def testVariablesSetDevice(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
# Force all Variables to reside on the device.
with tf.variable_scope('on_cpu'), tf.device('/cpu:0'):
inception.inception_v4(inputs, num_classes)
with tf.variable_scope('on_gpu'), tf.device('/gpu:0'):
inception.inception_v4(inputs, num_classes)
for v in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope='on_cpu'):
self.assertDeviceEqual(v.device, '/cpu:0')
for v in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope='on_gpu'):
self.assertDeviceEqual(v.device, '/gpu:0')
def model(x, H, reuse, is_training=True):
slim_attention_lname = 'Mixed_3b'
if H['slim_basename'] == 'resnet_v1_101':
with slim.arg_scope(resnet.resnet_arg_scope()):
_, T = resnet.resnet_v1_101(x,
is_training=is_training,
num_classes=1000,
reuse=reuse)
elif H['slim_basename'] == 'resnet_v2_152':
with slim.arg_scope(resnet.resnet_arg_scope()):
_, T = resnet.resnet_v2_152(x,
is_training=is_training,
num_classes=1001,
reuse=reuse)
elif H['slim_basename'] == 'InceptionV1':
with slim.arg_scope(inception.inception_v1_arg_scope()):
_, T = inception.inception_v1(x,
is_training=is_training,
num_classes=1001,
spatial_squeeze=False,
reuse=reuse)
elif H['slim_basename'] == 'InceptionV2':
with slim.arg_scope(inception.inception_v2_arg_scope()):
_, T = inception.inception_v2(x,
is_training=is_training,
num_classes=1001,
spatial_squeeze=False,
reuse=reuse)
elif H['slim_basename'] == 'InceptionV3':
with slim.arg_scope(inception.inception_v3_arg_scope()):
_, T = inception.inception_v3(x,
is_training=is_training,
num_classes=1001,
spatial_squeeze=False,
reuse=reuse)
slim_attention_lname = 'Mixed_5b'
elif H['slim_basename'] == 'InceptionV4':
with slim.arg_scope(inception.inception_v4_arg_scope()):
_, T = inception.inception_v4(x,
is_training=is_training,
num_classes=1001,
reuse=reuse)
slim_attention_lname = 'Mixed_4a'
elif H['slim_basename'] == 'MobilenetV1':
with slim.arg_scope(mobilenet_v1.mobilenet_v1_arg_scope()):
_, T = mobilenet_v1.mobilenet_v1(x,
is_training=is_training,
reuse=reuse)
# print '\n'.join(map(str, [(k, v.op.outputs[0].get_shape()) for k, v in T.iteritems()]))
coarse_feat = T[H['slim_top_lname']][:, :, :, :H['later_feat_channels']]
assert coarse_feat.op.outputs[0].get_shape()[3] == H['later_feat_channels']
# fine feat can be used to reinspect input
attention_lname = H.get('slim_attention_lname', slim_attention_lname)
early_feat = T[attention_lname]
return coarse_feat, early_feat
def testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 150, 150
num_classes = 1000
with self.test_session() as sess:
train_inputs = tf.random_uniform(
(train_batch_size, height, width, 3))
inception.inception_v4(train_inputs, num_classes)
eval_inputs = tf.random_uniform(
(eval_batch_size, height, width, 3))
logits, _ = inception.inception_v4(eval_inputs,
num_classes,
is_training=False,
reuse=True)
predictions = tf.argmax(logits, 1)
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size, ))
def testBuildWithoutAuxLogits(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, endpoints = inception.inception_v4(inputs,
num_classes,
create_aux_logits=False)
self.assertFalse('AuxLogits' in endpoints)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def testHalfSizeImages(self):
batch_size = 5
height, width = 150, 150
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v4(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_7d']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 3, 3, 1536])
def testEvaluation(self):
batch_size = 2
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_v4(eval_inputs,
num_classes,
is_training=False)
predictions = tf.argmax(logits, 1)
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size, ))
def testUnknownBatchSize(self):
batch_size = 1
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_v4(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[None, num_classes])
images = tf.random_uniform((batch_size, height, width, 3))
sess.run(tf.global_variables_initializer())
output = sess.run(logits, {inputs: images.eval()})
self.assertEquals(output.shape, (batch_size, num_classes))
def testAllEndPointsShapes(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_v4(inputs, num_classes)
endpoints_shapes = {
'Conv2d_1a_3x3': [batch_size, 149, 149, 32],
'Conv2d_2a_3x3': [batch_size, 147, 147, 32],
'Conv2d_2b_3x3': [batch_size, 147, 147, 64],
'Mixed_3a': [batch_size, 73, 73, 160],
'Mixed_4a': [batch_size, 71, 71, 192],
'Mixed_5a': [batch_size, 35, 35, 384],
# 4 x Inception-A blocks
'Mixed_5b': [batch_size, 35, 35, 384],
'Mixed_5c': [batch_size, 35, 35, 384],
'Mixed_5d': [batch_size, 35, 35, 384],
'Mixed_5e': [batch_size, 35, 35, 384],
# Reduction-A block
'Mixed_6a': [batch_size, 17, 17, 1024],
# 7 x Inception-B blocks
'Mixed_6b': [batch_size, 17, 17, 1024],
'Mixed_6c': [batch_size, 17, 17, 1024],
'Mixed_6d': [batch_size, 17, 17, 1024],
'Mixed_6e': [batch_size, 17, 17, 1024],
'Mixed_6f': [batch_size, 17, 17, 1024],
'Mixed_6g': [batch_size, 17, 17, 1024],
'Mixed_6h': [batch_size, 17, 17, 1024],
# Reduction-A block
'Mixed_7a': [batch_size, 8, 8, 1536],
# 3 x Inception-C blocks
'Mixed_7b': [batch_size, 8, 8, 1536],
'Mixed_7c': [batch_size, 8, 8, 1536],
'Mixed_7d': [batch_size, 8, 8, 1536],
# Logits and predictions
'AuxLogits': [batch_size, num_classes],
'PreLogitsFlatten': [batch_size, 1536],
'Logits': [batch_size, num_classes],
'Predictions': [batch_size, num_classes]
}
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 testBuildLogits(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_v4(inputs, num_classes)
auxlogits = end_points['AuxLogits']
predictions = end_points['Predictions']
self.assertTrue(auxlogits.op.name.startswith('InceptionV4/AuxLogits'))
self.assertListEqual(auxlogits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue(logits.op.name.startswith('InceptionV4/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue(
predictions.op.name.startswith('InceptionV4/Logits/Predictions'))
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size, num_classes])
