def test_model_variables(self):
with tf.Graph().as_default():
feats = tf.random.uniform([1, 512, 512, 3])
efficientdet_arch_keras.efficientdet('efficientdet-d0')(feats)
vars1 = [var.name for var in tf.global_variables()]
with tf.Graph().as_default():
feats = tf.random.uniform([1, 512, 512, 3])
legacy_arch.efficientdet(feats, 'efficientdet-d0')
vars2 = [var.name for var in tf.global_variables()]
self.assertEqual(vars1, vars2)
def build_model(self, keras=False):
tf.compat.v1.reset_default_graph()
inputs_shape = [1, 512, 512, 3]
inputs = tf.ones(shape=inputs_shape, name='input', dtype=tf.float32)
if not keras:
legacy_arch.efficientdet(inputs,
model_name='efficientdet-d0',
is_training_bn=False,
image_size=512)
else:
efficientdet_arch_keras.efficientdet(inputs,
model_name='efficientdet-d0',
is_training_bn=False,
image_size=512)
return [n.name for n in tf.global_variables()]
def test_model_variables(self):
# TODO(tanmingxing): Re-enable this code once pass internal tests.
feats = tf.ones([1, 512, 512, 3])
model = efficientdet_arch_keras.efficientdet('efficientdet-d0')
model(feats)
vars1 = sorted([var.name for var in model.trainable_variables])
vars2 = sorted([var.name for var in model.variables])
with tf.Graph().as_default():
feats = tf.ones([1, 512, 512, 3])
model = efficientdet_arch_keras.efficientdet('efficientdet-d0')
model(feats)
vars3 = sorted([var.name for var in model.trainable_variables])
vars4 = sorted([var.name for var in model.variables])
with tf.Graph().as_default():
feats = tf.ones([1, 512, 512, 3])
legacy_arch.efficientdet(feats, 'efficientdet-d0')
vars5 = sorted([var.name for var in tf.trainable_variables()])
vars6 = sorted([var.name for var in tf.global_variables()])
self.assertEqual(vars1, vars3)
self.assertEqual(vars3, vars5)
self.assertEqual(vars2, vars4)
self.assertEqual(vars4, vars6)
def model_arch(feats, model_name=None, **kwargs):
"""Construct a model arch for keras models."""
config = hparams_config.get_efficientdet_config(model_name)
config.override(kwargs)
model = efficientdet_arch_keras.efficientdet(model_name,
config=config,
feats=feats)
# convert the list of model outputs to a dictionary with key=level.
cls_out_list, box_out_list = model.outputs[0:5], model.outputs[5:]
assert len(cls_out_list) == config.max_level - config.min_level + 1
assert len(box_out_list) == config.max_level - config.min_level + 1
cls_outputs, box_outputs = {}, {}
for i in range(config.min_level, config.max_level + 1):
cls_outputs[i] = cls_out_list[i - config.min_level]
box_outputs[i] = box_out_list[i - config.min_level]
return cls_outputs, box_outputs
def test_model_variables(self):
feats = tf.ones([1, 512, 512, 3])
model = efficientdet_arch_keras.efficientdet('efficientdet-d0')
model(feats)
vars1 = [var.name for var in model.trainable_variables]
vars3 = [var.name for var in model.variables]
with tf.Graph().as_default():
feats = tf.ones([1, 512, 512, 3])
legacy_arch.efficientdet(feats, 'efficientdet-d0')
vars2 = [var.name for var in tf.trainable_variables()]
vars4 = [var.name for var in tf.global_variables()]
vars1.sort()
vars2.sort()
self.assertEqual(vars1, vars2)
vars3.sort()
vars4.sort()
self.assertEqual(vars3, vars4)
def test_model_output(self):
# TODO(fsx950223): Fix the test case
inputs_shape = [1, 512, 512, 3]
with tf.Session(graph=tf.Graph()) as sess:
feats = tf.ones(inputs_shape)
tf.random.set_random_seed(SEED)
_, class_outputs1, box_outputs1 = efficientdet_arch_keras.efficientdet(
'efficientdet-d0')(feats)
sess.run(tf.global_variables_initializer())
class_output1, box_output1 = sess.run([class_outputs1, box_outputs1])
with tf.Session(graph=tf.Graph()) as sess:
feats = tf.ones(inputs_shape)
tf.random.set_random_seed(SEED)
class_outputs2, box_outputs2 = legacy_arch.efficientdet(
feats, 'efficientdet-d0')
sess.run(tf.global_variables_initializer())
class_output2, box_output2 = sess.run([class_outputs2, box_outputs2])
for i in range(3, 8):
self.assertAllEqual(class_output1[i], class_output2[i])
self.assertAllEqual(box_output1[i], box_output2[i])
def test_model_output(self):
inputs_shape = [1, 512, 512, 3]
config = hparams_config.get_efficientdet_config('efficientdet-d0')
with tf.Session(graph=tf.Graph()) as sess:
feats = tf.ones(inputs_shape)
tf.random.set_random_seed(SEED)
feats = efficientdet_arch_keras.build_backbone(feats, config)
feats = efficientdet_arch_keras.build_feature_network(
feats, config)
feats = efficientdet_arch_keras.build_class_and_box_outputs(
feats, config)
sess.run(tf.global_variables_initializer())
class_output1, box_output1 = sess.run(feats)
with tf.Session(graph=tf.Graph()) as sess:
feats = tf.ones(inputs_shape)
tf.random.set_random_seed(SEED)
feats = legacy_arch.efficientdet(feats, config=config)
sess.run(tf.global_variables_initializer())
class_output2, box_output2 = sess.run(feats)
for i in range(3, 8):
self.assertAllEqual(class_output1[i], class_output2[i])
self.assertAllEqual(box_output1[i], box_output2[i])
with tf.Session(graph=tf.Graph()) as sess:
feats = tf.ones(inputs_shape)
tf.random.set_random_seed(SEED)
feats = efficientdet_arch_keras.efficientdet(config=config)(feats)
sess.run(tf.global_variables_initializer())
class_list, box_list = sess.run(feats)
for i in range(config.min_level, config.max_level + 1):
class_output3[i] = class_list[i - config.min_level]
box_outputs3[i] = box_list[i - config.min_level]
for i in range(3, 8):
# Failing.
self.assertAllEqual(class_output1[i], class_output3[i])
self.assertAllEqual(box_output1[i], box_output3[i])