def compute_mean_std(files, batch_size=128):
"""Load images in files in batches and compute mean."""
m = np.zeros((3,256,256))
s2 = np.zeros((3,256,256))
for i in range(0, len(files), batch_size):
print("done with {:>3} / {} images".format(i, len(files)))
try:
images = np.array([imageData.load_augment(f,256,256) for f in files[i : i + batch_size]])
except:
print (i)
raise
m += images.sum(axis=(0 ))
s2 += np.power(images, 2).sum(axis=(0))
shape = s2.shape
m = m / len(files)
m = np.mean(m,axis=(1,2))
n = len(files) * shape[1] * shape[2]
var = (s2/(n-1)).sum(axis=(1,2)) - (((m**2.0)*n) / (n - 1))
return m,np.sqrt(var)
def main(filelist):
filenames = imageData.get_files(filelist)
bs = 1000
batches = [filenames[i * bs : (i + 1) * bs]
for i in range(int(len(filenames) / bs) + 1)]
Us, evs = [], []
for batch in batches:
images = np.array([imageData.load_augment(f, 256, 256) for f in batch])
X = images.transpose(0, 2, 3, 1).reshape(-1, 3)
cov = np.dot(X.T, X) / X.shape[0]
U, S, V = np.linalg.svd(cov)
ev = np.sqrt(S)
Us.append(U)
evs.append(ev)
print('U')
print(np.mean(Us, axis=0))
print('eigenvalues')
print(np.mean(evs, axis=0))
def load_shared(args):
i, array_name, fname, kwargs = args
array = SharedArray.attach(array_name)
array[i] = imageData.load_augment(fname, **kwargs)
