一次从Numpy数组中选择多个切片

Question

I want to implement a vectorized SGD algorithm and would like to generate multiple mini batches at once.

Suppose data = np.arange(0, 100) , miniBatchSize=10 , n_miniBatches=10 and indices = np.random.randint(0, n_miniBatches, 5) (5 mini batches). What I would like to achieve is

miniBatches = np.zeros(5, miniBatchSize)
for i in range(5):
     miniBatches[i] = data[indices[i]: indices[i] + miniBatchSize]

Is there any way to avoid for loop?

Thanks!

Answer 1

It can be done using stride tricks :

from numpy.lib.stride_tricks import as_strided

a = as_strided(data[:n_miniBatches], shape=(miniBatchSize, n_miniBatches), strides=2*data.strides, writeable=False)    
miniBatches = a[:, indices].T


# E.g. indices = array([0, 7, 1, 0, 0])
Output:
array([[ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9],
       [ 7,  8,  9, 10, 11, 12, 13, 14, 15, 16],
       [ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10],
       [ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9],
       [ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9]])