David Buchaca Prats

I like the idea, I wish we could have a faster Knn in the package and leverage it in other packages, such as Clustering.jl. For reference I ended up doing...

I would say both make sense to have in the NearestNeighbors Package. KNN single threaded by default, and one version that does not store all pairwise distances (which is what...

This would come in handy for `Clustering.jl`, what do you think @KristofferC ? Currently cluster assigment is performed computing and storing all pairwise distances, which is quite bad in terms...

@jjlynch2 the memory problem you mention happens because the implementation stores a 500,000x50,000 distance matrix when using `pairwise`. I am interested in making a PR to avoid this. For each...

I´ve seen I can do this ``` Array(reshape(channelview(result_conv),(3, 254, 254))) ``` Which returns exactly what I wanted ``` 3×254×254 Array{Float32,3} ``` I think it is too complicated and prone to...

Thanks @johnnychen94 , maybe adding an example to the documentation would help future users.

Hello Tim, About `You're trying to make Julia throw away a lot of useful stuff simply because Matlab/Python can't handle stuff like that.` You are kind of right, but sometimes,...

I have found the data here: https://github.com/mbeyeler/opencv-machine-learning/tree/78f5f6ecfbbae3f61b378060d60641420331115c/notebooks/data/chapter6 Maybe you could simply add it in the repo and load it from the repo. When compressed its only some MB.

An even better idea would be to add the data in MLDatasets.jl so other people can use it independently of ImageFeatures easily.

@zygmuntszpak The link works but it's not the same data. This link contains 924 images not 2500 images. Besides there are no Negative samples. I don't know where to download...