def readXVecsFromOpenedFile(file, dim, count, extension):
if extension == 'bvecs':
points = yael.fvec_new(dim * count)
yael.b2fvecs_fread(file, points, count)
a = yael.fvec_to_numpy(points, (count, dim))
yael.free(points)
return a
elif extension == 'fvecs':
points = yael.fvec_new(dim * count)
yael.fvecs_fread(file, points, count, dim)
a = yael.fvec_to_numpy(points, (count, dim))
yael.free(points)
return a
else:
raise Exception('Bad file extension!')
def readXVecsFromOpenedFile(file, dim, count, extension):
if extension == 'bvecs':
points = yael.fvec_new(dim * count)
yael.b2fvecs_fread(file, points, count)
a = yael.fvec_to_numpy(points, (count, dim))
yael.free(points)
return a
elif extension == 'fvecs':
points = yael.fvec_new(dim * count)
yael.fvecs_fread(file, points, count, dim)
a = yael.fvec_to_numpy(points, (count, dim))
yael.free(points)
return a
else:
raise Exception('Bad file extension!')
def descs_to_sstats(xx, gmm):
""" Converts the descriptors to sufficient statistics.
Inputs
------
xx: array [nr_descs, nr_dimensions]
Data matrix containing the descriptors.
gmm: yael.gmm instance
Mixture of Gaussian object.
Output
------
sstats: array [nr_clusters + 2 * nr_clusters * nr_dimensions, ]
Concatenation of the averaged posterior probabilities `Q_sum`, the
first moment `Q_xx` and second-order moment `Q_xx_2`.
"""
xx = np.atleast_2d(xx)
N = xx.shape[0]
K = gmm.k
D = gmm.d
# Compute posterior probabilities using yael.
Q_yael = fvec_new(N * K)
gmm_compute_p(N, numpy_to_fvec_ref(xx), gmm, Q_yael, GMM_FLAGS_W)
Q = fvec_to_numpy(Q_yael, N * K).reshape(N, K) # NxK
yael.free(Q_yael)
# Compute statistics.
sstats = np.zeros(K + 2 * K * D, dtype=np.float32)
sstats[:K] = np.sum(Q, 0) / N # 1xK
sstats[K:K + K * D] = dot(Q.T, xx).flatten() / N # 1xKD
sstats[K + K * D:K + 2 * K * D] = dot(Q.T, xx**2).flatten() / N # 1xKD
return sstats
def descs_to_sstats(xx, gmm):
""" Converts the descriptors to sufficient statistics.
Inputs
------
xx: array [nr_descs, nr_dimensions]
Data matrix containing the descriptors.
gmm: yael.gmm instance
Mixture of Gaussian object.
Output
------
Q_sum: array [nr_clusters, ]
Averaged posterior probabilities.
"""
K = gmm.k
N = xx.shape[0]
# Compute posterior probabilities using yael.
Q_yael = fvec_new(N * K)
gmm_compute_p(N, numpy_to_fvec_ref(xx), gmm, Q_yael, GMM_FLAGS_W)
Q = fvec_to_numpy(Q_yael, N * K).reshape(N, K)
yael.free(Q_yael)
# Compute statistics.
Q_sum = sum(Q, 0) / N # 1xK
return np.array(Q_sum, dtype=np.float32)
def descs_to_sstats(xx, gmm):
""" Converts the descriptors to sufficient statistics.
Inputs
------
xx: array [nr_descs, nr_dimensions]
Data matrix containing the descriptors.
gmm: yael.gmm instance
Mixture of Gaussian object.
Output
------
sstats: array [nr_clusters + 2 * nr_clusters * nr_dimensions, ]
Concatenation of the averaged posterior probabilities `Q_sum`, the
first moment `Q_xx` and second-order moment `Q_xx_2`.
"""
xx = np.atleast_2d(xx)
N = xx.shape[0]
K = gmm.k
D = gmm.d
# Compute posterior probabilities using yael.
Q_yael = fvec_new(N * K)
gmm_compute_p(N, numpy_to_fvec_ref(xx), gmm, Q_yael, GMM_FLAGS_W)
Q = fvec_to_numpy(Q_yael, N * K).reshape(N, K) # NxK
yael.free(Q_yael)
# Compute statistics.
sstats = np.zeros(K + 2 * K * D, dtype=np.float32)
sstats[: K] = np.sum(Q, 0) / N # 1xK
sstats[K: K + K * D] = dot(Q.T, xx).flatten() / N # 1xKD
sstats[K + K * D: K + 2 * K * D] = dot(
Q.T, xx ** 2).flatten() / N # 1xKD
return sstats
def descs_to_sstats(xx, gmm):
""" Converts the descriptors to sufficient statistics.
Inputs
------
xx: array [nr_descs, nr_dimensions]
Data matrix containing the descriptors.
gmm: yael.gmm instance
Mixture of Gaussian object.
Output
------
Q_sum: array [nr_clusters, ]
Averaged posterior probabilities.
"""
K = gmm.k
N = xx.shape[0]
# Compute posterior probabilities using yael.
Q_yael = fvec_new(N * K)
gmm_compute_p(N, numpy_to_fvec_ref(xx), gmm, Q_yael, GMM_FLAGS_W)
Q = fvec_to_numpy(Q_yael, N * K).reshape(N, K)
yael.free(Q_yael)
# Compute statistics.
Q_sum = sum(Q, 0) / N # 1xK
return np.array(Q_sum, dtype=np.float32)
def gmm_predict_proba(xx, gmm):
"""Computes posterior probabilities using yael."""
N = xx.shape[0]
K = gmm.k
Q_yael = yael.fvec_new(N * K)
yael.gmm_compute_p(
N, yael.numpy_to_fvec_ref(xx), gmm, Q_yael, yael.GMM_FLAGS_W)
Q = yael.fvec_to_numpy(Q_yael, N * K).reshape(N, K)
yael.free(Q_yael)
return Q
def readXvecs(filename, dim, count, tonumpy=True):
extension = filename.strip().split('.')[-1]
if extension == 'bvecs':
points = yael.fvec_new(dim * count)
yael.b2fvecs_read(filename, dim, count, points)
if tonumpy:
a = yael.fvec_to_numpy(points, (count, dim))
yael.free(points)
return a
else:
return points
elif extension == 'fvecs':
points = yael.fvec_new(dim * count)
yael.fvecs_read(filename, dim, count, points)
if tonumpy:
a = yael.fvec_to_numpy(points, (count, dim))
yael.free(points)
return a
else:
return points
elif extension == 'i8vecs':
file = open(filename, 'r')
points = np.zeros((count, dim), dtype='float32')
for i in xrange(count):
file.read(4)
points[i,:] = np.fromfile(file, np.int8, dim).astype('float32')
return points
elif extension == 'ivecs':
points = yael.ivec_new(dim * count)
yael.ivecs_fread(open(filename, 'r'), points, count, dim)
if tonumpy:
a = yael.ivec_to_numpy(points, (count, dim))
yael.free(points)
return a
else:
return points
else:
raise Exception('Bad file extension!')
def readXvecs(filename, dim, count, tonumpy=True):
extension = filename.strip().split('.')[-1]
if extension == 'bvecs':
points = yael.fvec_new(dim * count)
yael.b2fvecs_read(filename, dim, count, points)
if tonumpy:
a = yael.fvec_to_numpy(points, (count, dim))
yael.free(points)
return a
else:
return points
elif extension == 'fvecs':
points = yael.fvec_new(dim * count)
yael.fvecs_read(filename, dim, count, points)
if tonumpy:
a = yael.fvec_to_numpy(points, (count, dim))
yael.free(points)
return a
else:
return points
elif extension == 'i8vecs':
file = open(filename, 'r')
points = np.zeros((count, dim), dtype='float32')
for i in xrange(count):
file.read(4)
points[i, :] = np.fromfile(file, np.int8, dim).astype('float32')
return points
elif extension == 'ivecs':
points = yael.ivec_new(dim * count)
yael.ivecs_fread(open(filename, 'r'), points, count, dim)
if tonumpy:
a = yael.ivec_to_numpy(points, (count, dim))
yael.free(points)
return a
else:
return points
else:
raise Exception('Bad file extension!')
def descs_to_spatial_sstats(xx, ll, gmm):
""" Computes spatial statistics from descriptors and their position.
Inputs
------
xx: array [N, D], required
N D-dimensional descriptors from an video (usually, after they are
processed with PCA).
ll: array [N, 3], required
Descriptor locations in an image; on each row, we have the triplet
(x, y, t).
gmm: instance of yael object gmm
Gauassian mixture object.
Output
------
ss: array [1, K + 2 * 3 * k]
Sufficient statistics in the form of a vector that concatenates
(i) the sum of posteriors, (ii) an expected value of the locations
ll under the posterior distribution Q and (iii) the second-order
moment of the locations ll under the posterior distribution Q.
"""
N = ll.shape[0]
K = gmm.k
# Compute posterior probabilities using yael.
Q_yael = fvec_new(N * K)
gmm_compute_p(N, numpy_to_fvec_ref(xx), gmm, Q_yael, GMM_FLAGS_W)
Q = fvec_to_numpy(Q_yael, N * K).reshape(N, K)
yael.free(Q_yael)
# Compute statistics.
Q_sum = sum(Q, 0) / N # 1xK
Q_ll = dot(Q.T, ll).flatten() / N # 1x3K
Q_ll_2 = dot(Q.T, ll ** 2).flatten() / N # 1x3K
return np.array(hstack((Q_sum, Q_ll, Q_ll_2)), dtype=np.float32)
def descs_to_spatial_sstats(xx, ll, gmm):
""" Computes spatial statistics from descriptors and their position.
Inputs
------
xx: array [N, D], required
N D-dimensional descriptors from an video (usually, after they are
processed with PCA).
ll: array [N, 3], required
Descriptor locations in an image; on each row, we have the triplet
(x, y, t).
gmm: instance of yael object gmm
Gauassian mixture object.
Output
------
ss: array [1, K + 2 * 3 * k]
Sufficient statistics in the form of a vector that concatenates
(i) the sum of posteriors, (ii) an expected value of the locations
ll under the posterior distribution Q and (iii) the second-order
moment of the locations ll under the posterior distribution Q.
"""
N = ll.shape[0]
K = gmm.k
# Compute posterior probabilities using yael.
Q_yael = fvec_new(N * K)
gmm_compute_p(N, numpy_to_fvec_ref(xx), gmm, Q_yael, GMM_FLAGS_W)
Q = fvec_to_numpy(Q_yael, N * K).reshape(N, K)
yael.free(Q_yael)
# Compute statistics.
Q_sum = sum(Q, 0) / N # 1xK
Q_ll = dot(Q.T, ll).flatten() / N # 1x3K
Q_ll_2 = dot(Q.T, ll**2).flatten() / N # 1x3K
return np.array(hstack((Q_sum, Q_ll, Q_ll_2)), dtype=np.float32)
#!/usr/bin/env python
from yael import yael
import time
n = 20000 # number of vectors
nq = 1000
d = 128 # dimensionality of the vectors
nt = 2 # number of threads to use
k = 1 # number of nn returned
v = yael.fvec_new_rand(d * n) # random set of vectors
q = yael.fvec_new_rand(d * nq)
idx = yael.ivec_new(nq * k)
dis = yael.fvec_new(nq * k)
t1 = time.time()
yael.knn_thread(nq, n, d, k, v, q, idx, nt)
t2 = time.time()
idx = yael.IntArray.acquirepointer(idx)
print([idx[i] for i in xrange(nq * k)])
print('kmeans performed in %.3fs' % (t2 - t1))
from yael import yael import time n = 20000 # number of vectors nq = 1000 d = 128 # dimensionality of the vectors nt = 2 # number of threads to use k = 1 # number of nn returned v = yael.fvec_new_rand (d * n) # random set of vectors q = yael.fvec_new_rand (d * nq) idx = yael.ivec_new (nq * k) dis = yael.fvec_new (nq * k) t1 = time.time() yael.knn_thread (nq, n, d, k, v, q, idx, nt) t2 = time.time() idx = yael.IntArray.acquirepointer (idx) print [idx[i] for i in xrange (nq * k)] print 'kmeans performed in %.3fs' % (t2 - t1)
from yael import yael import time k = 100 # number of cluster to create d = 128 # dimensionality of the vectors n = 10000 # number of vectors nt = 10 # number of threads to use v = yael.fvec_new_rand (d * n) # random set of vectors niter = 30 # number of iterations redo = 1 # number of redo #[centroids, dis, assign] = yael_kmeans (v, 100, 'nt', 2, 'niter', 25); centroids = yael.fvec_new (d * k) # output: centroids dis = yael.fvec_new (n) # point-to-cluster distance assign = yael.ivec_new (n) # quantization index of each point nassign = yael.ivec_new (k) # output: number of vectors assigned to each centroid nassign = yael.IntArray.acquirepointer (nassign) t1 = time.time() yael.kmeans (d, n, k, niter, v, nt, 0, redo, centroids, dis, assign, nassign) t2 = time.time() print [nassign[i] for i in xrange(k)] print 'kmeans performed in %.3fs' % (t2 - t1)