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 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 __call__(self, x_input):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
x_input = image_normalize(x_input, 'default')
with slim.arg_scope(inception.inception_v4_arg_scope()):
logit, end_points = inception.inception_v4(
x_input, num_classes=self.num_classes, is_training=True,
reuse=reuse)
self.built = True
output = end_points['Predictions']
# Strip off the extra reshape op at the output
probs = output.op.inputs[0]
return logit
def network(self):
with slim.arg_scope(inception.inception_v4_arg_scope()):
end_points = inception.inception_v4(inputs=self.x,
num_classes=1001,
is_training=self.is_training,
dropout_keep_prob=self.keep)
# print(end_points[1])
net = end_points[1]['PreLogitsFlatten']
print(net)
self.net = tf.stop_gradient(net) # 这层与之前的层都不进行梯度更新
print(net.shape)
with tf.variable_scope('D'): #重新建立两层全连接层
fc1 = slim.fully_connected(self.net,
512,
activation_fn=tf.nn.elu,
scope='fc1')
fc = slim.fully_connected(fc1,
48,
activation_fn=tf.nn.sigmoid,
scope='coding_layer')
self.y = slim.fully_connected(fc,
self.num_classes,
activation_fn=tf.nn.softmax,
scope='output')
tvars = tf.trainable_variables() # 获取所有可以更新的变量
d_params = [v for v in tvars if v.name.startswith('D/')
] # 只更新fc1,coding_layer与output的参数，其他的参数不更新
#计算loss值
self.cost = tf.losses.softmax_cross_entropy(onehot_labels=self.y_,
logits=self.y)
tf.summary.scalar('loss', self.cost)
self.global_step = tf.Variable(0, trainable=False)
#迭代递减的学习速率
lr = tf.train.exponential_decay(
self.config.lr, self.global_step,
self.config.total_nums / self.config.batch_size,
self.config.decay_rate)
#设置优化器
self.train_op = tf.train.GradientDescentOptimizer(lr).minimize(
loss=self.cost, global_step=self.global_step, var_list=d_params)
#计算正确率
self.correct_prediction = tf.equal(tf.argmax(self.y, 1),
tf.argmax(self.y_, 1))
self.accuracy = tf.reduce_mean(
tf.cast(self.correct_prediction, tf.float32))
tf.summary.scalar('accuracy', self.accuracy)
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])
