def validate(sess, paths, actual_issame, seed, batch_size, images_placeholder, phase_train_placeholder, embeddings, nrof_folds=10):
image_size = images_placeholder.get_shape()[1]
# Run forward pass to calculate embeddings
print('Runnning forward pass on LFW images')
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0*nrof_images / batch_size))
emb_list = []
for i in range(nrof_batches):
start_index = i*batch_size
end_index = min((i+1)*batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False, image_size)
feed_dict = { images_placeholder: images, phase_train_placeholder: False }
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), seed, nrof_folds=nrof_folds)
thresholds = np.arange(0, 4, 0.001)
val, val_std, far = facenet.calculate_val(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), 1e-3, seed, nrof_folds=nrof_folds)
return tpr, fpr, accuracy, val, val_std, far
def evaluate_accuracy(sess, images_placeholder, phase_train_placeholder,
embeddings, paths, actual_issame, augument_images,
aug_value):
nrof_images = len(paths)
nrof_batches = int(nrof_images / FLAGS.batch_size
) # Run forward pass on the remainder in the last batch
emb_list = []
for i in range(nrof_batches):
paths_batch = paths[i * FLAGS.batch_size:(i + 1) * FLAGS.batch_size]
images = facenet.load_data(paths_batch, False, False,
FLAGS.orig_image_size)
images_aug = augument_images(images, aug_value)
feed_dict = {
images_placeholder: images_aug,
phase_train_placeholder: False
}
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(
emb_list
) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
_, _, accuracy = facenet.calculate_roc(thresholds, embeddings1,
embeddings2,
np.asarray(actual_issame),
FLAGS.seed)
return accuracy
def evaluate(embeddings, actual_issame, nrof_folds=10, distance_metric=0):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
if distance_metric == 1:
thresholds = np.arange(0, 1, 0.001)
embeddings1 = embeddings[0::2]
embeddings2 = embeddings[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
nrof_folds=nrof_folds,
distance_metric=distance_metric)
thresholds = np.arange(0, 4, 0.001)
if distance_metric == 1:
thresholds = np.arange(0, 1, 0.001)
val, val_std, far = facenet.calculate_val(thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
1e-3,
nrof_folds=nrof_folds,
distance_metric=distance_metric)
f1 = 2 * np.mean(accuracy) * val / (np.mean(accuracy) + val)
return tpr, fpr, accuracy, val, val_std, far, f1
def evaluate_accuracy(sess, images_placeholder, phase_train_placeholder,
image_size, embeddings, paths, actual_issame,
augment_images, aug_value, batch_size, orig_image_size,
seed):
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0 * nrof_images / batch_size))
emb_list = []
for i in range(nrof_batches):
start_index = i * batch_size
end_index = min((i + 1) * batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False, orig_image_size)
images_aug = augment_images(images, aug_value, image_size)
feed_dict = {
images_placeholder: images_aug,
phase_train_placeholder: False
}
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(
emb_list
) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
_, _, accuracy = facenet.calculate_roc(thresholds, embeddings1,
embeddings2,
np.asarray(actual_issame), seed)
return accuracy
def evaluate(embeddings,
actual_issame,
nrof_folds=10,
distance_metric=0,
subtract_mean=False):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = embeddings[0::2]
embeddings2 = embeddings[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
nrof_folds=nrof_folds,
distance_metric=distance_metric,
subtract_mean=subtract_mean)
thresholds = np.arange(0, 4, 0.001)
val, val_std, far = facenet.calculate_val(thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
1e-3,
nrof_folds=nrof_folds,
distance_metric=distance_metric,
subtract_mean=subtract_mean)
return tpr, fpr, accuracy, val, val_std, far
def evaluate(embeddings, actual_issame, nrof_folds=10):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = embeddings[0::2]
embeddings2 = embeddings[1::2]
# tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2,
# np.asarray(actual_issame), nrof_folds=nrof_folds)
# thresholds = np.arange(0, 4, 0.001)
# val, val_std, far = facenet.calculate_val(thresholds, embeddings1, embeddings2,
# np.asarray(actual_issame), 1e-3, nrof_folds=nrof_folds)
tpr, fpr, accuracy, fp_idx, fn_idx, best_threshold_acc = facenet.calculate_roc(
thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
nrof_folds=nrof_folds)
thresholds = np.arange(0, 4, 0.001)
val, val_std, far, threshold_val = facenet.calculate_val(
thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
1e-3,
nrof_folds=nrof_folds)
return tpr, fpr, accuracy, val, val_std, far, fp_idx, fn_idx, best_threshold_acc, threshold_val
def validate(sess, paths, actual_issame, seed, batch_size, images_placeholder, phase_train_placeholder, embeddings, nrof_folds=10):
image_size = images_placeholder.get_shape()[1]
# Run forward pass to calculate embeddings
print('Runnning forward pass on LFW images')
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0*nrof_images / batch_size))
emb_list = []
for i in range(nrof_batches):
start_index = i*batch_size
end_index = min((i+1)*batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False, image_size)
feed_dict = { images_placeholder: images, phase_train_placeholder: False }
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), seed, nrof_folds=nrof_folds)
thresholds = np.arange(0, 4, 0.001)
val, val_std, far = facenet.calculate_val(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), 1e-3, seed, nrof_folds=nrof_folds)
return tpr, fpr, accuracy, val, val_std, far
def main():
pairs = read_pairs(os.path.expanduser(FLAGS.lfw_pairs))
paths, actual_issame = get_paths(os.path.expanduser(FLAGS.lfw_dir), pairs)
with tf.Graph().as_default():
# Creates graph from saved GraphDef
# NOTE: This does not work at the moment. Needs tensorflow to store variables in the graph_def.
# graphdef_filename = os.path.join(os.path.expanduser(FLAGS.model_dir), 'graphdef', 'graph_def.pb')
# with gfile.FastGFile(graphdef_filename, 'rb') as f:
# graph_def = tf.GraphDef()
# graph_def.ParseFromString(f.read())
# images_placeholder, phase_train_placeholder, embeddings = tf.import_graph_def(graph_def, return_elements = ['input', 'phase_train', 'embeddings'], name='')
# Placeholder for input images
images_placeholder = tf.placeholder(tf.float32, shape=(FLAGS.batch_size, FLAGS.image_size, FLAGS.image_size, 3), name='input')
# Placeholder for phase_train
phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')
# Build the inference graph
embeddings = facenet.inference_nn4_max_pool_96(images_placeholder, FLAGS.pool_type, FLAGS.use_lrn,
1.0, phase_train=phase_train_placeholder)
# Create a saver for restoring variable averages
ema = tf.train.ExponentialMovingAverage(1.0)
saver = tf.train.Saver(ema.variables_to_restore())
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(os.path.expanduser(FLAGS.model_dir))
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
raise ValueError('Checkpoint not found')
nrof_images = len(paths)
nrof_batches = int(nrof_images / FLAGS.batch_size) # Run forward pass on the remainder in the last batch
emb_list = []
for i in range(nrof_batches):
start_time = time.time()
paths_batch = paths[i*FLAGS.batch_size:(i+1)*FLAGS.batch_size]
images = facenet.load_data(paths_batch, False, False, FLAGS.image_size)
feed_dict = { images_placeholder: images, phase_train_placeholder: False }
emb_list += sess.run([embeddings], feed_dict=feed_dict)
duration = time.time() - start_time
print('Calculated embeddings for batch %d of %d: time=%.3f seconds' % (i+1,nrof_batches, duration))
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2, np.asarray(actual_issame), FLAGS.seed)
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(accuracy)))
facenet.plot_roc(fpr, tpr, 'NN4')
def main():
pairs = read_pairs(os.path.expanduser(FLAGS.lfw_pairs))
paths, actual_issame = get_paths(os.path.expanduser(FLAGS.lfw_dir), pairs)
with tf.Graph().as_default():
with tf.Session() as sess:
# Load the model
print('Loading model "%s"' % FLAGS.model_file)
load_model(FLAGS.model_file)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
image_size = images_placeholder.get_shape()[1]
# Run forward pass to calculate embeddings
nrof_images = len(paths)
nrof_batches = int(nrof_images / FLAGS.batch_size)
emb_list = []
for i in range(nrof_batches):
start_time = time.time()
paths_batch = paths[i * FLAGS.batch_size:(i + 1) *
FLAGS.batch_size]
images = facenet.load_data(paths_batch, False, False,
image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_list += sess.run([embeddings], feed_dict=feed_dict)
duration = time.time() - start_time
print(
'Calculated embeddings for batch %d of %d: time=%.3f seconds'
% (i + 1, nrof_batches, duration))
emb_array = np.vstack(
emb_list
) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(
thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), FLAGS.seed)
print('Accuracy: %1.3f+-%1.3f' %
(np.mean(accuracy), np.std(accuracy)))
facenet.plot_roc(fpr, tpr, 'NN4')
def evaluate(embeddings, seed, actual_issame, nrof_folds=10):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = embeddings[0::2]
embeddings2 = embeddings[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), seed, nrof_folds=nrof_folds)
thresholds = np.arange(0, 4, 0.001)
val, val_std, far = facenet.calculate_val(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), 1e-3, seed, nrof_folds=nrof_folds)
return tpr, fpr, accuracy, val, val_std, far
def evaluate(embeddings, actual_issame, nrof_folds=10):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = embeddings[0::2]
embeddings2 = embeddings[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), nrof_folds=nrof_folds)
thresholds = np.arange(0, 4, 0.001)
val, val_std, far = facenet.calculate_val(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), 1e-3, nrof_folds=nrof_folds)
return tpr, fpr, accuracy, val, val_std, far
def main():
pairs = read_pairs(os.path.expanduser(FLAGS.lfw_pairs))
paths, actual_issame = get_paths(os.path.expanduser(FLAGS.lfw_dir), pairs)
with tf.Graph().as_default():
with tf.Session() as sess:
print('Reading model "%s"' % FLAGS.model_file)
new_saver = tf.train.import_meta_graph(os.path.expanduser(FLAGS.model_file+'.meta'))
all_vars_dict = {var.name: var for var in tf.all_variables()}
restore_vars = {}
for var_name in all_vars_dict:
if '/ExponentialMovingAverage' in var_name:
param_name = var_name.replace('/ExponentialMovingAverage', '')
if param_name in all_vars_dict:
param = all_vars_dict[param_name]
print('%s\t%s' % (var_name, param))
restore_vars[var_name] = param
saver = tf.train.Saver(restore_vars, saver_def=new_saver.as_saver_def())
saver.restore(sess, os.path.expanduser(FLAGS.model_file))
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
image_size = images_placeholder.get_shape()[1]
nrof_images = len(paths)
nrof_batches = int(nrof_images / FLAGS.batch_size) # Run forward pass on the remainder in the last batch
emb_list = []
for i in range(nrof_batches):
start_time = time.time()
paths_batch = paths[i*FLAGS.batch_size:(i+1)*FLAGS.batch_size]
images = facenet.load_data(paths_batch, False, False, image_size)
feed_dict = { images_placeholder: images, phase_train_placeholder: False }
emb_list += sess.run([embeddings], feed_dict=feed_dict)
duration = time.time() - start_time
print('Calculated embeddings for batch %d of %d: time=%.3f seconds' % (i+1,nrof_batches, duration))
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2, np.asarray(actual_issame), FLAGS.seed)
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(accuracy)))
facenet.plot_roc(fpr, tpr, 'NN4')
def validate(sess, dataset, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, prefix_str, summary_writer):
nrof_people = FLAGS.people_per_batch * 4
print('Loading %s data' % prefix_str)
# Sample people and load new data
image_paths, num_per_class = facenet.sample_people(dataset, nrof_people, FLAGS.images_per_person)
image_data = facenet.load_data(image_paths, False, False, FLAGS.image_size)
print('Selecting random triplets from %s set' % prefix_str)
triplets, nrof_triplets = facenet.select_validation_triplets(num_per_class, nrof_people, image_data, FLAGS.batch_size)
start_time = time.time()
anchor_list = []
positive_list = []
negative_list = []
triplet_loss_list = []
# Run a forward pass for the sampled images
print('Running forward pass on %s set' % prefix_str)
nrof_batches_per_epoch = nrof_triplets * 3 // FLAGS.batch_size
for i in xrange(nrof_batches_per_epoch):
batch = facenet.get_triplet_batch(triplets, i, FLAGS.batch_size)
feed_dict = {images_placeholder: batch, phase_train_placeholder: False}
emb, triplet_loss, step = sess.run([embeddings, loss, global_step], feed_dict=feed_dict)
nrof_batch_triplets = emb.shape[0] / 3
anchor_list.append(emb[(0 * nrof_batch_triplets):(1 * nrof_batch_triplets), :])
positive_list.append(emb[(1 * nrof_batch_triplets):(2 * nrof_batch_triplets), :])
negative_list.append(emb[(2 * nrof_batch_triplets):(3 * nrof_batch_triplets), :])
triplet_loss_list.append(triplet_loss)
anchor = np.vstack(anchor_list)
positive = np.vstack(positive_list)
negative = np.vstack(negative_list)
duration = time.time() - start_time
thresholds = np.arange(0, 4, 0.01)
embeddings1 = np.vstack([anchor, anchor])
embeddings2 = np.vstack([positive, negative])
actual_issame = np.asarray([True] * anchor.shape[0] + [False] * anchor.shape[0])
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2, actual_issame, FLAGS.seed)
print('Epoch: [%d]\tTime %.3f\ttripErr %2.3f\t%sAccuracy %1.3f+-%1.3f' % (
epoch, duration, np.mean(triplet_loss_list), prefix_str, np.mean(accuracy), np.std(accuracy)))
# Add validation loss and accuracy to summary
summary = tf.Summary()
summary.value.add(tag='{}_loss'.format(prefix_str), simple_value=np.mean(triplet_loss_list).astype(float))
summary.value.add(tag='{}_accuracy'.format(prefix_str), simple_value=np.mean(accuracy))
summary_writer.add_summary(summary, step)
if False:
facenet.plot_roc(fpr, tpr, 'NN4')
def validate(sess, dataset, epoch, images_placeholder, phase_train_placeholder,
global_step, embeddings, loss, train_op, summary_op, summary_writer):
people_per_batch = FLAGS.people_per_batch * 4
print('Loading validation data')
# Sample people and load new data
image_paths, num_per_class = facenet.sample_people(dataset, people_per_batch, FLAGS.images_per_person)
image_data = facenet.load_data(image_paths)
print('Selecting random triplets for validation')
triplets, nrof_triplets = facenet.select_validation_triplets(num_per_class, people_per_batch, image_data)
start_time = time.time()
anchor_list = []
positive_list = []
negative_list = []
triplet_loss_list = []
# Run a forward pass for the sampled images
print('Running forward pass on validation set')
nrof_batches_per_epoch = nrof_triplets * 3 // FLAGS.batch_size
for i in xrange(nrof_batches_per_epoch):
batch = facenet.get_triplet_batch(triplets, i)
feed_dict = {images_placeholder: batch, phase_train_placeholder: False}
emb, triplet_loss, step = sess.run([embeddings, loss, global_step], feed_dict=feed_dict)
nrof_batch_triplets = emb.shape[0] / 3
anchor_list.append(emb[(0 * nrof_batch_triplets):(1 * nrof_batch_triplets), :])
positive_list.append(emb[(1 * nrof_batch_triplets):(2 * nrof_batch_triplets), :])
negative_list.append(emb[(2 * nrof_batch_triplets):(3 * nrof_batch_triplets), :])
triplet_loss_list.append(triplet_loss)
anchor = np.vstack(anchor_list)
positive = np.vstack(positive_list)
negative = np.vstack(negative_list)
duration = time.time() - start_time
thresholds = np.arange(0, 4, 0.01)
embeddings1 = np.vstack([anchor, anchor])
embeddings2 = np.vstack([positive, negative])
actual_issame = np.asarray([True] * anchor.shape[0] + [False] * anchor.shape[0])
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2, actual_issame)
print('Epoch: [%d]\tTime %.3f\ttripErr %2.3f\taccuracy %1.3f%c%1.3f' % (
epoch, duration, np.mean(triplet_loss_list), np.mean(accuracy), u"\u00B1", np.std(accuracy)))
# Add validation loss and accuracy to summary
summary = tf.Summary()
summary.value.add(tag='validation_loss', simple_value=np.mean(triplet_loss_list).astype(float))
summary.value.add(tag='accuracy', simple_value=np.mean(accuracy))
summary_writer.add_summary(summary, step)
if False:
facenet.plot_roc(fpr, tpr, 'NN4')
def evaluate(embeddings, actual_issame, nrof_folds=10):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01) # 0.01表示步长
# 四个点原来是取奇数和偶数列
embeddings1 = embeddings[0::2] # 取出奇数行的特征，取出偶数行的特征
embeddings2 = embeddings[1::2]
# print(len(embeddings1))
# print('wokao')
# print(len(embeddings2))
tpr, fpr, accuracy, threshold_acc = facenet.calculate_roc(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame),
nrof_folds=nrof_folds) # np.asarray将列表转换为数组
thresholds = np.arange(0, 4, 0.001)
val, val_std, far = facenet.calculate_val(thresholds, threshold_acc, embeddings1, embeddings2,
np.asarray(actual_issame), 1e-3, nrof_folds=nrof_folds)
return tpr, fpr, accuracy, val, val_std, far
def evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, embeddings, paths, actual_issame, augument_images, aug_value):
nrof_images = len(paths)
nrof_batches = int(nrof_images / FLAGS.batch_size) # Run forward pass on the remainder in the last batch
emb_list = []
for i in range(nrof_batches):
paths_batch = paths[i*FLAGS.batch_size:(i+1)*FLAGS.batch_size]
images = facenet.load_data(paths_batch)
images_aug = augument_images(images, aug_value)
feed_dict = { images_placeholder: images_aug, phase_train_placeholder: False }
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
_, _, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2, np.asarray(actual_issame))
return accuracy
def main(argv=None):
pairs = read_pairs(os.path.expanduser(FLAGS.lfw_pairs))
paths, actual_issame = get_paths(os.path.expanduser(FLAGS.lfw_dir), pairs)
with tf.Graph().as_default():
with tf.Session() as sess:
# Load the model
print('Loading model "%s"' % FLAGS.model_file)
facenet.load_model(FLAGS.model_file)
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
image_size = images_placeholder.get_shape()[1]
# Run forward pass to calculate embeddings
nrof_images = len(paths)
nrof_batches = int(nrof_images / FLAGS.batch_size)
emb_list = []
for i in range(nrof_batches):
start_time = time.time()
paths_batch = paths[i*FLAGS.batch_size:(i+1)*FLAGS.batch_size]
images = facenet.load_data(paths_batch, False, False, image_size)
feed_dict = { images_placeholder: images, phase_train_placeholder: False }
emb_list += sess.run([embeddings], feed_dict=feed_dict)
duration = time.time() - start_time
print('Calculated embeddings for batch %d of %d: time=%.3f seconds' % (i+1,nrof_batches, duration))
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2, np.asarray(actual_issame), FLAGS.seed)
print('Accuracy: %1.3f+-%1.3f' % (np.mean(accuracy), np.std(accuracy)))
thresholds = np.arange(0, 4, 0.001)
val, val_std, far = facenet.calculate_val(thresholds, embeddings1, embeddings2, np.asarray(actual_issame), 1e-3, FLAGS.seed)
print('Validation rate: %2.5f+-%2.5f @ FAR=%2.5f' % (val, val_std, far))
facenet.plot_roc(fpr, tpr, 'NN4')
def evaluate_accuracy(sess, images_placeholder, phase_train_placeholder, image_size, embeddings,
paths, actual_issame, augument_images, aug_value, batch_size, orig_image_size, seed):
nrof_images = len(paths)
nrof_batches = int(math.ceil(1.0*nrof_images / batch_size))
emb_list = []
for i in range(nrof_batches):
start_index = i*batch_size
end_index = min((i+1)*batch_size, nrof_images)
paths_batch = paths[start_index:end_index]
images = facenet.load_data(paths_batch, False, False, orig_image_size)
images_aug = augument_images(images, aug_value, image_size)
feed_dict = { images_placeholder: images_aug, phase_train_placeholder: False }
emb_list += sess.run([embeddings], feed_dict=feed_dict)
emb_array = np.vstack(emb_list) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
_, _, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2, np.asarray(actual_issame), seed)
return accuracy
def evaluate(embeddings, actual_issame, nrof_folds=10):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
# Note there that x[startAt:endBefore:skip] is the notation
# so embeddings1 and embeddings2 are simply two lists with
# embeddings1[i] and embeddings2[i] being the pairs that we need to validate
embeddings1 = embeddings[0::2]
embeddings2 = embeddings[1::2]
print("thresholds is: {}".format(thresholds))
print("embeddings1 is: {}".format(embeddings1))
print("embeddings2 is: {}".format(embeddings2))
tpr, fpr, accuracy = facenet.calculate_roc(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), nrof_folds=nrof_folds)
thresholds = np.arange(0, 4, 0.001)
# val is the percentage of samples that were classified to be correct
# val_std is the std of val
# far is the percentage of samples that were classified to be wrong
val, val_std, far = facenet.calculate_val(thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), 1e-3, nrof_folds=nrof_folds)
return tpr, fpr, accuracy, val, val_std, far
def evaluate(embeddings, actual_issame, nrof_folds=10):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
# start from 0, step=2
embeddings1 = embeddings[0::2]
# start from 1, step=2
embeddings2 = embeddings[1::2]
# embeddings1 is corresponding with embeddings2
tpr, fpr, accuracy = facenet.calculate_roc(thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
nrof_folds=nrof_folds)
thresholds = np.arange(0, 4, 0.001)
val, val_std, far = facenet.calculate_val(thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
1e-3,
nrof_folds=nrof_folds)
return tpr, fpr, accuracy, val, val_std, far
def evaluate(embeddings, actual_issame, nrof_folds=10):
# Calculate evaluation metrics
thresholds = np.arange(0, 4, 0.01)
embeddings1 = embeddings[0::2]
embeddings2 = embeddings[1::2]
# ipdb.set_trace()
tpr, fpr, accuracy = facenet.calculate_roc(thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
nrof_folds=nrof_folds)
thresholds = np.arange(0, 4, 0.001)
val, val_std, far = facenet.calculate_val(thresholds,
embeddings1,
embeddings2,
np.asarray(actual_issame),
1e-2,
nrof_folds=nrof_folds)
dot_product_threshold = np.arange(0.0, 1.0, 0.001)
# ipdb.set_trace()
best_threshold, acc_dot, recall, fpr_dot, precision_dot, dot_product_all, fp_idxs, fn_idxs, recall_th, precision_th,\
acc_th = facenet.calculate_acc_dot_product(dot_product_threshold, embeddings1, embeddings2, np.asarray(actual_issame))
return tpr, fpr, accuracy, val, val_std, far, best_threshold, acc_dot, recall, fpr_dot, precision_dot,\
dot_product_all, fp_idxs, fn_idxs, recall_th, precision_th, acc_th
def main():
pairs = read_pairs(os.path.expanduser(FLAGS.lfw_pairs))
paths, actual_issame = get_paths(os.path.expanduser(FLAGS.lfw_dir), pairs)
with tf.Graph().as_default():
with tf.Session() as sess:
print('Reading model "%s"' % FLAGS.model_file)
new_saver = tf.train.import_meta_graph(
os.path.expanduser(FLAGS.model_file + '.meta'))
all_vars_dict = {var.name: var for var in tf.all_variables()}
restore_vars = {}
for var_name in all_vars_dict:
if '/ExponentialMovingAverage' in var_name:
param_name = var_name.replace('/ExponentialMovingAverage',
'')
if param_name in all_vars_dict:
param = all_vars_dict[param_name]
print('%s\t%s' % (var_name, param))
restore_vars[var_name] = param
saver = tf.train.Saver(restore_vars,
saver_def=new_saver.as_saver_def())
saver.restore(sess, os.path.expanduser(FLAGS.model_file))
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
image_size = images_placeholder.get_shape()[1]
nrof_images = len(paths)
nrof_batches = int(
nrof_images / FLAGS.batch_size
) # Run forward pass on the remainder in the last batch
emb_list = []
for i in range(nrof_batches):
start_time = time.time()
paths_batch = paths[i * FLAGS.batch_size:(i + 1) *
FLAGS.batch_size]
images = facenet.load_data(paths_batch, False, False,
image_size)
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb_list += sess.run([embeddings], feed_dict=feed_dict)
duration = time.time() - start_time
print(
'Calculated embeddings for batch %d of %d: time=%.3f seconds'
% (i + 1, nrof_batches, duration))
emb_array = np.vstack(
emb_list
) # Stack the embeddings to a nrof_examples_per_epoch x 128 matrix
thresholds = np.arange(0, 4, 0.01)
embeddings1 = emb_array[0::2]
embeddings2 = emb_array[1::2]
tpr, fpr, accuracy = facenet.calculate_roc(
thresholds, embeddings1, embeddings2,
np.asarray(actual_issame), FLAGS.seed)
print('Accuracy: %1.3f+-%1.3f' %
(np.mean(accuracy), np.std(accuracy)))
facenet.plot_roc(fpr, tpr, 'NN4')