def whiten(data,
V,
m0,
s0,
nprincomps,
batchsize=500,
use_gpu=True,
verbose=True):
data = data.astype(np.float32)
ncases = data.shape[0]
nbatches = (ncases - 1) / batchsize + 1
data_white = np.zeros((ncases, nprincomps), dtype=np.float32)
for bidx in range(nbatches):
start = bidx * batchsize
end = min((bidx + 1) * batchsize, ncases)
if use_gpu:
data[start:end] = theano_subtract_m1(data[start:end])
data[start:end] = theano_divide_s1(data[start:end])
data[start:end] = theano_subtract_row(data[start:end], m0)
data[start:end] = theano_divide_row(data[start:end], s0)
data_white[start:end] = theano_dot(data[start:end],
V[:nprincomps].T)
else:
data[start:end] -= data[start:end].mean(1)[:, None]
s1 = data[start:end].std(1)[:, None]
data[start:end] /= s1 + s1.mean()
data[start:end] -= m0
data[start:end] /= s0
data_white[start:end] = np.dot(data[start:end], V[:nprincomps].T)
return data_white
def whitenX(data, V, m0, s0, nprincomps, batchsize=500, contrast_norm=True, dataset_norm=True, use_gpu=True, verbose=True):
data = data.astype(np.float32)
ncases = data.shape[0]
nbatches = (ncases - 1) / batchsize + 1
V = V[:nprincomps]
V = np.concatenate((V,-1*V),0).T
data_white = np.zeros((ncases, nprincomps*2), dtype=np.float32)
for bidx in range(nbatches):
start = bidx * batchsize
end = min((bidx + 1) * batchsize, ncases)
if use_gpu:
if contrast_norm:
data[start:end] = theano_subtract_m1(data[start:end])
data[start:end] = theano_divide_s1(data[start:end])
if dataset_norm:
data[start:end] = theano_subtract_row(data[start:end], m0)
data[start:end] = theano_divide_row(data[start:end], s0)
data_white[start:end] = theano_dot(data[start:end], V)
else:
if contrast_norm:
data[start:end] -= data[start:end].mean(1)[:, None]
s1 = data[start:end].std(1)[:, None]
data[start:end] /= s1 + s1.mean()
if dataset_norm:
data[start:end] -= m0
data[start:end] /= s0
data_white[start:end] = np.dot(data[start:end], V)
return (data_white > 0.)*data_white
def zca_whiten(data, W, batchsize=500, use_gpu=True, verbose=True):
data = data.astype(np.float32)
ncases = data.shape[0]
nbatches = (ncases - 1) / batchsize + 1
data_white = np.zeros((ncases, data.shape[1]), dtype=np.float32)
for bidx in range(nbatches):
start = bidx * batchsize
end = min((bidx + 1) * batchsize, ncases)
if use_gpu:
data[start:end] = theano_subtract_m1(data[start:end])
data[start:end] = theano_divide_s1(data[start:end])
data_white[start:end] = theano_dot(data[start:end], W)
else:
data[start:end] -= data[start:end].mean(1)[:, None]
s1 = data[start:end].std(1)[:, None]
data[start:end] /= s1 + s1.mean()
data_white[start:end] = np.dot(data[start:end], W)
return data_white
def whitenX(data,
V,
m0,
s0,
nprincomps,
batchsize=500,
contrast_norm=True,
dataset_norm=True,
use_gpu=True,
verbose=True):
data = data.astype(np.float32)
ncases = data.shape[0]
nbatches = (ncases - 1) / batchsize + 1
V = V[:nprincomps]
V = np.concatenate((V, -1 * V), 0).T
data_white = np.zeros((ncases, nprincomps * 2), dtype=np.float32)
for bidx in range(nbatches):
start = bidx * batchsize
end = min((bidx + 1) * batchsize, ncases)
if use_gpu:
if contrast_norm:
data[start:end] = theano_subtract_m1(data[start:end])
data[start:end] = theano_divide_s1(data[start:end])
if dataset_norm:
data[start:end] = theano_subtract_row(data[start:end], m0)
data[start:end] = theano_divide_row(data[start:end], s0)
data_white[start:end] = theano_dot(data[start:end], V)
else:
if contrast_norm:
data[start:end] -= data[start:end].mean(1)[:, None]
s1 = data[start:end].std(1)[:, None]
data[start:end] /= s1 + s1.mean()
if dataset_norm:
data[start:end] -= m0
data[start:end] /= s0
data_white[start:end] = np.dot(data[start:end], V)
return (data_white > 0.) * data_white