-
Notifications
You must be signed in to change notification settings - Fork 15
/
postprocessing.py
80 lines (63 loc) · 3.25 KB
/
postprocessing.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
from torch.nn import functional as F
from detectron2.layers import paste_masks_in_image
from detectron2.structures import Instances
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"):
if results.pred_masks.shape[0]:
results.pred_masks = F.interpolate(input=results.pred_masks, size=results.image_size,mode="bilinear", align_corners=False).gt(0.5).squeeze(1)
#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 sem_seg_postprocess(result, img_size, output_height, output_width):
"""
Return semantic segmentation predictions in the original resolution.
The input images are often resized when entering semantic segmentor. Moreover, in same
cases, they also padded inside segmentor to be divisible by maximum network stride.
As a result, we often need the predictions of the segmentor in a different
resolution from its inputs.
Args:
result (Tensor): semantic segmentation prediction logits. A tensor of shape (C, H, W),
where C is the number of classes, and H, W are the height and width of the prediction.
img_size (tuple): image size that segmentor is taking as input.
output_height, output_width: the desired output resolution.
Returns:
semantic segmentation prediction (Tensor): A tensor of the shape
(C, output_height, output_width) that contains per-pixel soft predictions.
"""
result = result[:, : img_size[0], : img_size[1]].expand(1, -1, -1, -1)
result = F.interpolate(
result, size=(output_height, output_width), mode="bilinear", align_corners=False
)[0]
return result