[ITEP-79015] Add GPU Device support for Manufacturing Edge AI Suites #786
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
tejaswinijayashanker943
requested review from
a team,
ajagadi1,
rrajore,
sajeevrajput,
sugnanprabhu and
xwu2intel
as code owners
tejaswinijayashanker943
changed the title
Contributor
Author
|
@sairampillai @deepaks2 @ajagadi1 Could you please do the first level review this PR. |
deepaks2
approved these changes
Oct 10, 2025
ajagadi1
reviewed
Oct 13, 2025
...uring-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json
Outdated
Show resolved
Hide resolved
ajagadi1
reviewed
Oct 13, 2025
...cturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json
Outdated
Show resolved
Hide resolved
ajagadi1
reviewed
Oct 13, 2025
manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json
Outdated
Show resolved
Hide resolved
ajagadi1
reviewed
Oct 13, 2025
...-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json
Outdated
Show resolved
Hide resolved
ajagadi1
reviewed
Oct 13, 2025
...te/industrial-edge-insights-vision/apps/pcb-anomaly-detection/docs/user-guide/get-started.md
Outdated
Show resolved
Hide resolved
ajagadi1
reviewed
Oct 13, 2025
Comment on lines
155
to
160
| > **NOTE:** This will start the pipeline. The inference stream can be viewed on WebRTC, in a browser at the following url: | ||
|
|
||
| ```bash | ||
| https://<HOST_IP>/mediamtx/anomaly/ | ||
| ``` | ||
|
|
Contributor
There was a problem hiding this comment.
Suggested change
| > **NOTE:** This will start the pipeline. The inference stream can be viewed on WebRTC, in a browser at the following url: | |
| ```bash | |
| https://<HOST_IP>/mediamtx/anomaly/ |
Similarly, if you have a GPU device, the GPU based pipeline can be started as ./sample_start.sh -p pcb_anomaly_detection_gpu and output stream can be viewed on https://<HOST_IP>/mediamtx/anomalygpu/
Contributor
There was a problem hiding this comment.
This will keep doc simple and avoid repetition
Co-authored-by: Ashish Jagadish <[email protected]>
Co-authored-by: Ashish Jagadish <[email protected]>
Co-authored-by: Ashish Jagadish <[email protected]>
Co-authored-by: Ashish Jagadish <[email protected]>
Co-authored-by: Ashish Jagadish <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR enhances the Manufacturing Sample Apps by adding GPU device-based payloads to improve stream density and achieve target FPS.
How Has This Been Tested?
Follow the setup guide. If Device is set to GPU, then the sample_start.sh automatically takes gpu based payload.
2 streams on GPU for PCB_Anomaly_Detection.
3 streams on GPU for Pallet_Defect_Detection.
6 streams on GPU for Weld_Porosity_Detection.
3 Streams on GPU for Worker Safety Gear Detection.
Lines of Code Changed:
Checklist: