Skip to content

Fix torch long to float tensor on HUB macOS#8067

Merged
glenn-jocher merged 1 commit intomasterfrom
fix/hub
Jun 1, 2022
Merged

Fix torch long to float tensor on HUB macOS#8067
glenn-jocher merged 1 commit intomasterfrom
fix/hub

Conversation

@glenn-jocher
Copy link
Copy Markdown
Member

@glenn-jocher glenn-jocher commented Jun 1, 2022 •
edited by UltralyticsAssistant
Loading

🛠️ PR Summary

Made with ❤️ by Ultralytics Actions

🌟 Summary

Refinement of anchor handling in loss computation for object detection.

📊 Key Changes

  • Combined two lines of code to simplify how anchors and tensor shapes are assigned.
  • Replaced hardcoded gain indices with the actual shape of prediction tensor for grid clamping.

🎯 Purpose & Impact

  • The purpose of these changes is to enhance code readability and maintainability by reducing complexity.
  • This could potentially minimize bugs related to tensor indexing and make it easier to understand how anchor boxes are used during loss computation.
  • Impact to users includes a clearer understanding of the inner mechanics of the model's loss function, which can aid in debugging and extending the code.

@glenn-jocher glenn-jocher self-assigned this Jun 1, 2022
@glenn-jocher glenn-jocher merged commit 7cef03d into master Jun 1, 2022
@glenn-jocher glenn-jocher deleted the fix/hub branch June 1, 2022 15:34
tdhooghe pushed a commit to tdhooghe/yolov5 that referenced this pull request Jun 10, 2022
@glenn-jocher @tdhooghe
Fix torch long to float tensor on HUB macOS (ultralytics#8067)
ffe6b25
@glenn-jocher glenn-jocher linked an issue Jul 18, 2022 that may be closed by this pull request
RuntimeError: result type Float can't be cast to the desired output type long int #8405
Closed
2 tasks
@glenn-jocher glenn-jocher mentioned this pull request Jul 18, 2022
Closed
2 tasks
@ItzDerock ItzDerock mentioned this pull request Jul 27, 2022
Open
ctjanuhowski pushed a commit to ctjanuhowski/yolov5 that referenced this pull request Sep 8, 2022
@glenn-jocher
Fix torch long to float tensor on HUB macOS (ultralytics#8067)
d5000df
Mindstan pushed a commit to PsycleResearch/yolov5 that referenced this pull request Sep 13, 2022
@glenn-jocher @Mindstan
Fix torch long to float tensor on HUB macOS (ultralytics#8067)
593ce56
Mindstan added a commit to PsycleResearch/yolov5 that referenced this pull request Sep 15, 2022
@Mindstan @glenn-jocher
Features: DEV-3305 Migrate to Poetry, Python 3.9, PyTorch 1.12 (#22)
d9f1cd8 
* Use poetry

* Only use Python >= 3.9

* Moved to PyTorch 1.12

* Bump version

* PyTorch 1.11.0 compatibility updates (ultralytics#6932)

Resolves `AttributeError: 'Upsample' object has no attribute 'recompute_scale_factor'` first raised in ultralytics#5499

* Bump beta version

* Fix torch `long` to `float` tensor on HUB macOS (ultralytics#8067)

* Bump beta version

* Updated Makefile

* Added README

* Added missing VERSION

* Final major version

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
@hojland hojland mentioned this pull request Oct 17, 2022
Merged
corey-nm added a commit to neuralmagic/yolov5 that referenced this pull request Oct 26, 2022
@corey-nm
Cherry pick of ultralytics#8067 from ultralytics fork
f3bed63
@corey-nm corey-nm mentioned this pull request Oct 26, 2022
Merged
bfineran pushed a commit to neuralmagic/yolov5 that referenced this pull request Oct 26, 2022
@corey-nm
Cherry pick of ultralytics#8067 from ultralytics fork (#120)
ebddcba
WasabiFan pushed a commit to WasabiFan/edgeai-yolov5 that referenced this pull request Dec 11, 2022
@glenn-jocher @WasabiFan
Fix torch long to float tensor on HUB macOS (ultralytics#8067)
3c99320
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

@glenn-jocher glenn-jocher

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

RuntimeError: result type Float can't be cast to the desired output type long int

1 participant

@glenn-jocher