def _postprocess(results,
result_mask_info,
output_height,
output_width,
mask_threshold=0.5):
"""
Post-process the output boxes for TensorMask.
The input images are often resized when entering an object detector.
As a result, we often need the outputs of the detector in a different
resolution from its inputs.
This function will postprocess the raw outputs of TensorMask
to produce outputs according to the desired output resolution.
Args:
results (Instances): the raw outputs from the detector.
`results.image_size` contains the input image resolution the detector sees.
This object might be modified in-place. Note that it does not contain the field
`pred_masks`, which is provided by another input `result_masks`.
result_mask_info (list[Tensor], Boxes): a pair of two items for mask related results.
The first item is a list of #detection tensors, each is the predicted masks.
The second item is the anchors corresponding to the predicted masks.
output_height, output_width: the desired output resolution.
Returns:
Instances: the postprocessed output from the model, based on the output resolution
"""
scale_x, scale_y = (output_width / results.image_size[1],
output_height / results.image_size[0])
results = Instances((output_height, output_width), **results.get_fields())
output_boxes = results.pred_boxes
output_boxes.tensor[:, 0::2] *= scale_x
output_boxes.tensor[:, 1::2] *= scale_y
output_boxes.clip(results.image_size)
inds_nonempty = output_boxes.nonempty()
results = results[inds_nonempty]
result_masks, result_anchors = result_mask_info
if result_masks:
result_anchors.tensor[:, 0::2] *= scale_x
result_anchors.tensor[:, 1::2] *= scale_y
result_masks = [
x for (i, x) in zip(inds_nonempty.tolist(), result_masks) if i
]
results.pred_masks = _paste_mask_lists_in_image(
result_masks,
result_anchors[inds_nonempty],
results.image_size,
threshold=mask_threshold,
)
return results
def detector_postprocess(results,
output_height,
output_width,
mask_threshold=0.5):
"""
Resize the output instances.
The input images are often resized when entering an object detector.
As a result, we often need the outputs of the detector in a different
resolution from its inputs.
This function will resize the raw outputs of an R-CNN detector
to produce outputs according to the desired output resolution.
Args:
results (Instances): the raw outputs from the detector.
`results.image_size` contains the input image resolution the detector sees.
This object might be modified in-place.
output_height, output_width: the desired output resolution.
Returns:
Instances: the resized output from the model, based on the output resolution
"""
scale_x, scale_y = (output_width / results.image_size[1],
output_height / results.image_size[0])
results = Instances((output_height, output_width), **results.get_fields())
if results.has("pred_boxes"):
output_boxes = results.pred_boxes
elif results.has("proposal_boxes"):
output_boxes = results.proposal_boxes
output_boxes.scale(scale_x, scale_y)
output_boxes.clip(results.image_size)
results = results[output_boxes.nonempty()]
if results.has("pred_masks"):
results.pred_masks = paste_masks_in_image(
results.pred_masks[:, 0, :, :], # N, 1, M, M
results.pred_boxes,
results.image_size,
threshold=mask_threshold,
)
if results.has("pred_keypoints"):
results.pred_keypoints[:, :, 0] *= scale_x
results.pred_keypoints[:, :, 1] *= scale_y
return results