Skip to content

issues Search Results · repo:zhijian-liu/torchprofile language:Python

Filter by

19 results
 (74 ms)

19 results

inzhijian-liu/torchprofile (press backspace or delete to remove)

@zhijian-liu As the title shows, I want to count the #params of a point cloud model (e.g., PointBERT) instead of an image model, the example input of point cloud data is of shape (batch_size, 1024, 3). ...
  • auniquesun
  • Opened 
    on Oct 30, 2024
  • #25

Thank you for your great work! I encountered this warning when using torchprofile. It seems like torchprofile cannot calculate the MACs of UserWarning: No handlers found: torchvision::roi_align . Skipped ...
enhancement
  • padeirocarlos
  • 2
  • Opened 
    on Feb 20, 2023
  • #21

Thank you for your great work! I encountered this warning when using torchprofile. It seems like torchprofile cannot calculate the GFLOPS of torch.nn.functional.grid_sample: UserWarning: No handlers found: ...
enhancement
  • RockeyCoss
  • Opened 
    on Feb 16, 2023
  • #20

UserWarning: No handlers found: aten::gelu . Skipped. UserWarning: No handlers found: aten::reshape . Skipped. UserWarning: No handlers found: aten::permute . Skipped
enhancement
  • HuCaoFighting
  • 1
  • Opened 
    on Nov 3, 2022
  • #19

No handlers found: aten::unsqueeze No handlers found: aten::pow . No handlers found: aten::sign No handlers found: aten::abs No handlers found: aten::fft_fft No handlers found: aten::real No handlers found: ...
enhancement
  • Ben-Yee
  • Opened 
    on Apr 27, 2022
  • #18

No handlers found: aten::unfold No handlers found: aten::split No handlers found: aten::einsum . No handlers found: aten::permute . hope to support these ops, thanks!
enhancement
  • 787629504
  • 4
  • Opened 
    on Mar 12, 2022
  • #17

nn.Linear layer is always used in Transformer-like models. Should I add this part when I use torchprofile to compute flops for a transformer model?
enhancement
  • Z-Zheng
  • 3
  • Opened 
    on Mar 10, 2022
  • #16

def profile_macs(model, args=(), kwargs=None, reduction=sum): results = dict() graph = trace(model, args, kwargs)
  • pengfeiZhao1993
  • 1
  • Opened 
    on Jul 19, 2021
  • #15

hope to support prim::pythonop and prim::tupleunpack operations Thanks and great tool!
  • Cosijopiii
  • 1
  • Opened 
    on Jun 12, 2021
  • #13

Thanks for your good job, but I found some problems: No handlers found: aten::group_norm . Skipped. No handlers found: aten::floor_divide . Skipped. No handlers found: aten::upsample_bilinear2d . Skipped. ...
enhancement
  • Hengwei-Zhao96
  • 2
  • Opened 
    on Apr 11, 2021
  • #12
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub