Skip to content

⚡ Bolt: Optimize TripletDataGenerator sampling to O(1) #14

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

Draft
google-labs-jules wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

⚡ Bolt: Optimize TripletDataGenerator sampling to O(1) #14

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
22 changes: 16 additions & 6 deletions deeptuner/datagenerators/triplet_data_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,15 @@ def __init__(self, image_paths, labels, batch_size, image_size, num_classes):
self.num_classes = num_classes
self.label_encoder = LabelEncoder()
self.encoded_labels = self.label_encoder.fit_transform(labels)

# Pre-compute label to paths mapping for O(1) sampling
self.label_to_paths = {}
for path, label in zip(self.image_paths, self.encoded_labels):
if label not in self.label_to_paths:
self.label_to_paths[label] = []
self.label_to_paths[label].append(path)
self.unique_labels = np.array(list(self.label_to_paths.keys()))

self.image_data_generator = ImageDataGenerator(preprocessing_function=resnet.preprocess_input)
self.on_epoch_end()
print(f"Initialized TripletDataGenerator with {len(self.image_paths)} images")
Expand Down Expand Up @@ -40,12 +49,13 @@ def _generate_triplet_batch(self, batch_image_paths, batch_labels):
anchor_path = batch_image_paths[i]
anchor_label = batch_labels[i]

positive_path = np.random.choice(
[p for p, l in zip(self.image_paths, self.encoded_labels) if l == anchor_label]
)
negative_path = np.random.choice(
[p for p, l in zip(self.image_paths, self.encoded_labels) if l != anchor_label]
)
positive_path = np.random.choice(self.label_to_paths[anchor_label])

while True:
neg_label = np.random.choice(self.unique_labels)
if neg_label != anchor_label:
break
negative_path = np.random.choice(self.label_to_paths[neg_label])

anchor_image = load_img(anchor_path, target_size=self.image_size)
positive_image = load_img(positive_path, target_size=self.image_size)
Expand Down