def learn_vocabulary(k, max_iter, single_file, vector_matrix=None, input_path=None):
if vector_matrix is None:
if single_file:
vector_matrix = read_feature_vector(input_path)
else:
file_names = list_all_files(input_path)
vector_matrix = read_feature_vector(input_path + file_names[0])
for f in xrange(1, len(file_names)):
vector = read_feature_vector(input_path + file_names[f])
if vector is not None:
vector_matrix = append(vector_matrix, vector, axis=0)
return mykmeans_plus(data=vector_matrix,k=k, max_iter=max_iter)[0]
def learn_vocabulary(k,
max_iter,
single_file,
vector_matrix=None,
input_path=None):
if vector_matrix is None:
if single_file:
vector_matrix = read_feature_vector(input_path)
else:
file_names = list_all_files(input_path)
vector_matrix = read_feature_vector(input_path + file_names[0])
for f in xrange(1, len(file_names)):
vector = read_feature_vector(input_path + file_names[f])
if vector is not None:
vector_matrix = append(vector_matrix, vector, axis=0)
return mykmeans_plus(data=vector_matrix, k=k, max_iter=max_iter)[0]
def vlad_vector(vector_path, vocabulary):
features = read_feature_vector(vector_path)
codes = vq(features, vocabulary)[0]
vlad = zeros(vocabulary.shape)
for idx in range(codes.size):
diff = subtract(features[idx], vocabulary[codes[idx]])
vlad[codes[idx]] = add(diff, vlad[codes[idx]])
return ndarray.flatten(vlad)
def vlad_vector(vector_path, vocabulary):
features = read_feature_vector(vector_path)
codes_idx = vq(features, vocabulary)[
0] #A length M array holding the code book index for each observation
vlad = zeros(vocabulary.shape)
for i in range(codes_idx.size):
code_idx = codes_idx[i]
diff = subtract(features[i], vocabulary[code_idx])
vlad[code_idx] = add(diff, vlad[code_idx])
return ndarray.flatten(vlad)
