morvan_neural networks
- x_data = np.linspace(-1, 1, 300, dtype=np.float32)[:,np.newaxis] #从-1-1,300个等分数据,300行
-
noise = np.random.normal(0, 0.5, x_data.shpae).astype(np.float32) #
numpy.random.
normal
(loc=0.0, scale=1.0, size=None)size : int or tuple of ints, optional