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

Avoid FP64 ops for MPS support in train.py #8511

Merged
merged 1 commit into from
Jul 7, 2022
Merged

Avoid FP64 ops for MPS support in train.py #8511

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions utils/general.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -644,7 +644,7 @@ def labels_to_class_weights(labels, nc=80):
return torch.Tensor()

labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO
classes = labels[:, 0].astype(np.int) # labels = [class xywh]
classes = labels[:, 0].astype(int) # labels = [class xywh]
weights = np.bincount(classes, minlength=nc) # occurrences per class

# Prepend gridpoint count (for uCE training)
Expand All @@ -654,13 +654,13 @@ def labels_to_class_weights(labels, nc=80):
weights[weights == 0] = 1 # replace empty bins with 1
weights = 1 / weights # number of targets per class
weights /= weights.sum() # normalize
return torch.from_numpy(weights)
return torch.from_numpy(weights).float()


def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
# Produces image weights based on class_weights and image contents
# Usage: index = random.choices(range(n), weights=image_weights, k=1) # weighted image sample
class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels])
class_counts = np.array([np.bincount(x[:, 0].astype(int), minlength=nc) for x in labels])
return (class_weights.reshape(1, nc) * class_counts).sum(1)


Expand Down