def build_backbone(features, config):
backbone_name = config.backbone_name
is_training_bn = config.is_training_bn
if 'efficientnet' in backbone_name:
override_params = {
'relu_fn': tf.nn.swish,
'batch_norm': utils.batch_norm_class(is_training_bn),
}
if 'b0' in backbone_name:
override_params['survival_prob'] = 0.0
if config.backbone_config is not None:
override_params['blocks_args'] = (
efficientnet_builder.BlockDecoder().encode(
config.backbone_config.blocks))
_, endpoints = efficientnet_builder.build_model_base(
features,
backbone_name,
training=is_training_bn,
override_params=override_params)
u2 = endpoints['reduction_2']
u3 = endpoints['reduction_3']
u4 = endpoints['reduction_4']
u5 = endpoints['reduction_5']
else:
raise ValueError(
'backbone model {} is not supported.'.format(backbone_name))
return {2: u2, 3: u3, 4: u4, 5: u5}
def test_efficientnet_b0_base(self):
# Creates a base model using the model configuration.
images = tf.zeros((1, 224, 224, 3), dtype=tf.float32)
_, endpoints = efficientnet_builder.build_model_base(
images, model_name='efficientnet-b0', training=False)
# reduction_1 to reduction_5 should be in endpoints
self.assertEqual(len(endpoints), 5)
def test_efficientnet_b0_base(self):
# Creates a base model using the model configuration.
images = tf.zeros((1, 224, 224, 3), dtype=tf.float32)
_, endpoints = efficientnet_builder.build_model_base(
images, model_name='efficientnet-b0', training=True)
# reduction_1 to reduction_5 should be in endpoints
self.assertIn('reduction_1', endpoints)
self.assertIn('reduction_5', endpoints)
# reduction_5 should be the last one: no reduction_6.
self.assertNotIn('reduction_6', endpoints)
def build_backbone(features, config):
"""Builds backbone model.
Args:
features: input tensor.
config: config for backbone, such as is_training_bn and backbone name.
Returns:
A dict from levels to the feature maps from the output of the backbone model
with strides of 8, 16 and 32.
Raises:
ValueError: if backbone_name is not supported.
"""
backbone_name = config.backbone_name
is_training_bn = config.is_training_bn
if 'efficientnet' in backbone_name:
override_params = {
'relu_fn': utils.backbone_relu_fn,
'batch_norm': utils.batch_norm_class(is_training_bn),
}
if 'b0' in backbone_name:
override_params['survival_prob'] = 0.0
if config.backbone_config is not None:
override_params['blocks_args'] = (
efficientnet_builder.BlockDecoder().encode(
config.backbone_config.blocks))
_, endpoints = efficientnet_builder.build_model_base(
features,
backbone_name,
training=is_training_bn,
override_params=override_params)
u2 = endpoints['reduction_2']
u3 = endpoints['reduction_3']
u4 = endpoints['reduction_4']
u5 = endpoints['reduction_5']
else:
raise ValueError(
'backbone model {} is not supported.'.format(backbone_name))
return {2: u2, 3: u3, 4: u4, 5: u5}
