Added dexined quantized model for edge detection#272
Merged
fengyuentau merged 4 commits intoopencv:mainfrom Sep 18, 2024
Merged
Added dexined quantized model for edge detection#272fengyuentau merged 4 commits intoopencv:mainfrom
fengyuentau merged 4 commits intoopencv:mainfrom
Conversation
fengyuentau
reviewed
Aug 29, 2024
Member
fengyuentau
left a comment
There was a problem hiding this comment.
- License is required for every model in the zoo. Compatible licenses are Apache 2.0, MIT. Please refer to the original license.
- Add a readme and a link to the sample code in opencv/samples. Also add reference to the original source of the model.
- Follow the naming pattern. The filename of the model should be
${task}_${model_name}_${timestamp}.onnx, such asedge_detection_dexined_2024sep.onnx.
6 tasks
fengyuentau
reviewed
Sep 11, 2024
fengyuentau
reviewed
Sep 13, 2024
| # Forward pass through the model | ||
| out = self._model.forward() | ||
| result, _ = self.postProcessing(out, image.shape[:2]) | ||
| t, _ = self._model.getPerfProfile() |
Member
There was a problem hiding this comment.
No need to get profile data here. The benchmark script measures at the whole infer function.
We normally measure the time of the whole pipeline including preprocessing, inference and post processing. You can use TickMeter to do so, e.g.
opencv_zoo/models/face_detection_yunet/demo.py
Lines 128 to 141 in c764e50
Member
There was a problem hiding this comment.
Could you rename the file to demo.cpp? Just want to keep aligned with others in this repo.
Member
There was a problem hiding this comment.
Could you rename the file to demo.py? Just want to keep aligned with others in this repo.
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
2 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.
Added dexined quantized model for edge detection DNN sample.