def test_image_pooler_scale_box_large_crop_scale_and_resize(self):
"""Crop bbox that is scaled, resize the cropped box"""
H, W = 398, 224
all_boxes = Boxes(
torch.Tensor([[50, 40, 100, 80], [150, 60, 200, 120]]))
image = rh.get_batched_inputs(1, (H, W), (H, W), all_boxes)[0]["image"]
boxes = bu.get_box_union(all_boxes)
img_pooler = image_pooler.ImagePooler(
resize_type="resize_shortest",
resize_short=48,
resize_max=180,
box_scale_factor=1.2,
).eval()
pooled_img, pooled_box, transforms = img_pooler(image, boxes.tensor)
self.assertEqual(pooled_img.shape, torch.Size([3, 48, 90]))
# bbox with scaling in the original space
orig_crop_box = transforms.inverse().apply_box(
[0, 0, pooled_img.shape[2], pooled_img.shape[1]])
self.assertArrayEqual(orig_crop_box, [[35, 32, 215, 128]])
# bbox without scaling in the original space
orig_boxes = transforms.inverse().apply_box(pooled_box)
self.assertArrayEqual(orig_boxes, boxes.tensor)
sub_boxes = rh.get_detected_instances_from_image([{
"image": pooled_img
}])[0].pred_boxes
# [[7.5, 4, 32.5, 24], [57.5, 14, 82.5, 44]]
self.assertArrayEqual(sub_boxes.tensor,
[[7, 4, 33, 24], [57, 14, 83, 44]])
def test_get_instances_from_image(self):
boxes = Boxes(torch.Tensor([[50, 40, 100, 80], [150, 60, 200, 120]]))
gt_kpts = torch.Tensor([75, 60, 1.0] * 21 +
[175, 90, 1.0] * 21).reshape(2, 21, 3)
batched_inputs = rh.get_batched_inputs(2, boxes=boxes)
instances = rh.get_detected_instances_from_image(batched_inputs)
self.assertEqual(len(instances), 2)
self.assertArrayEqual(instances[0].pred_boxes.tensor, boxes.tensor)
self.assertArrayEqual(instances[0].pred_keypoints, gt_kpts)
def test_get_instances_from_image_scale_image(self):
H, W = 398, 224
all_boxes = Boxes(
torch.Tensor([[50, 40, 100, 80], [150, 60, 200, 120]]))
image = rh.get_batched_inputs(1, (H, W), (H, W), all_boxes)[0]["image"]
boxes = rh.get_detected_instances_from_image([{
"image": image
}])[0].pred_boxes
self.assertArrayEqual(boxes.tensor, all_boxes.tensor)
# scale image by 0.5
scale_image = torch.nn.functional.interpolate(
torch.unsqueeze(image, 0),
scale_factor=(0.5, 0.5),
mode="bilinear",
align_corners=False,
recompute_scale_factor=False,
)[0]
sub_boxes = rh.get_detected_instances_from_image([{
"image": scale_image
}])[0].pred_boxes
self.assertArrayEqual(sub_boxes.tensor,
[[25, 20, 50, 40], [75, 30, 100, 60]])
# scale image by 0.75
scale_image = torch.nn.functional.interpolate(
torch.unsqueeze(image, 0),
scale_factor=(0.75, 0.75),
mode="bilinear",
align_corners=False,
recompute_scale_factor=False,
)[0]
sub_boxes = rh.get_detected_instances_from_image([{
"image": scale_image
}])[0].pred_boxes
# [[37.5, 30, 75, 60], [112.5, 45, 150, 90]])
self.assertArrayEqual(sub_boxes.tensor,
[[37, 30, 75, 60], [112, 45, 150, 90]])
def test_image_pooler_scale_box_large_crop_only(self):
"""Crop bbox"""
H, W = 398, 224
all_boxes = Boxes(
torch.Tensor([[50, 40, 100, 80], [150, 60, 200, 120]]))
image = rh.get_batched_inputs(1, (H, W), (H, W), all_boxes)[0]["image"]
boxes = bu.get_box_union(all_boxes)
self.assertArrayEqual(boxes.tensor, [[50, 40, 200, 120]])
img_pooler = image_pooler.ImagePooler(resize_type=None,
box_scale_factor=1.0).eval()
pooled_img, pooled_box, transforms = img_pooler(image, boxes.tensor)
self.assertEqual(pooled_img.shape, torch.Size([3, 80, 150]))
sub_boxes = rh.get_detected_instances_from_image([{
"image": pooled_img
}])[0].pred_boxes
self.assertArrayEqual(sub_boxes.tensor,
[[0, 0, 50, 40], [100, 20, 150, 80]])
def test_image_pooler_scale_box_large_crop_and_scale(self):
"""Crop bbox that is scaled"""
H, W = 398, 224
all_boxes = Boxes(
torch.Tensor([[50, 40, 100, 80], [150, 60, 200, 120]]))
image = rh.get_batched_inputs(1, (H, W), (H, W), all_boxes)[0]["image"]
boxes = bu.get_box_union(all_boxes)
img_pooler = image_pooler.ImagePooler(resize_type=None,
box_scale_factor=1.2).eval()
pooled_img, pooled_box, transforms = img_pooler(image, boxes.tensor)
self.assertEqual(pooled_img.shape, torch.Size([3, 96, 180]))
# bbox with scaling in the original space
orig_crop_box = transforms.inverse().apply_box(
[0, 0, pooled_img.shape[2], pooled_img.shape[1]])
self.assertArrayEqual(orig_crop_box, [[35, 32, 215, 128]])
sub_boxes = rh.get_detected_instances_from_image([{
"image": pooled_img
}])[0].pred_boxes
# gt_offset_xy = (50 - 35 = 15, 40 - 32 = 8)
self.assertArrayEqual(sub_boxes.tensor,
[[15, 8, 65, 48], [115, 28, 165, 88]])