Numpy- Deep Learning, Training Examples -

silly question, going through third week of andrew ng's newest deep learning course, , getting stuck @ simple numpy function ( think? ).

the exercise find how many training examples, m , have.

any idea numpy function find out size of preloaded training example.

thanks!

shape_x = x.shape shape_y = y.shape m = ?   print ('the shape of x is: ' + str(shape_x)) print ('the shape of y is: ' + str(shape_y)) print ('i have m = %d training examples!' % (m)) 

it depends on kind of storage-approach use.

most python-based tools use [n_samples, n_features] approach first dimension sample-dimension, second dimension feature-dimension (like in scikit-learn , co.). alternatively expressed: samples rows , features columns.

so:

#     feature  1 2 3 4 x = np.array([[1,2,3,4], # first sample               [2,3,4,5], # second sample               [3,4,5,6]              ]) 

is training-set of 3 samples 4 features each.

the sizes m,n (again: interpretation might different others) can with:

m, n = x.shape 

because numpy's first dimension rows, numpy's second dimension columns like in matrix-algebra.

for above example, target-array of shape (m) = n_samples.