Skip to content

Navigation Menu

Appearance settings

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

Appearance settings

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

CMU-Perceptual-Computing-Lab / openpose Public

Notifications You must be signed in to change notification settings
Fork 8k
Star 32.8k

Code
Issues 336
Pull requests 21
Actions
Projects
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Actions
Projects
Security
Insights

Tensor RT #285

Open

bushibushi wants to merge 55 commits intoCMU-Perceptual-Computing-Lab:masterCMU-Perceptual-Computing-Lab/openpose:masterfrom

Deepomatic:TensorRT_PRDeepomatic/openpose:TensorRT_PRCopy head branch name to clipboard

Conversation Commits55 (55)Checks Files changed

Open

Tensor RT #285
bushibushi wants to merge 55 commits intoCMU-Perceptual-Computing-Lab:masterfrom
Deepomatic:TensorRT_PR

Commits

Commits on Sep 21, 2017

Files for tensort rt pose detection, for now nothing done.
bushibushi
committed
Adding timer in new demo and checking build before replacing inference.
bushibushi
committed
PoseExtractorTensorRT changed names for build conflicts but still performs Caffe inference.
bushibushi
committed
Started modifying tutorial pose 3.
bushibushi
committed
More precise timing.
bushibushi
committed
More precise timings before replacing inference.
bushibushi
committed
Clearer timing display.
bushibushi
committed
Replaced poseExtractorCaffe with poseExtractorTensorRT
bushibushi
committed
Added inference sample code at end of poseExtractorTensorRT to work on laptop. DOES NOT compile, convenience commit.
bushibushi
committed

Commits on Sep 22, 2017

First code adaptation trial. Will not compile, still loads to replace.
bushibushi
committed
New netTensorRT version, cleaner, ready for debug, loads of questions.
bushibushi
committed
Fixed everything to compile, runs, reads network and convert but then segfault, need precise step logs or debug.
bushibushi
committed
Debug logs.
bushibushi
committed

Commits on Sep 25, 2017

First try on tensorRT inference with caffe Blobs.
bushibushi
committed
Running, but not pose recognition. Find a way to copy memory correctly.
bushibushi
committed
pose.sh script
bushibushi
committed

Commits on Sep 26, 2017

Timing in original pose demo
bushibushi
committed
Did not take into account forwardPass input data !
bushibushi
committed
Data copied to cuda memory. Correct sizes hardcoded, no CUDA error anymore, still not working.
bushibushi
committed
Tutorial pose 3 working !!!! Gaining x2 inference time, now time for cleaning.
bushibushi
committed
TensorRT Net input and output dimensions at runtime.
bushibushi
committed
NetTensorRT cleaning.
bushibushi
committed
NetTensorRT cleaning bis.
bushibushi
committed
Cleaning compilation fix.
bushibushi
committed
caffeToGIE needs fixed input size and cannot be determined at runtime for now.
bushibushi
committed
Engine serialization and deserialization.
bushibushi
committed
Targetting highest possible FPS in demo.
bushibushi
committed
Asynchronous inference.
bushibushi
committed
Way simpler inference code, a lot was useless.
bushibushi
committed
Removing log to speedup inference.
bushibushi
committed

Commits on Sep 27, 2017

ResizeAndMergeBase CPU version.
bushibushi
committed
Inference model for pose net size 256x192
bushibushi
committed
Detailed poseExtractor Timings.
bushibushi
committed
Faster Resize and Merge.
bushibushi
committed

Commits on Oct 11, 2017

Merge branch 'master' into TensorRT_PR
bushibushi
committed
TENSORRT precompiler guards
bushibushi
committed
TENSORRT compilation is still partly using caffe
bushibushi
committed
Missing guards for TensorRT
bushibushi
committed

Commits on Nov 13, 2017

PIMPL version of poseExtractorTensorRT, still having template compilation errors.
bushibushi
committed
Spot the differences part 1.
bushibushi
committed
Spot the differences part 2
bushibushi
committed
Spot the differences 3
bushibushi
committed

Commits on Nov 14, 2017

Fixed compilation without TensorRT
bushibushi
committed
Fix attempt
bushibushi
committed
Wrong variable name
bushibushi
committed
Merge branch 'master' into TensorRT_PR
bushibushi
committed
Too much changed in poseExtractorCaffe, need to rewrite TensorRT one from scratch.
bushibushi
committed

Commits on Nov 15, 2017

PIMPL for netTensorRT
bushibushi
committed
Fix source issues, example remains.
bushibushi
committed
Fix samples
bushibushi
committed
Compilation fixed, TensorRT net optimisation works, segfault on inference
bushibushi
committed
Code kind of work, not full pipeline lead to no shape displayed, sizes hardcoded.
bushibushi
committed
Useless preproc macros
bushibushi
committed
NetTensorRT modifs
bushibushi
committed
Merge branch 'master' into TensorRT_PR
bushibushi
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.