, nsample) output: (n, c), None

input: grad_out: (n, nsample, c) output: grad_input1: (n, c), grad_input2: (n, c)

input: grad_out: (n, c) output: grad_input: (n, c), grad_position: (n, nsample, c), grad_weight : (n, nsample, c')

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

input: grad_output: (N, h, C//h) output: (M, h), (N, h, C//h), None, None

input: grad_output: (N, h, C//h) output: (M, h), (N, h, C//h), None, None

input: grad_output: (N, h, C//h) output: (M, h), (N, h, C//h), None, None

input: grad_output: (L, h, C//h) output: (M, h), (N, h, C//h), None, None

input: grad_output: [M, h] output: (N, h, hdim), None, (L, h, hdim, 3), None

input: grad_output: [M, h] output: (N, h, hdim), None, (L, h, hdim, 3), None

input: grad_output: [M, h] output: (N, h, hdim), None, (L, h, hdim, 3), None

input: grad_output: (N, h, C//h) output: (M, h), (N, h, C//h), None, None, (L, h, hdim, 3), None

input: grad_output: (N, h, C//h) output: (M, h), (N, h, C//h), None, None, (L, h, hdim, 3), None

input: grad_out: (n, nsample, c) output: grad_input1: (n, c), grad_input2: (n, c)

input: grad_out: (n, c) output: grad_input: (n, c), grad_position: (n, nsample, c), grad_weight : (n, nsample, c')

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

input: grad_out: (n, c) output: grad_input: (n, c), grad_position: (n, nsample, c), grad_weight : (n, nsample, c')

input: grad_out: (n, nsample, c) output: grad_input1: (n, c), grad_input2: (n, c)

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

input: grad_output: (n, g, c) output: grad_weight: (m, g), grad_value: (n, g, c), none, none

Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor with t

Calculates prototypes from labels. This function calculates prototypes (mean direction) from embedding features for each label. This function

sumary_line Keyword arguments: masks: N, V, H, W labels: N returns: V, H, W