Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
Contributor
|
This PR will be closed in a week because of 2 weeks of no activity. |
This branch has not been deployed
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR overview
This PR provides a notebook that enables and quantizes the CSRNet model in OpenVINO for FP32, FP16, and INT8 and tests on crowd-counting. Following are the details.
Tickets:
Jira: CVS-190026.
Application: Crowd-counting.
Model: CSRNet (PyTorch, 16 M params, FP32).
PyTorch FP32 → OpenVINO FP32, FP16 IR conversion.
NNCF based mixed-precision OpenVINO INT8 quantization.
IRs validated for accuracy on ShanghaiTech datasets Part A and Part B.
benchmark_app results on Intel Arc B390 iGPU (PTL): FP16: 20.4 ms / 49 FPS INT8: 10.7 ms / 93 FPS.
Test image: IMG_114.jpg → PyTorch model count =162, OpenVINO model count =162 (FP32, FP16, INT8).
Dataset source link:
https://drive.google.com/file/d/16dhJn7k4FWVwByRsQAEpl9lwjuV03jVI/view
Model fallback link:
https://drive.google.com/file/d/1Z-atzS5Y2pOd-nEWqZRVBDMYJDreGWHH/view
Disclaimer:
AI assistance is taken in creating the notebook. However, all cells are verified manually and the notebook is manually tested for its output and it works as expected.