def evaluate(feats, labels, num_pairs=10_000):
indices = range(len(labels))
pairs = [(i, j) for i, j in product(indices, indices) if i != j]
pairs = random.sample(pairs, num_pairs)
sim = lambda u, v: u @ v
x = np.array([sim(feats[i], feats[j]) for i, j in pairs])
y = np.array([int(labels[i] == labels[j]) for i, j in pairs])
eer, thresh = toolkits.calculate_eer(y, x)
eer = eer * 100
print("τ: {:.3f} ".format(thresh))
print("EER: {:.3f}%".format(eer))
def evaluate(feats, labels, pairs):
sys.path.insert(0, "/home/doneata/src/vgg-speaker-recognition/tool")
import toolkits
feats_r, feats_s = feats
labels_r, labels_s = labels
sim = lambda u, v: u @ v
x = np.array([sim(feats_r[i], feats_s[j]) for i, j in pairs])
y = np.array([int(labels_r[i] == labels_s[j]) for i, j in pairs])
eer, thresh = toolkits.calculate_eer(y, x)
eer = eer * 100
print(f"+: {sum(y)} / {len(y)}")
print("τ: {:.3f} ".format(thresh))
print("EER: {:.3f}%".format(eer))
def main():
# gpu configuration
toolkits.initialize_GPU(args)
import model
# ==================================
# Get Train/Val.
# ==================================
print('==> calculating test({}) data lists...'.format(args.test_type))
if args.test_type == 'normal':
verify_list = np.loadtxt('../meta/voxceleb1_veri_test.txt', str)
elif args.test_type == 'hard':
verify_list = np.loadtxt('../meta/voxceleb1_veri_test_hard.txt', str)
elif args.test_type == 'extend':
verify_list = np.loadtxt('../meta/voxceleb1_veri_test_extended.txt',
str)
else:
raise IOError('==> unknown test type.')
verify_lb = np.array([int(i[0]) for i in verify_list])
list1 = np.array([os.path.join(args.data_path, i[1]) for i in verify_list])
list2 = np.array([os.path.join(args.data_path, i[2]) for i in verify_list])
total_list = np.concatenate((list1, list2))
unique_list = np.unique(total_list)
# ==================================
# Get Model
# ==================================
# construct the data generator.
params = {
'dim': (257, 100, 1),
'nfft': 512,
'spec_len': 100,
'win_length': 400,
'hop_length': 160,
'n_classes': 5994,
'sampling_rate': 16000,
'normalize': True,
}
network_eval = model.vggvox_resnet2d_icassp(input_dim=params['dim'],
num_class=params['n_classes'],
mode='eval',
args=args)
# ==> load pre-trained model ???
if args.resume:
# ==> get real_model from arguments input,
# load the model if the imag_model == real_model.
if os.path.isfile(args.resume):
network_eval.load_weights(os.path.join(args.resume), by_name=True)
result_path = set_result_path(args)
print('==> successfully loading model {}.'.format(args.resume))
else:
raise IOError("==> no checkpoint found at '{}'".format(
args.resume))
else:
raise IOError('==> please type in the model to load')
print('==> start testing.')
# The feature extraction process has to be done sample-by-sample,
# because each sample is of different lengths.
total_length = len(unique_list)
feats, scores, labels = [], [], []
for c, ID in enumerate(unique_list):
if c % 50 == 0:
print('Finish extracting features for {}/{}th wav.'.format(
c, total_length))
specs = ut.load_data(ID,
win_length=params['win_length'],
sr=params['sampling_rate'],
hop_length=params['hop_length'],
n_fft=params['nfft'],
spec_len=params['spec_len'],
mode='eval')
specs = np.expand_dims(np.expand_dims(specs, 0), -1)
v = network_eval.predict(specs)
feats += [v]
feats = np.array(feats)
# ==> compute the pair-wise similarity.
for c, (p1, p2) in enumerate(zip(list1, list2)):
ind1 = np.where(unique_list == p1)[0][0]
ind2 = np.where(unique_list == p2)[0][0]
v1 = feats[ind1, 0]
v2 = feats[ind2, 0]
scores += [np.sum(v1 * v2)]
labels += [verify_lb[c]]
print('scores : {}, gt : {}'.format(scores[-1], verify_lb[c]))
scores = np.array(scores)
labels = np.array(labels)
np.save(os.path.join(result_path, 'prediction_scores.npy'), scores)
np.save(os.path.join(result_path, 'groundtruth_labels.npy'), labels)
eer, thresh = toolkits.calculate_eer(labels, scores)
print('==> model : {}, EER: {}'.format(args.resume, eer))