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

Range analysis improvements and better input shape override #97

Merged
merged 12 commits into from
Feb 5, 2024
Merged

Range analysis improvements and better input shape override #97

merged 12 commits into from
Feb 5, 2024

Conversation

maltanar
Copy link
Collaborator

@maltanar maltanar commented Feb 5, 2024 •
edited
Loading

  • Support extracting bias from ConvTranspose nodes using ExtractBiasFromConv
  • Allow specifying general input shape as well as bias for input shape override in cleanup_model (please note that override_batchsize is now override_inpsize)
  • Range analysis improvements: support float16 tensors, use calc_monotonic_range for more op types, support Split, support multi-output nodes, support per-channel input range specification

maltanar and others added 12 commits August 30, 2023 14:56
@maltanar maltanar merged commit 3fd9386 into main Feb 5, 2024
5 checks passed
@maltanar maltanar deleted the feature/tensor_stats branch February 5, 2024 14:59
@maltanar maltanar mentioned this pull request Feb 5, 2024
Closed
4 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@maltanar