def testModelHasExpectedNumberOfParameters(self):
batch_size = 5
height, width = 224, 224
inputs = tf.random_uniform((batch_size, height, width, 3))
with slim.arg_scope(inception.inception_v1_arg_scope()):
inception.inception_v1_base(inputs)
total_params, _ = slim.model_analyzer.analyze_vars(
slim.get_model_variables())
self.assertAlmostEqual(5607184, total_params)
def testModelHasExpectedNumberOfParameters(self):
batch_size = 5
height, width = 224, 224
inputs = tf.random_uniform((batch_size, height, width, 3))
with slim.arg_scope(inception.inception_v1_arg_scope()):
inception.inception_v1_base(inputs)
total_params, _ = slim.model_analyzer.analyze_vars(
slim.get_model_variables())
self.assertAlmostEqual(5607184, total_params)
def testBuildAndCheckAllEndPointsUptoMixed5c(self):
batch_size = 5
height, width = 224, 224
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v1_base(inputs,
final_endpoint='Mixed_5c')
endpoints_shapes = {'Conv2d_1a_7x7': [5, 112, 112, 64],
'MaxPool_2a_3x3': [5, 56, 56, 64],
'Conv2d_2b_1x1': [5, 56, 56, 64],
'Conv2d_2c_3x3': [5, 56, 56, 192],
'MaxPool_3a_3x3': [5, 28, 28, 192],
'Mixed_3b': [5, 28, 28, 256],
'Mixed_3c': [5, 28, 28, 480],
'MaxPool_4a_3x3': [5, 14, 14, 480],
'Mixed_4b': [5, 14, 14, 512],
'Mixed_4c': [5, 14, 14, 512],
'Mixed_4d': [5, 14, 14, 512],
'Mixed_4e': [5, 14, 14, 528],
'Mixed_4f': [5, 14, 14, 832],
'MaxPool_5a_2x2': [5, 7, 7, 832],
'Mixed_5b': [5, 7, 7, 832],
'Mixed_5c': [5, 7, 7, 1024]}
self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
for endpoint_name in endpoints_shapes:
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 testBuildAndCheckAllEndPointsUptoMixed5c(self):
batch_size = 5
height, width = 224, 224
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v1_base(inputs,
final_endpoint='Mixed_5c')
endpoints_shapes = {
'Conv2d_1a_7x7': [5, 112, 112, 64],
'MaxPool_2a_3x3': [5, 56, 56, 64],
'Conv2d_2b_1x1': [5, 56, 56, 64],
'Conv2d_2c_3x3': [5, 56, 56, 192],
'MaxPool_3a_3x3': [5, 28, 28, 192],
'Mixed_3b': [5, 28, 28, 256],
'Mixed_3c': [5, 28, 28, 480],
'MaxPool_4a_3x3': [5, 14, 14, 480],
'Mixed_4b': [5, 14, 14, 512],
'Mixed_4c': [5, 14, 14, 512],
'Mixed_4d': [5, 14, 14, 512],
'Mixed_4e': [5, 14, 14, 528],
'Mixed_4f': [5, 14, 14, 832],
'MaxPool_5a_2x2': [5, 7, 7, 832],
'Mixed_5b': [5, 7, 7, 832],
'Mixed_5c': [5, 7, 7, 1024]
}
self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
for endpoint_name in endpoints_shapes:
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 build_model(model_name, inputs, num_classes, is_training, dropout_keep_prob):
use_fcn = False
if model_name.find('fcn') >= 0:
use_fcn = True
model_base_name = model_name[0:-4]
else:
model_base_name = model_name
if model_base_name == 'vgg16':
net = vgg16_base(inputs)
elif model_base_name == 'inception_v1':
with slim.arg_scope(inception.inception_v1_arg_scope()):
net, _ = inception.inception_v1_base(inputs)
elif model_base_name == 'inception_v2':
with slim.arg_scope(inception.inception_v2_arg_scope()):
net, _ = inception.inception_v2_base(inputs)
elif model_base_name == 'inception_v3':
with slim.arg_scope(inception.inception_v3_arg_scope()):
net, _ = inception.inception_v3_base(inputs)
else:
raise Exception('model {} is not existed'.format(model_name))
with tf.variable_scope('not_pretrained'):
if use_fcn:
net = fully_convolutional_networks(net, num_classes, is_training, dropout_keep_prob)
else:
net = fully_connected_networks(net, num_classes, is_training, dropout_keep_prob)
return net
def testHalfSizeImages(self):
batch_size = 5
height, width = 112, 112
inputs = tf.random_uniform((batch_size, height, width, 3))
mixed_5c, _ = inception.inception_v1_base(inputs)
self.assertTrue(mixed_5c.op.name.startswith('InceptionV1/Mixed_5c'))
self.assertListEqual(mixed_5c.get_shape().as_list(),
[batch_size, 4, 4, 1024])
def testHalfSizeImages(self):
batch_size = 5
height, width = 112, 112
inputs = tf.random_uniform((batch_size, height, width, 3))
mixed_5c, _ = inception.inception_v1_base(inputs)
self.assertTrue(mixed_5c.op.name.startswith('InceptionV1/Mixed_5c'))
self.assertListEqual(mixed_5c.get_shape().as_list(),
[batch_size, 4, 4, 1024])
def build(self,
inputs,
input_pixel_size,
is_training,
scope='img_inception'):
"""Inception for BEV feature extraction
Args:
inputs: a tensor of size [batch_size, height, width, channels].
input_pixel_size: size of the input (H x W)
is_training: True for training, False fo validation/testing.
scope: Optional scope for the variables.
Returns:
The net, a rank-4 tensor of size [batch, height_out, width_out,
channels_out] and end_points dict.
"""
inception_config = self.config
with tf.variable_scope(scope, 'img_inception', [inputs]) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
if inception_config.inception_v == 'inception_v1':
with slim.arg_scope(inception.inception_v1_arg_scope()):
net, end_points = inception.inception_v1_base(
inputs, scope=scope)
elif inception_config.inception_v == 'inception_v2':
with slim.arg_scope(inception.inception_v2_arg_scope()):
net, end_points = inception.inception_v2_base(
inputs, scope=scope)
elif inception_config.inception_v == 'inception_v3':
with slim.arg_scope(inception.inception_v3_arg_scope()):
net, end_points = inception.inception_v3_base(
inputs, scope=scope)
else:
raise ValueError('Invalid Inception version {},'.format(
inception_config.inception_v))
with tf.variable_scope('upsampling'):
# This feature extractor downsamples the input by a factor
# of 32
downsampling_factor = 32
downsampled_shape = input_pixel_size / downsampling_factor
upsampled_shape = downsampled_shape * \
inception_config.upsampling_multiplier
feature_maps_out = tf.image.resize_bilinear(
net, upsampled_shape)
return feature_maps_out, end_points
def testBuildBaseNetwork(self):
batch_size = 5
height, width = 224, 224
inputs = tf.random_uniform((batch_size, height, width, 3))
mixed_6c, end_points = inception.inception_v1_base(inputs)
self.assertTrue(mixed_6c.op.name.startswith('InceptionV1/Mixed_5c'))
self.assertListEqual(mixed_6c.get_shape().as_list(),
[batch_size, 7, 7, 1024])
expected_endpoints = ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b',
'Mixed_3c', 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c',
'Mixed_4d', 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2',
'Mixed_5b', 'Mixed_5c']
self.assertItemsEqual(end_points.keys(), expected_endpoints)
def testBuildBaseNetwork(self):
batch_size = 5
height, width = 224, 224
inputs = tf.random_uniform((batch_size, height, width, 3))
mixed_6c, end_points = inception.inception_v1_base(inputs)
self.assertTrue(mixed_6c.op.name.startswith('InceptionV1/Mixed_5c'))
self.assertListEqual(mixed_6c.get_shape().as_list(),
[batch_size, 7, 7, 1024])
expected_endpoints = ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b',
'Mixed_3c', 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c',
'Mixed_4d', 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2',
'Mixed_5b', 'Mixed_5c']
self.assertItemsEqual(end_points.keys(), expected_endpoints)
def testBuildOnlyUptoFinalEndpoint(self):
batch_size = 5
height, width = 224, 224
endpoints = ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c',
'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d',
'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b',
'Mixed_5c']
for index, endpoint in enumerate(endpoints):
with tf.Graph().as_default():
inputs = tf.random_uniform((batch_size, height, width, 3))
out_tensor, end_points = inception.inception_v1_base(
inputs, final_endpoint=endpoint)
self.assertTrue(out_tensor.op.name.startswith(
'InceptionV1/' + endpoint))
self.assertItemsEqual(endpoints[:index+1], end_points)
def testBuildOnlyUptoFinalEndpoint(self):
batch_size = 5
height, width = 224, 224
endpoints = ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c',
'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d',
'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b',
'Mixed_5c']
for index, endpoint in enumerate(endpoints):
with tf.Graph().as_default():
inputs = tf.random_uniform((batch_size, height, width, 3))
out_tensor, end_points = inception.inception_v1_base(
inputs, final_endpoint=endpoint)
self.assertTrue(out_tensor.op.name.startswith(
'InceptionV1/' + endpoint))
self.assertItemsEqual(endpoints[:index+1], end_points)
def compute_embedding_inception_v1(inputs,
embedding_dim=64,
is_training=True,
dropout_keep_prob=0.8,
scope='InceptionV1',
l2_normalize=True):
"""Compute embedding with inception v1."""
with tf.variable_scope(scope, 'InceptionV1',
[inputs, embedding_dim]) as scope:
with slim.arg_scope([layers.batch_norm, layers.dropout],
is_training=is_training):
with slim.arg_scope(inception.inception_v1_arg_scope()):
net, end_points = inception.inception_v1_base(inputs,
scope=scope)
net = layers.avg_pool2d(net, [7, 7],
stride=1,
scope='AvgPool_0a_7x7')
net = layers.dropout(net,
dropout_keep_prob,
scope='Dropout_0b')
base_variables = slim.get_variables_to_restore(
exclude=['global_step'])
# Embedding bottleneck.
net = layers.conv2d(net,
embedding_dim, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='Bottleneck')
embedding = tf.squeeze(net, [1, 2], name='SpatialSqueeze')
if l2_normalize:
embedding = tf.nn.l2_normalize(embedding, dim=1)
end_points['embeddings'] = embedding
bottleneck_variables = tf.contrib.framework.get_variables(
scope='InceptionV1/Bottleneck')
return embedding, end_points, base_variables, bottleneck_variables
def __call__(self, training, img, dropout):
"""Applies convolutions to the image
Args:
training: (tf.placeholder) tf.bool
img: batch of img, shape = (?, height, width, channels), of type
tf.uint8
Returns:
the encoded images, shape = (?, h', w', c')
"""
img = tf.cast(img, tf.float32) / 255.
# out, _ = inception.inception_v2_base(img, final_endpoint='MaxPool_3a_3x3',
# scope="convolutional_encoder")
out, _ = inception.inception_v1_base(img, final_endpoint='MaxPool_3a_3x3',
scope="convolutional_encoder")
if self._config.positional_embeddings:
# from tensor2tensor lib - positional embeddings
out = add_timing_signal_nd(out)
return out
