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
def postprocess(self, results, output_height, output_width, resized_in_h,
resized_in_w, padded_im_h, padded_im_w):
scale_x, scale_y = (output_width / resized_in_w,
output_height / resized_in_h)
# gather detection result to Instances
results = Instances((output_height, output_width),
**results.get_fields())
# scale detection box results from resized_padded_image space to source image space and clip
output_boxes = results.pred_boxes
output_boxes.scale(scale_x, scale_y)
output_boxes.clip(results.image_size)
# filter empty detection in source image space
results = results[output_boxes.nonempty()]
if results.has("pred_global_logits"):
mask_h, mask_w = results.pred_global_logits.shape[-2:]
factor_h = padded_im_h // mask_h
factor_w = padded_im_w // mask_w
assert factor_h == factor_w
factor = factor_h
# aligned upsample instances mask to resized_padded_image shape
pred_global_masks = aligned_bilinear(
results.pred_global_logits.sigmoid(), factor)
pred_global_masks = pred_global_masks[:, :, :resized_in_h, :
resized_in_w]
# scale mask from resized_image shape to source image shape
# this is a inverse procedure of opencv or PIL interpolation
# which align_corners is False
pred_global_masks = F.interpolate(pred_global_masks,
size=(output_height,
output_width),
mode="bilinear",
align_corners=False)
pred_global_masks = pred_global_masks[:, 0, :, :]
# filter out the pred masks with low confidence score
results.pred_masks = pred_global_masks > self.infer_mask_threshold
return results
