def evaluate():
g = tf.Graph()
with g.as_default():
# load data get iterator
data_loader = data_utils_mean.DataLoader(SEQUENCE_LENGTH, BATCH_SIZE,
NUM_EPOCHS)
iterator = data_loader.load_data(VALID_TFR_PATH, False)
frameNo, image, label = iterator.get_next()
# define model graph
# VGG FACE network
VGGFace_network = vgg_face.VGGFace(SEQUENCE_LENGTH * BATCH_SIZE)
image_batch = tf.reshape(image, [-1, 96, 96, 3])
VGGFace_network.setup(
image_batch
) # image_batch is a tensor of shape (batch_size*seq_length,image_dim,image_dim,3)
face_output = VGGFace_network.get_face_fc0()
# RNN part
rnn_in = reshape_to_rnn(face_output)
prediction = models.get_prediction_indRNN(rnn_in)
prediction = tf.reshape(prediction, [BATCH_SIZE, SEQUENCE_LENGTH, 2])
label_batch = tf.reshape(label, [BATCH_SIZE, SEQUENCE_LENGTH, 2])
# Computing MSE and Concordance values, and adding them to summary
names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
'eval/mse_valence':
slim.metrics.streaming_mean_squared_error(prediction[:, :, 0],
label_batch[:, :, 0]),
'eval/mse_arousal':
slim.metrics.streaming_mean_squared_error(prediction[:, :, 1],
label_batch[:, :, 1]),
})
summary_ops = []
conc_total = 0
mse_total = 0
for i, name in enumerate(['valence', 'arousal']):
with tf.name_scope(name) as scope:
concordance_cc2, values, updates = metrics.concordance_cc2(
tf.reshape(prediction[:, :, i], [-1]),
tf.reshape(label_batch[:, :, i], [-1]))
for n, v in updates.items():
names_to_updates[n + '/' + name] = v
op = tf.summary.scalar('eval/concordance_' + name, concordance_cc2)
op = tf.Print(op, [concordance_cc2], 'eval/concordance_' + name)
summary_ops.append(op)
mse_eval = 'eval/mse_' + name
op = tf.summary.scalar(mse_eval, names_to_values[mse_eval])
op = tf.Print(op, [names_to_values[mse_eval]], mse_eval)
summary_ops.append(op)
mse_total += names_to_values[mse_eval]
conc_total += concordance_cc2
conc_total = conc_total / 2
mse_total = mse_total / 2
op = tf.summary.scalar('eval/concordance_total', conc_total)
op = tf.Print(op, [conc_total], 'eval/concordance_total')
summary_ops.append(op)
op = tf.summary.scalar('eval/mse_total', mse_total)
op = tf.Print(op, [mse_total], 'eval/mse_total')
summary_ops.append(op)
num_batches = int(NUM_BATCHES)
loggingTF.set_verbosity(1)
if not os.path.exists(SUMMARY_PATH):
os.makedirs(SUMMARY_PATH)
# always check latest ckpt and wait for next.
slim.evaluation.evaluation_loop(
'',
CHECK_POINT_DIR,
SUMMARY_PATH,
num_evals=num_batches,
eval_op=list(names_to_updates.values()),
summary_op=tf.summary.merge(summary_ops),
eval_interval_secs=EVAL_INTERVAL_SECS,
)
def evaluate():
g = tf.Graph()
with g.as_default():
# load data get iterator
data_loader = data_utils_mean.DataLoader(SEQUENCE_LENGTH, BATCH_SIZE,
NUM_EPOCHS)
iterator = data_loader.load_data(TEST_TFR_PATH, False)
frameNo, image, label = iterator.get_next()
# define model graph
image_batch = tf.reshape(image, [-1, 96, 96, 3])
# Construct and return the model
network_fn = nets_factory.get_network_fn(name='densenet161',
num_classes=None,
weight_decay=0.00004,
data_format='NHWC',
is_training=False)
face_output, _ = network_fn(image_batch)
# RNN part
rnn_in = reshape_to_rnn(face_output)
prediction = models.get_prediction_atten(rnn_in)
prediction = tf.reshape(prediction, [BATCH_SIZE, SEQUENCE_LENGTH, 2])
label_batch = tf.reshape(label, [BATCH_SIZE, SEQUENCE_LENGTH, 2])
# Computing MSE and Concordance values, and adding them to summary
names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
'eval/mse_valence':
slim.metrics.streaming_mean_squared_error(prediction[:, :, 0],
label_batch[:, :, 0]),
'eval/mse_arousal':
slim.metrics.streaming_mean_squared_error(prediction[:, :, 1],
label_batch[:, :, 1]),
})
summary_ops = []
conc_total = 0
mse_total = 0
for i, name in enumerate(['valence', 'arousal']):
with tf.name_scope(name) as scope:
concordance_cc2, values, updates = metrics.concordance_cc2(
tf.reshape(prediction[:, :, i], [-1]),
tf.reshape(label_batch[:, :, i], [-1]))
for n, v in updates.items():
names_to_updates[n + '/' + name] = v
op = tf.summary.scalar('eval/concordance_' + name, concordance_cc2)
op = tf.Print(op, [concordance_cc2], 'eval/concordance_' + name)
summary_ops.append(op)
mse_eval = 'eval/mse_' + name
op = tf.summary.scalar(mse_eval, names_to_values[mse_eval])
op = tf.Print(op, [names_to_values[mse_eval]], mse_eval)
summary_ops.append(op)
mse_total += names_to_values[mse_eval]
conc_total += concordance_cc2
conc_total = conc_total / 2
mse_total = mse_total / 2
op = tf.summary.scalar('eval/concordance_total', conc_total)
op = tf.Print(op, [conc_total], 'eval/concordance_total')
summary_ops.append(op)
op = tf.summary.scalar('eval/mse_total', mse_total)
op = tf.Print(op, [mse_total], 'eval/mse_total')
summary_ops.append(op)
num_batches = int(NUM_BATCHES)
loggingTF.set_verbosity(1)
if not os.path.exists(SUMMARY_PATH):
os.makedirs(SUMMARY_PATH)
slim.evaluation.evaluate_once(
'',
MODEL_PATH,
SUMMARY_PATH,
num_evals=num_batches,
eval_op=list(names_to_updates.values()),
summary_op=tf.summary.merge(summary_ops),
)
def evaluate(data_folder):
g = tf.Graph()
with g.as_default():
# Load dataset.
frames, audio, ground_truth, _ = data_provider.get_split(
data_folder, False, FLAGS.portion, FLAGS.batch_size,
FLAGS.seq_length)
# Define model graph.
with slim.arg_scope([slim.batch_norm, slim.layers.dropout],
is_training=False):
with slim.arg_scope(
slim.nets.resnet_utils.resnet_arg_scope(
is_training=False)):
prediction = models.get_model(FLAGS.model)(
frames, audio, hidden_units=FLAGS.hidden_units)
# Computing MSE and Concordance values, and adding them to summary
names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
'eval/mse_arousal':
slim.metrics.streaming_mean_squared_error(prediction[:, :, 0],
ground_truth[:, :, 0]),
'eval/mse_valence':
slim.metrics.streaming_mean_squared_error(prediction[:, :, 1],
ground_truth[:, :, 1]),
})
summary_ops = []
conc_total = 0
mse_total = 0
for i, name in enumerate(['arousal', 'valence']):
with tf.name_scope(name) as scope:
concordance_cc2, values, updates = metrics.concordance_cc2(
tf.reshape(prediction[:, :, i], [-1]),
tf.reshape(ground_truth[:, :, i], [-1]))
for n, v in updates.items():
names_to_updates[n + '/' + name] = v
op = tf.summary.scalar('eval/concordance_' + name, concordance_cc2)
op = tf.Print(op, [concordance_cc2], 'eval/concordance_' + name)
summary_ops.append(op)
mse_eval = 'eval/mse_' + name
op = tf.summary.scalar(mse_eval, names_to_values[mse_eval])
op = tf.Print(op, [names_to_values[mse_eval]], mse_eval)
summary_ops.append(op)
mse_total += names_to_values[mse_eval]
conc_total += concordance_cc2
conc_total = conc_total / 2
mse_total = mse_total / 2
op = tf.summary.scalar('eval/concordance_total', conc_total)
op = tf.Print(op, [conc_total], 'eval/concordance_total')
summary_ops.append(op)
op = tf.summary.scalar('eval/mse_total', mse_total)
op = tf.Print(op, [mse_total], 'eval/mse_total')
summary_ops.append(op)
num_examples = FLAGS.num_examples
num_batches = int(num_examples / (FLAGS.batch_size * FLAGS.seq_length))
logging.set_verbosity(1)
# Setup the global step.
eval_interval_secs = FLAGS.eval_interval_secs # How often to run the evaluation.
slim.evaluation.evaluation_loop(
'',
FLAGS.checkpoint_dir,
FLAGS.log_dir,
num_evals=num_batches,
eval_op=list(names_to_updates.values()),
summary_op=tf.summary.merge(summary_ops),
eval_interval_secs=eval_interval_secs)
