Arraymancer
Arraymancer copied to clipboard
mratsim
A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends
See https://github.com/arogozhnikov/einops And code comparison vs PyTorch https://arogozhnikov.github.io/einops/pytorch-examples.html
opening this issue to track ideas for how to port Halide to nim. This could be either using halide in Nim via: * A1: a wrapper (eg using nimterop) or...
`import arraymancer` was just broken for me due to an issue with my local `untar` version. I got curious why Arraymancer actually needs this and noticed that the default import...
See https://ci.appveyor.com/project/mratsim/arraymancer/builds/25128064/job/iq1o3vh55p65g8ba#L674
NVIDIA Dali can be used as inspiration - https://github.com/NVIDIA/DALI
Hello, Thanks for your good DL framework. I implemented simple cifar-10 classification using Arraymancer. The demo is placed here ( https://github.com/cashiwamochi/nim_dl ) . How do you think about adding this...
See fast.ai - announcement: http://nlp.fast.ai/classification/2018/05/15/introducting-ulmfit.html - paper: https://arxiv.org/abs/1801.06146 - course: http://course.fast.ai/lessons/lesson10.html 
Seems to be key for RNNs to learn long-term dependencies. Foundational paper: Exact solutions to the nonlinear dynamics of learning in deep linear neural networks 2013, Saxe et al, https://arxiv.org/abs/1312.6120...
ML is notoriously hard to test as an error in the output of a model can be due to: - not enough data - model architecture not suitable - implementation...