Performance on np.matmul

[Banyc]

The shape of x is [200, 1000], of w is [1000, 500], and of b is [500]

b is filled with zeros, x and w are random float64/double.

Example code of NumSharp:

var out = np.matmul(x, w) + b;

... takes 3-4 seconds.

Example code of numpy:

out = x @ w + b

... finishes immediately.

[Oceania2018]

@Banyc Can you test it in TensorFlow.NET eager mode?

[Banyc]

I use only this package to implement neural network layers from the stretch, without using other packages like Tensorflow.NET.

[Oceania2018]

It will have performance issue. Should use other more mature package.