/ex150808.py Secret
Last active
August 29, 2015 14:27
Star
You must be signed in to star a gist
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 cv2 | |
import mnist_sub150808 as mnist_sub | |
import nnet150718 as nnet | |
def addNoise( X ): | |
#Xnoisy = mnist_sub.addSaltPepperNoise( X, 0.1 ) | |
#Xnoisy = mnist_sub.shift( X, 2 ) | |
X2 = mnist_sub.shift( X, 2 ) | |
Xnoisy = mnist_sub.addSaltPepperNoise( X2, 0.1 ) | |
return Xnoisy | |
def setData( X, Xm, aetype ): | |
if aetype == 'Org-Org': # conventional AE | |
Xin = X - Xm | |
Zteacher = Xin | |
elif aetype == 'Noisy-Org': # denoising AE | |
Xin = addNoise( X ) - Xm | |
Zteacher = X - Xm | |
else: # Noisy-Noisy | |
Xin = addNoise( X ) - Xm | |
Zteacher = Xin | |
return Xin, Zteacher | |
if __name__ == '__main__': | |
dirMNIST = '.' | |
np.random.seed( 0 ) | |
##### setting the training data & the validation data | |
# | |
XL, labL, XV, labV = mnist_sub.getDataLV( dirMNIST = dirMNIST ) | |
Xm = np.mean( XL, axis = 0 ) | |
NL, D = XL.shape | |
NV, D = XV.shape | |
##### mini batch indicies for stochastic gradient ascent | |
# | |
batchsize = 100 | |
biL = mnist_sub.makeBatchIndex( NL, batchsize ) | |
nbatchL = biL.shape[0] | |
biV = mnist_sub.makeBatchIndex( NV, batchsize ) | |
nbatchV = biV.shape[0] | |
##### training | |
# | |
H = 1000 | |
#L1 = nnet.Layer( D, H, 'linear', withBias = False, Wini = 0.01 ) | |
L1 = nnet.Layer( D, H, 'ReLu', withBias = True, Wini = 0.01 ) | |
L2 = nnet.Layer( H, D, 'linear', withBias = False, Wini = 0.01 ) | |
ae = nnet.MLP( [ L1, L2 ], cost = 'squared_error' ) | |
eta, mu, lam = 0.01, 0.9, 0.0 | |
nepoch = 50 | |
print '# eta = ', eta, ' mu = ', mu, ' lam = ', lam | |
print '### training: NL = ', NL, 'NV = ', NV, ' batchsize = ', batchsize | |
print '# eta = ', eta, 'mu = ', mu, 'lam = ', lam | |
print '# D = ', D, ' H = ', H | |
for i in range( nepoch ): | |
sqeL = 0.0 | |
for ib in np.random.permutation( nbatchL ): | |
ii = biL[ib, :] | |
#aetype = 'Org-Org' | |
#aetype = 'Noisy-Noisy' | |
aetype = 'Noisy-Org' | |
Xin, Zteacher = setData( XL[ii, :], Xm, aetype = aetype ) | |
sqeL += ae.train( Xin, Zteacher, eta, mu, lam ) * Xin.shape[0] | |
if i < 10 or i % 10 == 0: | |
# validation error for Noisy-Org | |
sqeV = 0.0 | |
for ib in range( nbatchV ): | |
ii = biV[ib, :] | |
Xin, Zteacher = setData( XV[ii, :], Xm, aetype = 'Noisy-Org' ) | |
tmp, Z = ae.output( Xin ) | |
sqeV += np.sum( ae.cost( Z, Zteacher ) ) | |
print i, sqeL / NL, sqeV / NV | |
##### setting the test data | |
# | |
XT, labT = mnist_sub.getDataT( dirMNIST = dirMNIST ) | |
NT, D = XT.shape | |
biT = mnist_sub.makeBatchIndex( NT, batchsize ) | |
nbatchT = biT.shape[0] | |
# test error for Noisy-Org | |
print '### test: NT = ', NT | |
sqeT = 0.0 | |
for ib in range( nbatchT ): | |
ii = biT[ib, :] | |
Xin, Zteacher = setData( XT[ii, :], Xm, aetype = 'Noisy-Org' ) | |
tmp, Z = ae.output( Xin ) | |
sqeT += np.sum( ae.cost( Z, Zteacher ) ) | |
print i, sqeL / NL, sqeV / NV, sqeT / NT | |
# visualizing the reconstruction for noisy test data | |
Xin, Zteacher = setData( XT[:50, :], Xm, aetype = 'Noisy-Org' ) | |
tmp, Z = ae.output( Xin ) | |
img = mnist_sub.visualize( XT[:50, :] * 255, 10, 5 ) | |
cv2.imwrite( 'hogeXorg.png', img ) | |
img = mnist_sub.visualize( ( Xin + Xm ) * 255, 10, 5 ) | |
cv2.imwrite( 'hogeXnoisy.png', img ) | |
img = mnist_sub.visualize( ( Z + Xm ) * 255, 10, 5 ) | |
cv2.imwrite( 'hogeZ.png', img ) | |
# visualizing the network weights | |
if ae.Layers[0].withBias: | |
W0 = ae.Layers[0].getParams()[0] | |
else: | |
W0 = ae.Layers[0].getParams() | |
absmax = np.max( np.abs( W0 ), axis = 1 ) | |
W0 = W0 / absmax[:, np.newaxis] * 127 + 128 | |
img = mnist_sub.visualize( W0[:100], 10, 10 ) | |
cv2.imwrite( 'hogeW0.png', img ) | |
if ae.Layers[1].withBias: | |
W1 = ae.Layers[1].getParams()[0].T | |
else: | |
W1 = ae.Layers[1].getParams().T | |
absmax = np.max( np.abs( W1 ), axis = 1 ) | |
W1 = W1 / absmax[:, np.newaxis] * 127 + 128 | |
img = mnist_sub.visualize( W1[:100], 10, 10 ) | |
cv2.imwrite( 'hogeW1.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 struct | |
import os | |
import numpy as np | |
class MNIST: | |
def __init__( self, LT, dirMNIST = '.' ): | |
self.nclass = 10 | |
self.LT = LT | |
if self.LT == 'L': | |
self.fnLabel = os.path.join( dirMNIST, 'train-labels-idx1-ubyte' ) | |
self.fnImage = os.path.join( dirMNIST, 'train-images-idx3-ubyte' ) | |
else: | |
self.fnLabel = os.path.join( dirMNIST, 't10k-labels-idx1-ubyte' ) | |
self.fnImage = os.path.join( dirMNIST, 't10k-images-idx3-ubyte' ) | |
def getLabel( self ): | |
return _readLabel( self.fnLabel ) | |
def getImage( self ): | |
return _readImage( self.fnImage ) | |
##### reading the label file | |
# | |
def _readLabel( fnLabel ): | |
f = open( fnLabel, 'r' ) | |
### header (two 4B integers, magic number(2049) & number of items) | |
# | |
header = f.read( 8 ) | |
mn, num = struct.unpack( '>2i', header ) # MSB first (bigendian) | |
assert( mn == 2049 ) | |
#print mn, num | |
### labels (unsigned byte) | |
# | |
label = np.array( struct.unpack( '>%dB' % num, f.read() ), dtype = int ) | |
f.close() | |
return label | |
##### reading the image file | |
# | |
def _readImage( fnImage ): | |
f = open( fnImage, 'r' ) | |
### header (four 4B integers, magic number(2051), #images, #rows, and #cols | |
# | |
header = f.read( 16 ) | |
mn, num, nrow, ncol = struct.unpack( '>4i', header ) # MSB first (bigendian) | |
assert( mn == 2051 ) | |
### pixels (unsigned byte) | |
# | |
npixel = ncol * nrow | |
pixel = np.empty( ( num, npixel ) ) | |
for i in range( num ): | |
buf = struct.unpack( '>%dB' % npixel, f.read( npixel ) ) | |
pixel[i, :] = np.asarray( buf ) | |
f.close() | |
return pixel | |
if __name__ == '__main__': | |
dirMNIST = '.' | |
print '# MNIST training data' | |
mnist = MNIST( 'L', dirMNIST = dirMNIST ) | |
lab = mnist.getLabel() | |
dat = mnist.getImage() | |
print lab.shape, dat.shape | |
print '# MNIST test data' | |
mnist = MNIST( 'T', dirMNIST = dirMNIST ) | |
lab = mnist.getLabel() | |
dat = mnist.getImage() | |
print lab.shape, dat.shape | |
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 mnist150808 as mnist | |
def getDataLV( dirMNIST = '.' ): | |
mn = mnist.MNIST( 'L', dirMNIST = dirMNIST ) | |
X = np.asarray( mn.getImage() / 255, dtype = np.float32 ) # => in [0,1] | |
lab = np.asarray( mn.getLabel(), dtype = np.int32 ) | |
XL, labL = X[:50000], lab[:50000] | |
XV, labV = X[50000:], lab[50000:] | |
return XL, labL, XV, labV | |
def getDataT( dirMNIST = '.' ): | |
mn = mnist.MNIST( 'T', dirMNIST = dirMNIST ) | |
XT = np.asarray( mn.getImage() / 255, dtype = np.float32 ) # => in [0,1] | |
labT = np.asarray( mn.getLabel(), dtype = np.int32 ) | |
return XT, labT | |
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 | |
def addSaltPepperNoise( Xbatch, p ): | |
Xnoisy = np.copy( Xbatch ) | |
pvec = np.random.random_sample( Xbatch.shape[0] * Xbatch.shape[1] ) | |
idxB = pvec < p/2 | |
idxW = ( p/2 <= pvec ) * ( pvec < p ) | |
Xnoisy2 = Xnoisy.reshape( -1 ) | |
Xnoisy2[idxB] = 0.0 | |
Xnoisy2[idxW] = 1.0 | |
return Xnoisy | |
def shift( Xbatch, dmax ): | |
nrow = ncol = 28 | |
N = Xbatch.shape[0] | |
delta = np.random.randint( -dmax, dmax + 1, ( N, 2 ) ) | |
Xnoisy = np.zeros_like( Xbatch ) | |
for i in range( N ): | |
src = Xbatch[i, :].reshape( ( nrow, ncol ) ) | |
dst = np.zeros( ( nrow + 2*dmax, ncol + 2*dmax ) ) | |
dx, dy = delta[i, 0], delta[i, 1] | |
dst[dmax+dy:dmax+dy+nrow, dmax+dx:dmax+dx+ncol] = src | |
Xnoisy[i, :] = dst[dmax:dmax+nrow, dmax:dmax+ncol].reshape( -1 ) | |
return Xnoisy | |
def visualize( src, nx, ny, nrow = 28, ncol = 28, gap = 4 ): | |
src2 = src.reshape( ( ny, nx, nrow, ncol ) ) | |
w = nx * ( ncol + gap ) + gap | |
h = ny * ( nrow + gap ) + gap | |
img = np.zeros( ( h, w ), dtype = int ) + 128 | |
for iy in range( ny ): | |
lty = iy * ( nrow + gap ) + gap | |
for ix in range( nx ): | |
ltx = ix * ( ncol + gap ) + gap | |
img[lty:lty+nrow, ltx:ltx+ncol] = src2[iy, ix, :, :] | |
return img |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment