Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

remove batch_dims from make bounding boxes and detection masks #7855

Merged
merged 3 commits into from
Aug 18, 2023
Merged

remove batch_dims from make bounding boxes and detection masks #7855

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
905b790
remove batch_dims from make bounding boxes and detection masks
pmeier Aug 18, 2023
ced5cf1
remove num_objects paramter
pmeier Aug 18, 2023
57ff336
Merge branch 'main' into cleanup-make-bounding-boxes
pmeier Aug 18, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 6 additions & 10 deletions test/common_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -406,26 +406,21 @@ def make_bounding_boxes(
canvas_size=DEFAULT_SIZE,
*,
format=datapoints.BoundingBoxFormat.XYXY,
batch_dims=(),
dtype=None,
device="cpu",
):
def sample_position(values, max_value):
# We cannot use torch.randint directly here, because it only allows integer scalars as values for low and high.
# However, if we have batch_dims, we need tensors as limits.
return torch.stack([torch.randint(max_value - v, ()) for v in values.flatten().tolist()]).reshape(values.shape)
return torch.stack([torch.randint(max_value - v, ()) for v in values.tolist()])

if isinstance(format, str):
format = datapoints.BoundingBoxFormat[format]

dtype = dtype or torch.float32

if any(dim == 0 for dim in batch_dims):
return datapoints.BoundingBoxes(
torch.empty(*batch_dims, 4, dtype=dtype, device=device), format=format, canvas_size=canvas_size
)

h, w = [torch.randint(1, c, batch_dims) for c in canvas_size]
num_objects = 1
h, w = [torch.randint(1, c, (num_objects,)) for c in canvas_size]
y = sample_position(h, canvas_size[0])
x = sample_position(w, canvas_size[1])

Expand All @@ -448,11 +443,12 @@ def sample_position(values, max_value):
)


def make_detection_mask(size=DEFAULT_SIZE, *, num_objects=5, batch_dims=(), dtype=None, device="cpu"):
def make_detection_mask(size=DEFAULT_SIZE, *, dtype=None, device="cpu"):
"""Make a "detection" mask, i.e. (*, N, H, W), where each object is encoded as one of N boolean masks"""
num_objects = 1
return datapoints.Mask(
torch.testing.make_tensor(
(*batch_dims, num_objects, *size),
(num_objects, *size),
low=0,
high=2,
dtype=dtype or torch.bool,
Expand Down
Loading