Yuantao Feng
Yuantao Feng
## Compilation 1. Set up environment variable for AscendCL includes and libraries: `export ASCEND_INSTALL_DIR=/path/to/Ascend/ascend-toolkit/`, where you can find `include` and `acllib`. 2. Set up environment variable for Ascend drivers: `export...
Changes separated from #18594 ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the...
Fixes #22215 . Things has to be done for the support: - [x] Identity node: getting input from constBlob. - [ ] [Range node](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Range): implementation for Range node. ### Pull...
Hello! I wonder whether we can provide opencv-python nightly builds. Consider a case like this: patch https://github.com/opencv/opencv/pull/22100 fixed the clip node issue which [allows us to load mobilenet v2 again](https://github.com/opencv/opencv_zoo/issues/55)....
Benchmark configuration files should be refactored as follows to improve robustness and readability: ```yaml Benchmark: name: str type: str data: path: str # necessary files: List[str] # necessary and must...
Fixes #22528 ONNX operator doc: https://github.com/onnx/onnx/blob/main/docs/Operators.md#Scatter ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x]...
Fixes https://github.com/opencv/opencv/issues/19779. And one step forward to support [the ssd-mobilenet from onnx model zoo](https://github.com/onnx/models/tree/main/vision/object_detection_segmentation/ssd-mobilenetv1). https://github.com/opencv/opencv_extra/pull/1005 TODO list: - [x] Supports the case where exporting a PyTorch model with `torchvision.ops.nms` to...
https://github.com/opencv/opencv/pull/22529
https://github.com/opencv/opencv/pull/22473
This is the test case that I used when doing the gemm integration to opencv dnn. However, I found the result from ficus nn is different from numpy. Doublechecked with...