I added yolov7 tiny to the model zoo since it already exists in the ncnn-assets #4693
Conversation
This file contains 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
Adding yolov7_Tiny to the model zoo list
Adding yolov7-tiny to the model_store since the param and bin files already exist in https://github.com/nihui/ncnn-assets/raw/master/models/
|
|
|
Thanks for your contribution ! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
I saw that yolov7-tiny within https://github.com/nihui/ncnn-assets/tree/master/models so it could be available to the python interface if there was a wrapper that executed the network call and post processing.
I added the yolov7.py file and updated the model_zoo and model_store so that it can transparently run within the python interface with model_zoo.
I followed the format of the other model_zoo entries as closely as I could.
I added an optional argument use_strides to the arguments that restricts which strides to extract from the network in case users know ahead of time the size of the objects they wish to detect. Since the anchor sizes are strongly connected to the size of the objects detected you can speed up yolov7 by targeting just the output layers that you are interested in.