Considering the glut of neural network libraries, it'd be useful if there were some blurb about what makes this "special".
To clarify myself, "what niche does this belong to". Caffe for instance remains (to the misery of people like me) the standard library on which reference CNNs are implemented (other than that little pony's YOLO :P).
Tensorflow/MXnet/Chainer/Torch have nice dynamic interfaces... but basically are doing the same thing underneath (calling cuDNN/GEMM), and have the backing of well-known researchers/big corporations (maybe not Chainer...).
To clarify myself, "what niche does this belong to". Caffe for instance remains (to the misery of people like me) the standard library on which reference CNNs are implemented (other than that little pony's YOLO :P).
Tensorflow/MXnet/Chainer/Torch have nice dynamic interfaces... but basically are doing the same thing underneath (calling cuDNN/GEMM), and have the backing of well-known researchers/big corporations (maybe not Chainer...).