def test_backbone_feats(self):
config = hparams_config.get_efficientdet_config('efficientdet-d0')
images = tf.ones([4, 224, 224, 3])
feats = efficientdet_arch.build_backbone(images, config)
self.assertEqual(list(feats.keys()), [0, 1, 2, 3, 4, 5])
self.assertEqual(feats[0].shape, [4, 224, 224, 3])
self.assertEqual(feats[5].shape, [4, 7, 7, 320])
def test_backbone(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)
sess.run(tf.global_variables_initializer())
feats1 = 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.build_backbone(feats, config)
sess.run(tf.global_variables_initializer())
feats2 = sess.run(feats)
for key in list(feats.keys()):
self.assertAllEqual(feats1[key], feats2[key])
def test_backbone(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_keras.build_backbone(feats, config)
sess.run(tf.global_variables_initializer())
keras_feats = 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.build_backbone(feats, config)
sess.run(tf.global_variables_initializer())
legacy_feats = sess.run(feats)
for i, feat in enumerate(keras_feats):
level = i + config.min_level
self.assertAllClose(feat, legacy_feats[level])
def efficientdet(features, model_name=None, config=None, **kwargs):
"""Build EfficientDet model.
Args:
features: input tensor.
model_name: String of the model (eg. efficientdet-d0)
config: Dict of parameters for the network
**kwargs: other parameters.
Returns:
A tuple (class_outputs, box_outputs) for predictions.
"""
if not config and not model_name:
raise ValueError('please specify either model name or config')
if not config:
config = hparams_config.get_efficientdet_config(model_name)
elif isinstance(config, dict):
config = hparams_config.Config(config) # wrap dict in Config object
if kwargs:
config.override(kwargs)
logging.info(config)
# build backbone features.
features = legacy_arch.build_backbone(features, config)
logging.info('backbone params/flops = {:.6f}M, {:.9f}B'.format(
*utils.num_params_flops()))
# build feature network.
fpn_feats = legacy_arch.build_feature_network(features, config)
logging.info('backbone+fpn params/flops = {:.6f}M, {:.9f}B'.format(
*utils.num_params_flops()))
# build class and box predictions.
class_box = BuildClassAndBoxOutputs(**config)
class_outputs, box_outputs = class_box.call(fpn_feats)
logging.info('backbone+fpn+box params/flops = {:.6f}M, {:.9f}B'.format(
*utils.num_params_flops()))
return class_outputs, box_outputs
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.build_backbone(feats, config)
feats = legacy_arch.build_feature_network(feats, config)
feats = legacy_arch.build_class_and_box_outputs(feats, 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])
