Leonidas Valavanis

probably a bit late but I think I have the answer. Many papers have a threshold to define a positive image (for example if the ratio of the distance of...

lets say that for a query the top 2 distances of the retrieved images are dist1 and dist2 . The ratio is defined as `ratio = dist1 / dist2` then...

I tried docker-compose down docker-compose build docker-compose up -d but the changes won't take place. I still can register a user and see the tasks list. Any ideas ?

> @valavanisleonidas Hi, 1) I used adam with no learning rate scheduler with lr=1e-2, momentum=0.9. 2)Training data is just the standard three splits of the UBC dataset, ie train on...

Checking the repository you suggested and loading the wasm using this library i get an error in the init function of the instance.exports.init() [here](https://github.com/0xPolygonID/js-sdk-react-native-tools/blob/0d12d927f52345ff15fc3fd7085af710a040e305/share/proof/witness-calculator-native.ts#L134). is this supported in this library...

> @valavanisleonidas #129 got merged. We can work on this PR now. Yes I saw that thank you. should we also have dynamic batch size for onnx models since the...

@SkalskiP I think the PR is mostly ready. Two things to mention. 1. in the providers for onnx we can add a device id for the GPU to use (and...

Hey @SkalskiP, any news on this PR ?

> Hi, dear developer, how is going on ? I also need to use the ONNX model to predict. this PR is not up to date with the latest changes....

Hello @MustafaKiwaPI , it’s not up to me to merge this. In order to use it because I wanted it as well I forked the code with the change and...