def build_model_base(images, model_name, training, override_params=None):
"""A helper functiion to create a base model and return global_pool.
Args:
images: input images tensor.
model_name: string, the predefined model name.
training: boolean, whether the model is constructed for training.
override_params: A dictionary of params for overriding. Fields must exist in
efficientnet_model.GlobalParams.
Returns:
features: global pool features.
endpoints: the endpoints for each layer.
Raises:
When model_name specified an undefined model, raises NotImplementedError.
When override_params has invalid fields, raises ValueError.
"""
assert isinstance(images, tf.Tensor)
# For backward compatibility.
if override_params and override_params.get('drop_connect_rate', None):
override_params['survival_prob'] = 1 - override_params['drop_connect_rate']
blocks_args, global_params = get_model_params(model_name, override_params)
with tf.variable_scope(model_name, reuse = tf.AUTO_REUSE):
model = efficientnet_model.Model(blocks_args, global_params)
features = model(images, training=training, features_only=True)
features = tf.identity(features, 'features')
return features, model.endpoints
def build_model_base(images, model_name, training, override_params=None):
"""A helper functiion to create a base model and return global_pool.
Args:
images: input images tensor.
model_name: string, the model name of a pre-defined MnasNet.
training: boolean, whether the model is constructed for training.
override_params: A dictionary of params for overriding. Fields must exist in
mnasnet_model.GlobalParams.
Returns:
features: global pool features.
endpoints: the endpoints for each layer.
Raises:
When model_name specified an undefined model, raises NotImplementedError.
When override_params has invalid fields, raises ValueError.
"""
assert isinstance(images, tf.Tensor)
blocks_args, global_params = get_model_params(model_name, override_params)
with tf.variable_scope(model_name):
model = efficientnet_model.Model(blocks_args, global_params)
features = model(images, training=training, features_only=True)
features = tf.identity(features, 'global_pool')
return features, model.endpoints
def build_model(images,
model_name,
training,
override_params=None,
model_dir=None,
fine_tuning=False):
"""A helper functiion to creates a model and returns predicted logits.
Args:
images: input images tensor.
model_name: string, the predefined model name.
training: boolean, whether the model is constructed for training.
override_params: A dictionary of params for overriding. Fields must exist in
efficientnet_model.GlobalParams.
model_dir: string, optional model dir for saving configs.
fine_tuning: boolean, whether the model is used for finetuning.
Returns:
logits: the logits tensor of classes.
endpoints: the endpoints for each layer.
Raises:
When model_name specified an undefined model, raises NotImplementedError.
When override_params has invalid fields, raises ValueError.
"""
assert isinstance(images, tf.Tensor)
if not training or fine_tuning:
if not override_params:
override_params = {}
override_params['batch_norm'] = utils.BatchNormalization
blocks_args, global_params = get_model_params(model_name, override_params)
if not training or fine_tuning:
global_params = global_params._replace(
batch_norm=utils.BatchNormalization)
if model_dir:
param_file = os.path.join(model_dir, 'model_params.txt')
if not tf.gfile.Exists(param_file):
if not tf.gfile.Exists(model_dir):
tf.gfile.MakeDirs(model_dir)
with tf.gfile.GFile(param_file, 'w') as f:
tf.logging.info('writing to %s' % param_file)
f.write('model_name= %s\n\n' % model_name)
f.write('global_params= %s\n\n' % str(global_params))
f.write('blocks_args= %s\n\n' % str(blocks_args))
with tf.variable_scope(model_name):
model = efficientnet_model.Model(blocks_args, global_params)
logits = model(images, training=training)
logits = tf.identity(logits, 'logits')
return logits, model.endpoints
def build_model(images,
model_name,
training,
override_params=None,
model_dir=None,
fine_tuning=False,
features_only=False,
pooled_features_only=False):
"""A helper functiion to creates a model and returns predicted logits.
Args:
images: input images tensor.
model_name: string, the predefined model name.
training: boolean, whether the model is constructed for training.
override_params: A dictionary of params for overriding. Fields must exist in
efficientnet_model.GlobalParams.
model_dir: string, optional model dir for saving configs.
fine_tuning: boolean, whether the model is used for finetuning.
features_only: build the base feature network only (excluding final
1x1 conv layer, global pooling, dropout and fc head).
pooled_features_only: build the base network for features extraction (after
1x1 conv layer and global pooling, but before dropout and fc head).
Returns:
logits: the logits tensor of classes.
endpoints: the endpoints for each layer.
Raises:
When model_name specified an undefined model, raises NotImplementedError.
When override_params has invalid fields, raises ValueError.
"""
assert isinstance(images, tf.Tensor)
assert not (features_only and pooled_features_only)
# For backward compatibility.
if override_params and override_params.get('drop_connect_rate', None):
override_params['survival_prob'] = 1 - override_params['drop_connect_rate']
if not training or fine_tuning:
if not override_params:
override_params = {}
override_params['batch_norm'] = utils.BatchNormalization
if fine_tuning:
override_params['relu_fn'] = functools.partial(swish, use_native=False)
blocks_args, global_params = get_model_params(model_name, override_params)
if model_dir:
param_file = os.path.join(model_dir, 'model_params.txt')
if not tf.gfile.Exists(param_file):
if not tf.gfile.Exists(model_dir):
tf.gfile.MakeDirs(model_dir)
with tf.gfile.GFile(param_file, 'w') as f:
logging.info('writing to %s', param_file)
f.write('model_name= %s\n\n' % model_name)
f.write('global_params= %s\n\n' % str(global_params))
f.write('blocks_args= %s\n\n' % str(blocks_args))
with tf.variable_scope(model_name):
model = efficientnet_model.Model(blocks_args, global_params)
outputs = model(
images,
training=training,
features_only=features_only,
pooled_features_only=pooled_features_only)
if features_only:
outputs = tf.identity(outputs, 'features')
elif pooled_features_only:
outputs = tf.identity(outputs, 'pooled_features')
else:
outputs = tf.identity(outputs, 'logits')
return outputs, model.endpoints