def populate_gmms(sample_vids, GMM_OUT, k_gmm, sample_size=400000, PCA=False):
"""
sample_size is the number of IDTFs that we sample from the total_lines number of IDTFs
that were computed previously.
GMM_OUT is the output file to save the list of GMMs.
Saves the GMMs in the GMM_OUT file as the gmm_list attribute.
Returns the list of gmms.
"""
#total_lines = 2488317, sample size=1500000
#total_line (30 classes) = 686680, sample size = 400000
total_lines = total_IDTF_lines()
print total_lines
sample_size = min(total_lines, sample_size)
sample_indices = random.sample(xrange(total_lines), sample_size)
sample_indices.sort()
sample_descriptors = IDT_feature.list_descriptors_sampled(
GMM_dir, sample_vids, sample_indices)
bm_list = IDT_feature.bm_descriptors(sample_descriptors)
#Construct gmm models for each of the different descriptor types.
gmm_list = [gmm_model(bm, k_gmm, PCA=PCA) for bm in bm_list]
print "gmm_list complete"
np.savez(GMM_OUT, gmm_list=gmm_list)
print "Save gmm_list.npz"
return gmm_list
def populate_gmms(PROJ_DIR,TMP_FEATURES,k_gmm,GMM_OUT,sample_size=1500000, PCA=False):
"""
sample_size is the number of IDTFs that we sample from the total_lines number of IDTFs
that were computed previously.
Saves the GMMs in the GMM_OUT file as the gmm_list attribute.
PROJ_DIR is the directory of the project (directory where we save the gmm_list)
TMP_FEATURES is the directory of the temporary .feature vectors
Returns the list of gmms.
"""
feature_list = [filename for filename in os.listdir(TMP_FEATURES) if filename.endswith('.features')]
#total_lines = 2488317
total_lines = total_IDTF_lines(TMP_FEATURES)
print "Total IDTFs constructed", total_lines
sample_size = min(total_lines,sample_size)
sample_indices = random.sample(xrange(total_lines),sample_size)
sample_indices.sort()
sample_descriptors = IDT_feature.list_descriptors_sampled(TMP_FEATURES, feature_list, sample_indices)
bm_list = IDT_feature.bm_descriptors(sample_descriptors)
#Construct gmm models for each of the different descriptor types.
gmm_list = [gmm_model(bm, k_gmm, PCA=PCA) for bm in bm_list]
np.savez(GMM_OUT, gmm_list=gmm_list)
return gmm_list
def populate_gmms(sample_vids, GMM_OUT, k_gmm, sample_size=1500000, PCA=False):
"""
sample_size is the number of IDTFs that we sample from the total_lines number of IDTFs
that were computed previously.
GMM_OUT is the output file to save the list of GMMs.
Saves the GMMs in the GMM_OUT file as the gmm_list attribute.
Returns the list of gmms.
"""
#total_lines = 2488317
total_lines = total_IDTF_lines()
print total_lines
sample_size = min(total_lines,sample_size)
sample_indices = random.sample(xrange(total_lines),sample_size)
sample_indices.sort()
sample_descriptors = IDT_feature.list_descriptors_sampled(GMM_dir, sample_vids, sample_indices)
bm_list = IDT_feature.bm_descriptors(sample_descriptors)
#Construct gmm models for each of the different descriptor types.
gmm_list = [gmm_model(bm, k_gmm, PCA=PCA) for bm in bm_list]
np.savez(GMM_OUT, gmm_list=gmm_list)
return gmm_list
def populate_gmms(IDT_DIR, sample_vids, gmm_file, k_gmm, sample_size=1500000, PCA=False):
"""
sample_size is the number of IDTFs that we sample from the total_lines number of IDTFs
that were computed previously.
gmm_file is the output file to save the list of GMMs.
Saves the GMMs in the gmm_file file as the gmm_list attribute.
Returns the list of gmms.
"""
nr_vids = len(sample_vids)
nr_samples_pvid = int(np.ceil(sample_size/nr_vids))
sample_descriptors = IDT_feature.list_descriptors_sampled(IDT_DIR, sample_vids, nr_samples_pvid)
bm_list = IDT_feature.bm_descriptors(sample_descriptors)
# save all sampled descriptors for learning gmm
bm_file = os.path.join(os.path.dirname(gmm_file), 'bm_descriptors_%d' % (sample_size,))
np.savez(bm_file, bm_list=bm_list)
# why sqrt? just like root sift! already done!!
# bm_list[0] = bm_list[0]
# bm_list[1] = np.sqrt(bm_list[1])
# bm_list[2] = np.sqrt(bm_list[2])
# bm_list[3] = np.sqrt(bm_list[3])
# Construct gmm models for each of the different descriptor types.
gmm_list = [gmm_model(bm, k_gmm, PCA=PCA) for bm in bm_list]
np.savez(gmm_file, gmm_list=gmm_list)
return gmm_list
def populate_gmms(sample_vids, GMM_OUT, k_gmm, sample_size=256000, PCA=False):
"""
sample_size is the number of IDTFs that we sample from the total_lines number of IDTFs
that were computed previously.
GMM_OUT is the output file to save the list of GMMs.
Saves the GMMs in the GMM_OUT file as the gmm_list attribute.
Returns the list of gmms.
"""
# total_lines = 3000
# total_lines = 158638780-787-1323 # ucf101
total_lines = 8081693 # something
# print('Counting all IDTF lines')
# total_lines = total_IDTF_lines()
print('All lines: ', str(total_lines))
sample_size = min(total_lines, sample_size)
sample_indices = random.sample(xrange(total_lines), sample_size)
sample_indices.sort()
sample_descriptors = IDT_feature.list_descriptors_sampled(
GMM_dir, sample_vids, sample_indices)
bm_list = IDT_feature.bm_descriptors(sample_descriptors)
#Construct gmm models for each of the different descriptor types.
gmm_list = [gmm_model(bm, k_gmm, PCA=PCA) for bm in bm_list]
np.savez(GMM_OUT, gmm_list=gmm_list)
return gmm_list
def populate_gmms(IDT_DIR,
sample_vids,
gmm_file,
k_gmm,
sample_size=1500000,
PCA=False):
"""
sample_size is the number of IDTFs that we sample from the total_lines number of IDTFs
that were computed previously.
gmm_file is the output file to save the list of GMMs.
Saves the GMMs in the gmm_file file as the gmm_list attribute.
Returns the list of gmms.
"""
nr_vids = len(sample_vids)
nr_samples_pvid = int(np.ceil(sample_size / nr_vids))
sample_descriptors = IDT_feature.list_descriptors_sampled(
IDT_DIR, sample_vids, nr_samples_pvid)
bm_list = IDT_feature.bm_descriptors(sample_descriptors)
# save all sampled descriptors for learning gmm
bm_file = os.path.join(os.path.dirname(gmm_file),
'bm_descriptors_%d' % (sample_size, ))
np.savez(bm_file, bm_list=bm_list)
# why sqrt? just like root sift! already done!!
# bm_list[0] = bm_list[0]
# bm_list[1] = np.sqrt(bm_list[1])
# bm_list[2] = np.sqrt(bm_list[2])
# bm_list[3] = np.sqrt(bm_list[3])
# Construct gmm models for each of the different descriptor types.
gmm_list = [gmm_model(bm, k_gmm, PCA=PCA) for bm in bm_list]
np.savez(gmm_file, gmm_list=gmm_list)
return gmm_list
