Skip to content

Fix: forward drop_last to make_videodataset #126

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

Open
laszloturanyi wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix: forward drop_last to make_videodataset #126

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
331b779
Fix: forward drop_last to make_videodataset
laszloturanyi Mar 11, 2026
d3e9d74
Fix overlap sampling to use uniform arange instead of linspace
laszloturanyi Mar 12, 2026
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
1 change: 1 addition & 0 deletions src/datasets/data_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,7 @@ def init_data(
num_workers=num_workers,
pin_mem=pin_mem,
persistent_workers=persistent_workers,
drop_last=drop_last,
world_size=world_size,
rank=rank,
deterministic=deterministic,
Expand Down
13 changes: 4 additions & 9 deletions src/datasets/video_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -348,15 +348,10 @@ def loadvideo_decord(self, sample, fpc):
# If partition overlap is allowed and partition_len < clip_len
# then start_indx of segment i+1 will lie within segment i
else:
sample_len = min(clip_len, len(vr)) - 1
indices = np.linspace(0, sample_len, num=sample_len // fstp)
indices = np.concatenate(
(
indices,
np.ones(fpc - sample_len // fstp) * sample_len,
)
)
indices = np.clip(indices, 0, sample_len - 1).astype(np.int64)
max_idx = min(clip_len, len(vr)) - 1
indices = np.clip(
np.arange(fpc) * fstp, 0, max_idx
).astype(np.int64)
# --
clip_step = 0
if len(vr) > clip_len:
Expand Down