def _image_to_head(self, is_training, reuse=None):
with slim.arg_scope(nasnet_large_arg_scope()):
pool, _ = build_nasnet_large(self._input,
0,
is_training=is_training)
return pool
def testBuildPreLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = None
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
net, end_points = nasnet.build_nasnet_large(inputs, num_classes)
self.assertFalse('AuxLogits' in end_points)
self.assertFalse('Predictions' in end_points)
self.assertTrue(net.op.name.startswith('final_layer/Mean'))
self.assertListEqual(net.get_shape().as_list(), [batch_size, 4032])
def infer(self, inputs):
images = inputs['images']
with tf.variable_scope(tf.get_variable_scope()):
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
_, _, nas_dict = build_nasnet_large(
images, is_training=self.is_training)
with tf.variable_scope('refinenet'):
pred, _ = build_refine_net(nas_dict,
num_classes=self.num_cls,
keep_prob=self.keep_prob)
return {'logits': pred}
def __call__(self, x_input, batch_size=None, is_training=False):
""" Construct the model and return probablities for given input ."""
if self.built:
return self.logits
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
with tf.variable_scope(self.ckpt):
logits, end_points = nasnet.build_nasnet_large(
x_input, self.num_classes, is_training=False)
self.built = True
self.scores = end_points['Predictions']
self.logits = logits
self.preds = tf.argmax(logits, axis=1)
return self.logits
def testOverrideHParamsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
config = nasnet.large_imagenet_config()
config.set_hparam('data_format', 'NCHW')
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
_, end_points = nasnet.build_nasnet_large(inputs,
num_classes,
config=config)
self.assertListEqual(end_points['Stem'].shape.as_list(),
[batch_size, 336, 42, 42])
def testNoAuxHeadLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
for use_aux_head in (True, False):
tf.reset_default_graph()
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
config = nasnet.large_imagenet_config()
config.set_hparam('use_aux_head', int(use_aux_head))
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
_, end_points = nasnet.build_nasnet_large(inputs,
num_classes,
config=config)
self.assertEqual('AuxLogits' in end_points, use_aux_head)
def testBuildLogitsLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
logits, end_points = nasnet.build_nasnet_large(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
def testAllEndPointsShapesLargeModel(self):
batch_size = 5
height, width = 331, 331
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
tf.train.create_global_step()
with slim.arg_scope(nasnet.nasnet_large_arg_scope()):
_, end_points = nasnet.build_nasnet_large(inputs, num_classes)
endpoints_shapes = {
'Stem': [batch_size, 42, 42, 336],
'Cell_0': [batch_size, 42, 42, 1008],
'Cell_1': [batch_size, 42, 42, 1008],
'Cell_2': [batch_size, 42, 42, 1008],
'Cell_3': [batch_size, 42, 42, 1008],
'Cell_4': [batch_size, 42, 42, 1008],
'Cell_5': [batch_size, 42, 42, 1008],
'Cell_6': [batch_size, 21, 21, 2016],
'Cell_7': [batch_size, 21, 21, 2016],
'Cell_8': [batch_size, 21, 21, 2016],
'Cell_9': [batch_size, 21, 21, 2016],
'Cell_10': [batch_size, 21, 21, 2016],
'Cell_11': [batch_size, 21, 21, 2016],
'Cell_12': [batch_size, 11, 11, 4032],
'Cell_13': [batch_size, 11, 11, 4032],
'Cell_14': [batch_size, 11, 11, 4032],
'Cell_15': [batch_size, 11, 11, 4032],
'Cell_16': [batch_size, 11, 11, 4032],
'Cell_17': [batch_size, 11, 11, 4032],
'Reduction_Cell_0': [batch_size, 21, 21, 1344],
'Reduction_Cell_1': [batch_size, 11, 11, 2688],
'global_pool': [batch_size, 4032],
# Logits and predictions
'AuxLogits': [batch_size, num_classes],
'Logits': [batch_size, num_classes],
'Predictions': [batch_size, num_classes]
}
self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
for endpoint_name in endpoints_shapes:
tf.logging.info('Endpoint name: {}'.format(endpoint_name))
expected_shape = endpoints_shapes[endpoint_name]
self.assertTrue(endpoint_name in end_points)
self.assertListEqual(
end_points[endpoint_name].get_shape().as_list(),
expected_shape)
def pnasnet_large_arg_scope(weight_decay=4e-5,
batch_norm_decay=0.9997,
batch_norm_epsilon=0.001):
"""Default arg scope for the PNASNet Large ImageNet model."""
return nasnet.nasnet_large_arg_scope(weight_decay, batch_norm_decay,
batch_norm_epsilon)