def testRaiseValueErrorWithInvalidDepthMultiplier(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
with self.assertRaises(ValueError):
_ = inception.inception_v2(inputs, num_classes, depth_multiplier=-0.1)
with self.assertRaises(ValueError):
_ = inception.inception_v2(inputs, num_classes, depth_multiplier=0.0)
def testRaiseValueErrorWithInvalidDepthMultiplier(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
with self.assertRaises(ValueError):
_ = inception.inception_v2(inputs, num_classes, depth_multiplier=-0.1)
with self.assertRaises(ValueError):
_ = inception.inception_v2(inputs, num_classes, depth_multiplier=0.0)
def testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 150, 150
num_classes = 1000
train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
inception.inception_v2(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_v2(eval_inputs, num_classes, reuse=True)
predictions = tf.argmax(logits, 1)
with self.test_session() as sess:
sess.run(tf.initialize_all_variables())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size,))
def get_model(images,
num_classes=10,
is_training=True,
weight_decay=4e-5,
dropout_keep_prob=0.75):
"""Neural Image Assessment from https://arxiv.org/abs/1709.05424
Talebi, Hossein, and Peyman Milanfar. "NIMA: Neural Image Assessment."
arXiv preprint arXiv:1709.05424 (2017).
Args:
images: a tensor of shape [batch_size, height, width, channels].
num_classes: number of predicted classes. Defaults to 10.
is_training: whether is training or not.
weight_decay: the weight decay to use for regularizing the model.
dropout_keep_prob: the percentage of activation values that are retained.
Defaults to 0.75
Returns:
predictions: a tensor of size [batch_size, num_classes].
end_points: a dictionary from components of the network.
"""
arg_scope = inception.inception_v2_arg_scope(weight_decay=weight_decay)
with slim.arg_scope(arg_scope):
logits, end_points = inception.inception_v2(
images,
num_classes,
is_training=is_training,
dropout_keep_prob=dropout_keep_prob)
predictions = tf.nn.softmax(logits)
return predictions, end_points
def __init__(self, model_path=INCEPTION_V2_PATH, image_size=299):
cache_dir = os.sep.join(model_path.split(os.sep)[:-1])
get_file(fname=model_path.split(os.sep)[-1],
cache_dir=cache_dir,
cache_subdir='',
origin=INCEPTION_V2_URL,
untar=True)
self._get_session()
self.checkpoint_file = model_path
self.image_size = image_size
self._get_inception_preprocessing(inception_size=224)
self.arg_scope = inception.inception_v2_arg_scope()
with slim.arg_scope(self.arg_scope):
self.logits, self.end_points = inception.inception_v2(
self.scaled_input_tensor,
is_training=False,
num_classes=1001,
reuse=False)
end_point = list(self.end_points.values())[-3]
kernel_size = end_point.get_shape().as_list()[-2]
with variable_scope.variable_scope('InceptionV2/Logits',
reuse=True):
embedding = layers_lib.avg_pool2d(end_point,
kernel_size,
padding='VALID',
scope='AvgPool_1a_%dx%d' %
(kernel_size, kernel_size))
self.end_points['PreLogits'] = embedding
self._restore()
def testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 150, 150
num_classes = 1000
train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
inception.inception_v2(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_v2(eval_inputs, num_classes, reuse=True)
predictions = tf.argmax(logits, 1)
with self.test_session() as sess:
sess.run(tf.initialize_all_variables())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size,))
def testLogitsNotSqueezed(self):
num_classes = 25
images = tf.random_uniform([1, 224, 224, 3])
logits, _ = inception.inception_v2(images, num_classes=num_classes, spatial_squeeze=False)
with self.test_session() as sess:
tf.global_variables_initializer().run()
logits_out = sess.run(logits)
self.assertListEqual(list(logits_out.shape), [1, 1, 1, num_classes])
def testBuildEndPointsWithDepthMultiplierGreaterThanOne(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v2(inputs, num_classes)
endpoint_keys = [key for key in end_points.keys() if key.startswith("Mixed") or key.startswith("Conv")]
_, end_points_with_multiplier = inception.inception_v2(
inputs, num_classes, scope="depth_multiplied_net", depth_multiplier=2.0
)
for key in endpoint_keys:
original_depth = end_points[key].get_shape().as_list()[3]
new_depth = end_points_with_multiplier[key].get_shape().as_list()[3]
self.assertEqual(2.0 * original_depth, new_depth)
def testBuildEndPointsWithDepthMultiplierGreaterThanOne(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v2(inputs, num_classes)
endpoint_keys = [key for key in end_points.keys()
if key.startswith('Mixed') or key.startswith('Conv')]
_, end_points_with_multiplier = inception.inception_v2(
inputs, num_classes, scope='depth_multiplied_net',
depth_multiplier=2.0)
for key in endpoint_keys:
original_depth = end_points[key].get_shape().as_list()[3]
new_depth = end_points_with_multiplier[key].get_shape().as_list()[3]
self.assertEqual(2.0 * original_depth, new_depth)
def testLogitsNotSqueezed(self):
num_classes = 25
images = tf.random_uniform([1, 224, 224, 3])
logits, _ = inception.inception_v2(images,
num_classes=num_classes,
spatial_squeeze=False)
with self.test_session() as sess:
tf.initialize_all_variables().run()
logits_out = sess.run(logits)
self.assertListEqual(list(logits_out.shape), [1, 1, 1, num_classes])
def testHalfSizeImages(self):
batch_size = 5
height, width = 112, 112
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith("InceptionV2/Logits"))
self.assertListEqual(logits.get_shape().as_list(), [batch_size, num_classes])
pre_pool = end_points["Mixed_5c"]
self.assertListEqual(pre_pool.get_shape().as_list(), [batch_size, 4, 4, 1024])
def testBuildClassificationNetwork(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith("InceptionV2/Logits"))
self.assertListEqual(logits.get_shape().as_list(), [batch_size, num_classes])
self.assertTrue("Predictions" in end_points)
self.assertListEqual(end_points["Predictions"].get_shape().as_list(), [batch_size, num_classes])
def run(name, image_size, num_classes):
with tf.Graph().as_default():
image = tf.placeholder("float", [1, image_size, image_size, 3], name="input")
with slim.arg_scope(inception.inception_v2_arg_scope()):
logits, _ = inception.inception_v2(image, num_classes, is_training=False, spatial_squeeze=False)
probabilities = tf.nn.softmax(logits, name='output')
init_fn = slim.assign_from_checkpoint_fn('inception_v2.ckpt', slim.get_model_variables('InceptionV2'))
with tf.Session() as sess:
init_fn(sess)
saver = tf.train.Saver(tf.global_variables())
saver.save(sess, "output/"+name)
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v2(eval_inputs, num_classes, is_training=False)
predictions = tf.argmax(logits, 1)
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size,))
def testBuildClassificationNetwork(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue('Predictions' in end_points)
self.assertListEqual(end_points['Predictions'].get_shape().as_list(),
[batch_size, num_classes])
def testHalfSizeImages(self):
batch_size = 5
height, width = 112, 112
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_5c']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 4, 4, 1024])
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v2(eval_inputs, num_classes,
is_training=False)
predictions = tf.argmax(logits, 1)
with self.test_session() as sess:
sess.run(tf.initialize_all_variables())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size,))
def testUnknownBatchSize(self):
batch_size = 1
height, width = 224, 224
num_classes = 1000
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith("InceptionV2/Logits"))
self.assertListEqual(logits.get_shape().as_list(), [None, num_classes])
images = tf.random_uniform((batch_size, height, width, 3))
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(logits, {inputs: images.eval()})
self.assertEquals(output.shape, (batch_size, num_classes))
def testUnknowBatchSize(self):
batch_size = 1
height, width = 224, 224
num_classes = 1000
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(), [None, num_classes])
images = tf.random_uniform((batch_size, height, width, 3))
with self.test_session() as sess:
sess.run(tf.initialize_all_variables())
output = sess.run(logits, {inputs: images.eval()})
self.assertEquals(output.shape, (batch_size, num_classes))
def testUnknownImageShape(self):
tf.reset_default_graph()
batch_size = 2
height, width = 224, 224
num_classes = 1000
input_np = np.random.uniform(0, 1, (batch_size, height, width, 3))
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, shape=(batch_size, None, None, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith("InceptionV2/Logits"))
self.assertListEqual(logits.get_shape().as_list(), [batch_size, num_classes])
pre_pool = end_points["Mixed_5c"]
feed_dict = {inputs: input_np}
tf.global_variables_initializer().run()
pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict)
self.assertListEqual(list(pre_pool_out.shape), [batch_size, 7, 7, 1024])
def run(name, image_size, num_classes):
with tf.Graph().as_default():
image = tf.placeholder("float", [1, image_size, image_size, 3],
name="input")
with slim.arg_scope(inception.inception_v2_arg_scope()):
logits, _ = inception.inception_v2(image,
num_classes,
is_training=False,
spatial_squeeze=False)
probabilities = tf.nn.softmax(logits, name='output')
init_fn = slim.assign_from_checkpoint_fn(
'inception_v2.ckpt', slim.get_model_variables('InceptionV2'))
with tf.Session() as sess:
init_fn(sess)
saver = tf.train.Saver(tf.global_variables())
saver.save(sess, "output/" + name)
def testUnknownImageShape(self):
tf.reset_default_graph()
batch_size = 2
height, width = 224, 224
num_classes = 1000
input_np = np.random.uniform(0, 1, (batch_size, height, width, 3))
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, shape=(batch_size, None, None, 3))
logits, end_points = inception.inception_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_5c']
feed_dict = {inputs: input_np}
tf.initialize_all_variables().run()
pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict)
self.assertListEqual(list(pre_pool_out.shape), [batch_size, 7, 7, 1024])
def inception_v2(inputs,reuse_flag=False): with slim.arg_scope(inception.inception_v2_arg_scope()): net, end_points = inception.inception_v2(inputs) print end_points return net,end_points['Mixed_5c']
