dnn: test data for depthwise QLinearConv (opencv #28798)#1360
Open
5usu wants to merge 1 commit into
Open
Conversation
Contributor
|
@5usu Thanks for the contribution! How do you generated the model file and reference input/output tensors? If you do it with torch/onnx-script or similar tool, please add you code to one of generate_ scripts in https://github.com/opencv/opencv_extra/tree/5.x/testdata/dnn/onnx. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Companion PR for opencv/opencv#28920.
Adds three small fixtures (~9 KB total) for the depthwise QLinearConv regression test:
testdata/dnn/onnx/models/quantized_depthwise_conv_int8_weights.onnx(629 B)testdata/dnn/onnx/data/input_quantized_depthwise_conv_int8_weights.npy(4.2 KB)testdata/dnn/onnx/data/output_quantized_depthwise_conv_int8_weights.npy(4.2 KB)The model is a single 16-group, 1-channel-per-group, 3×3 depthwise QLinearConv with non-zero
x_zp— the minimal shape that exercises theKg<K0code path fixed in the OpenCV PR. Reference output produced by onnxruntime.Branch name matches the OpenCV PR per the contribution guide.