Aleksei Zinovev

Could you measure the same for 10, 50, 100 epochs instead of 3 by default on CPU and on the same GPU? Did you know how to run [KotlinDL on...

Unfortunately, I don't know it is possible with an anaconda or not (highly likely that is not possible); in my case, I reinstall drivers for video cards manually, and it...

Great data, thanks @wuhanstudio ! Looks very good, thanks for the great work!

It will be great if somebody with M1 will help to reproduce the issue with ONNX Runtime (the same problem is known for TF Runtime)

@Craigacp thanks for the comment! It's important to know

@avan1235 looks like the constraint will be postponed because I have no idea how to apply them to the variables. It should become a part of the weight update in...

Could you please share a Keras example for Deep Q Learning with multiple outputs for regression, hope to fix it in the 0.4 or 0.5 release of KotlinDL

Thanks for the example you gave me. Multiple outputs for models are not supported yet, but I agree that this is a good idea

Added a note for a possible solution to this problem: the following [example ](https://github.com/zaleslaw/KotlinDL/blob/feature-254/examples/src/main/kotlin/examples/ml/MultipleRegression.kt) should work. The current OnHeapDataset supports only `y` as FloatArray but should be Array like `x`...

It's an interesting proposal, but I need a time to estimate the power of this refactoring, give me a couple of days here to trace all the code routes in...