Taylor Koon

np.argsort not sorting properly

1

I am attempting to call np.argsort() on the following array: [0.700656592845917, 0.651415288448334, 0.719015657901764] dtype = Double The expected result should be: [1, 0, 2] However, the actual result I'm getting...

MxNet Converted Arcface Model Slow Compared to Provided Arcface Model

1

I have a arcface/resnet100 model that I've trained using InsightFace's MxNet training. For inference, I have converted the model to ONNX with the help of https://github.com/linghu8812/tensorrt_inference/blob/master/project/arcface/export_onnx.py. The inference results are...

[Feature-Request] Expose stats used for 3A algorithms

3

### Start with the `why`: We are working to improve image quality in poor lighting situations and have found that the 3A evaluations (auto-focus/auto-exposure/auto-white balance) do not give us our...

Initializing Mat object with 3 dimensional NDarray

7

I have a 250x250 image that is loaded into an `NDArray` that uses three channels, so the dimensions of the `NDArray` are (250, 250, 3). It looks like the `Mat`...

I have an image that is loaded in memory that I need to get into a `Mat` object. Can `cv2.imdecode()` be implemented as it is in OpenCvSharp? It looks like...

Hi TorchSharp Team, First, thank you for all the incredible work on this library. TorchSharp has allowed our team to develop ML tasks with ease thanks to all of your...