Audun Mathias Øygard
Audun Mathias Øygard
Hi, it seems the option `shared_axes` for PReLU activations (https://keras.io/layers/advanced-activations/#prelu) is not supported in Keras-js. In my case I made a simple hack around this by modifying the code [here](https://github.com/transcranial/keras-js/blob/master/src/layers/advanced_activations/PReLU.js#L57):...
It needs to be possible to track a face in images and canvas-elements as well as video elements.
when calling stop() on a headtracker instance from an eventlistener, an InvalidStateError is raised in Chrome: Uncaught InvalidStateError: An attempt was made to use an object that is not, or...
While the Whitehead bias-adjusted estimator seems to work decently, it would be nice to be able to estimate bias conditional on number of samples the test needed to finish. Furthermore,...
It's possible to extend most sequential GLR tests to multi-hypothesis settings, i.e. multivariate testing. It might need ability to calculate several-dimensional optimization, in order to calculate thresholds.
It is fairly trivial to add the possibility to set a minimum samplesize (to ensure that post-analysis estimates are better) since this can be simulated as usual. Adding the possibility...
Similarly to bernoulli comparison of proportions we would like to know the worst-case samplesize at a given level. This can not be simulated, but needs to be calculated analytically.
The library should include more precalculated thresholds than the one currently included.
The current implementation of optimization to find the thresholds at given levels, is a mocked up gradient descent algorithm where simulation is used to find the gradient descent steps. While...
Since training models in javascript/webgl is likely to be slow compared to frameworks utilizing e.g. cuda and cudnn, it would be nice to be able to import trained models from...