Image stack how is a numpy array faster (than preallocation)?

Question

I often have to add 2d numpy (tiff images) arrays. To do this, I will first add them to the list and use np.dstack. This is apparently the fastest way to get 3D arrays stacking images. But is there a faster / more memory efficient way?

from time import time
import numpy as np

# Create 100 images of the same dimention 256x512 (8-bit). 
# In reality, each image comes from a different file
img = np.random.randint(0,255,(256, 512, 100))

t0 = time()
temp = []
for n in range(100):
    temp.append(img[:,:,n])
stacked = np.dstack(temp)
#stacked = np.array(temp)  # much slower 3.5 s for 100

print time()-t0  # 0.58 s for 100 frames
print stacked.shape

# dstack in each loop is slower
t0 = time()
temp = img[:,:,0]
for n in range(1, 100):
    temp = np.dstack((temp, img[:,:,n]))
print time()-t0  # 3.13 s for 100 frames
print temp.shape

# counter-intuitive but preallocation is slightly slower
stacked = np.empty((256, 512, 100))
t0 = time()
for n in range(100):
    stacked[:,:,n] = img[:,:,n]
print time()-t0  # 0.651 s for 100 frames
print stacked.shape

# (Edit) As in the accepted answer, re-arranging axis to mainly use 
# the first axis to access data improved the speed significantly.
img = np.random.randint(0,255,(100, 256, 512))

stacked = np.empty((100, 256, 512))
t0 = time()
for n in range(100):
    stacked[n,:,:] = img[n,:,:]
print time()-t0  # 0.08 s for 100 frames
print stacked.shape

Answer 1

otterb , - . -, (n), . n ( "C": , ), :

from time import time
import numpy as np

# Create 100 images of the same dimention 256x512 (8-bit). 
# In reality, each image comes from a different file
img = np.random.randint(0,255,(100, 256, 512))

# counter-intuitive but preallocation is slightly slower
stacked = np.empty((100, 256, 512))
t0 = time()
for n in range(100):
    stacked[n] = img[n]
print time()-t0  
print stacked.shape