-
-
Save takatakamanbou/413467c6c36177c5d6e3 to your computer and use it in GitHub Desktop.
cifar10.py & cifar10_sub150823.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import scipy as sp | |
import os | |
import cPickle | |
class CIFAR10( object ): | |
def __init__( self, dirname ): | |
self.path = dirname | |
f_meta = open( os.path.join( self.path, 'batches.meta'), 'r' ) | |
self.meta = cPickle.load( f_meta ) | |
f_meta.close() | |
self.nclass = len( self.meta['label_names'] ) | |
print '##### CIFAR-10 #####' | |
print '# label_names =', self.meta['label_names'] | |
print '# num_vis = ', self.meta['num_vis'] | |
def _loadBatch( self, fn ): | |
p = os.path.join( self.path, fn ) | |
f = open( p, 'r' ) | |
d = cPickle.load( f ) | |
f.close() | |
data = d['data'] # 10000 x 3072 ( 3072 = 3 x 32 x 32 ), unit8s | |
labels = d['labels'] # 10000-dim, in { 0, 1, ..., 9 } | |
return data, np.array( labels ) | |
def _loadL( self ): | |
fnList = [ 'data_batch_%d' % i for i in range( 1, 6 ) ] | |
dataList, labelsList = [], [] | |
for fn in fnList: | |
d, l = self._loadBatch( fn ) | |
dataList.append( d ) | |
labelsList.append( l ) | |
return np.vstack( dataList ), np.hstack( labelsList ) | |
def _loadT( self ): | |
return self._loadBatch( 'test_batch' ) | |
##### loading the data | |
# | |
def loadData( self, LT ): | |
if LT == 'L': | |
dat, lab = self._loadL() | |
else: | |
dat, lab = self._loadT() | |
#X = np.asarray( dat, dtype = float ).reshape( ( -1, 3, 32, 32 ) ) / 255 | |
X = np.asarray( dat, dtype = float ).reshape( ( -1, 3, 32, 32 ) ) | |
t = np.zeros( ( lab.shape[0], self.nclass ), dtype = bool ) | |
for ik in range( self.nclass ): | |
t[lab == ik, ik] = True | |
return X, lab, t | |
##### generating the index of training & validation data | |
# | |
def genIndexLV( self, lab, seed = 0 ): | |
np.random.seed( seed ) | |
idx = np.random.permutation( lab.shape[0] ) | |
idxV = np.zeros( lab.shape[0], dtype = bool ) | |
# selecting 1000 images per class for validation | |
for ik in range( self.nclass ): | |
i = np.where( lab[idx] == ik )[0][:1000] | |
idxV[idx[i]] = True | |
idxL = -idxV | |
return idxL, idxV | |
if __name__ == "__main__": | |
import cv2 | |
dirCIFAR10 = './cifar10/cifar-10-batches-py' | |
cifar10 = CIFAR10( dirCIFAR10 ) | |
dataL, labelsL = cifar10._loadL() | |
w = h = 32 | |
nclass = 10 | |
nimg = 10 | |
gap = 4 | |
width = nimg * ( w + gap ) + gap | |
height = nclass * ( h + gap ) + gap | |
img = np.zeros( ( height, width, 3 ), dtype = int ) + 128 | |
for iy in range( nclass ): | |
lty = iy * ( h + gap ) + gap | |
idx = np.where( labelsL == iy )[0] | |
for ix in range( nimg ): | |
ltx = ix * ( w + gap ) + gap | |
tmp = dataL[idx[ix], :].reshape( ( 3, h, w ) ) | |
# BGR <= RGB | |
img[lty:lty+h, ltx:ltx+w, 0] = tmp[2, :, :] | |
img[lty:lty+h, ltx:ltx+w, 1] = tmp[1, :, :] | |
img[lty:lty+h, ltx:ltx+w, 2] = tmp[0, :, :] | |
cv2.imwrite( 'hoge.png', img ) | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import scipy as sp | |
# ZCA whitening | |
def ZCAtrans( Xraw, Uzca = None ): | |
assert Xraw.ndim == 4 # Xraw is assumed to be N x 3 x 32 x 32 | |
Xraw2 = Xraw.reshape( ( Xraw.shape[0], -1 ) ) | |
if Uzca == None: | |
# Xraw is assumed to be zero-mean | |
C = np.dot( Xraw2.T, Xraw2 ) / Xraw2.shape[0] | |
U, eva, V = np.linalg.svd( C ) # U[:, i] is the i-th eigenvector | |
sqeva = np.sqrt( eva + 0.001 ) | |
Uzca = np.dot( U / sqeva[np.newaxis, :], U.T ) | |
X = np.dot( Xraw2, Uzca ).reshape( Xraw.shape ) | |
return X, Uzca | |
else: | |
X = np.dot( Xraw2, Uzca ).reshape( Xraw.shape ) | |
return X | |
# mini batch indicies for stochastic gradient ascent | |
def makebatchindex( N, batchsize ): | |
idx = np.random.permutation( N ) | |
nbatch = int( np.ceil( float( N ) / batchsize ) ) | |
idxB = np.zeros( ( nbatch, N ), dtype = bool ) | |
for ib in range( nbatch - 1 ): | |
idxB[ib, idx[ib*batchsize:(ib+1)*batchsize]] = True | |
ib = nbatch - 1 | |
idxB[ib, idx[ib*batchsize:]] = True | |
return idxB | |
# making translated and horizontally flipped images | |
def translate( Xsrc, dstshape ): | |
assert Xsrc.ndim == 4 # Xsrc is assumed to be N x 3 x 32 x 32 | |
N = Xsrc.shape[0] | |
h, w = dstshape | |
tmax_x, tmax_y = 32 - w, 32 - h | |
tx = np.random.randint( 0, tmax_x, N ) | |
ty = np.random.randint( 0, tmax_y, N ) | |
hf = np.random.random_sample( N ) < 0.5 | |
Xdst = np.empty( ( N, 3, dstshape[0], dstshape[1] ), dtype = Xsrc.dtype ) | |
for n in range( N ): | |
if hf[n]: | |
Xdst[n, :, :, :] = Xsrc[n, :, ty[n]:ty[n]+h, tx[n]:tx[n]+w] | |
else: | |
Xdst[n, :, :, :] = Xsrc[n, :, ty[n]:ty[n]+h, tx[n]+w:tx[n]:-1] | |
return Xdst | |
# making translated and horizontally flipped images | |
def translate2( Xsrc, dstshape ): | |
assert Xsrc.ndim == 4 # Xsrc is assumed to be N x 3 x 32 x 32 | |
N = Xsrc.shape[0] | |
h, w = dstshape | |
tmax_x, tmax_y = 32 - w, 32 - h | |
tx = np.random.randint( 0, tmax_x ) | |
ty = np.random.randint( 0, tmax_y ) | |
hf = np.random.random_sample() < 0.5 | |
if hf: | |
return Xsrc[:, :, ty:ty+h, tx:tx+w] | |
else: | |
return Xsrc[:, :, ty:ty+h, tx+w:tx:-1] | |
# clipping the center of the image w/o horizontal flip | |
def clipcenter( Xsrc, dstshape ): | |
assert Xsrc.ndim == 4 # Xsrc is assumed to be N x 3 x 32 x 32 | |
h, w = dstshape | |
ty, tx = ( 32 - h ) / 2, ( 32 - w ) / 2 | |
return Xsrc[:, :, ty:ty+h, tx:tx+w] | |
if __name__ == "__main__": | |
import cv2 | |
import cifar10 | |
dirCIFAR10 = './cifar10/cifar-10-batches-py' | |
c10 = cifar10.CIFAR10( dirCIFAR10 ) | |
dataL, labelsL = c10._loadL() | |
Xorg = dataL[:500].reshape( ( -1, 3, 32, 32 ) ) | |
lab = labelsL[:500] | |
w = h = 24 | |
nclass = 10 | |
nimg = 10 | |
gap = 4 | |
width = nimg * ( w + gap ) + gap | |
height = nclass * ( h + gap ) + gap | |
img = np.zeros( ( height, width, 3 ), dtype = int ) + 128 | |
for iy in range( nclass ): | |
lty = iy * ( h + gap ) + gap | |
idx = np.where( lab == iy )[0] | |
X = translate( Xorg[idx], ( h, w ) ) | |
for ix in range( nimg ): | |
ltx = ix * ( w + gap ) + gap | |
tmp = X[ix] | |
# BGR <= RGB | |
img[lty:lty+h, ltx:ltx+w, 0] = tmp[2, :, :] | |
img[lty:lty+h, ltx:ltx+w, 1] = tmp[1, :, :] | |
img[lty:lty+h, ltx:ltx+w, 2] = tmp[0, :, :] | |
cv2.imwrite( 'hoge.png', img ) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment