def bottleneck(inputs, depth, depth_bottleneck, stride, rate=1, outputs_collections=None, scope=None): """Bottleneck residual unit variant with BN after convolutions. This is the original residual unit proposed in [1]. See Fig. 1(a) of [2] for its definition. Note that we use here the bottleneck variant which has an extra bottleneck layer. When putting together two consecutive ResNet blocks that use this unit, one should use stride = 2 in the last unit of the first block. Args: inputs: A tensor of size [batch, height, width, channels]. depth: The depth of the ResNet unit output. depth_bottleneck: The depth of the bottleneck layers. stride: The ResNet unit's stride. Determines the amount of downsampling of the units output compared to its input. rate: An integer, rate for atrous convolution. outputs_collections: Collection to add the ResNet unit output. scope: Optional variable_scope. Returns: The ResNet unit's output. """ with tf.variable_scope(scope, 'bottleneck_v1', [inputs]) as sc: depth_in = slim.utils.last_dimension(inputs.get_shape(), min_rank=4) if depth == depth_in: shortcut = resnet_utils.subsample(inputs, stride, 'shortcut') else: shortcut = slim.conv2d(inputs, depth, [1, 1], stride=stride, activation_fn=None, scope='shortcut') residual = slim.conv2d(inputs, depth_bottleneck, [1, 1], stride=1, scope='conv1') residual = resnet_utils.conv2d_same(residual, depth_bottleneck, 3, stride, rate=rate, scope='conv2') residual = slim.conv2d(residual, depth, [1, 1], stride=1, activation_fn=None, scope='conv3') output = tf.nn.relu(shortcut + residual) return slim.utils.collect_named_outputs(outputs_collections, sc.original_name_scope, output)
def testAtrousFullyConvolutionalValues(self): """Verify dense feature extraction with atrous convolution.""" nominal_stride = 32 for output_stride in [4, 8, 16, 32, None]: with slim.arg_scope(resnet_utils.resnet_arg_scope()): with tf.Graph().as_default(): with self.test_session() as sess: tf.set_random_seed(0) inputs = create_test_input(2, 81, 81, 3) # Dense feature extraction followed by subsampling. output, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False, output_stride=output_stride) if output_stride is None: factor = 1 else: factor = nominal_stride // output_stride output = resnet_utils.subsample(output, factor) # Make the two networks use the same weights. tf.get_variable_scope().reuse_variables() # Feature extraction at the nominal network rate. expected, _ = self._resnet_small(inputs, None, is_training=False, global_pool=False) sess.run(tf.global_variables_initializer()) self.assertAllClose(output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
def _atrousValues(self, bottleneck): """Verify the values of dense feature extraction by atrous convolution. Make sure that dense feature extraction by stack_blocks_dense() followed by subsampling gives identical results to feature extraction at the nominal network output stride using the simple self._stack_blocks_nondense() above. Args: bottleneck: The bottleneck function. """ blocks = [ resnet_utils.Block('block1', bottleneck, [(4, 1, 1), (4, 1, 2)]), resnet_utils.Block('block2', bottleneck, [(8, 2, 1), (8, 2, 2)]), resnet_utils.Block('block3', bottleneck, [(16, 4, 1), (16, 4, 2)]), resnet_utils.Block('block4', bottleneck, [(32, 8, 1), (32, 8, 1)]) ] nominal_stride = 8 # Test both odd and even input dimensions. height = 30 width = 31 with slim.arg_scope(resnet_utils.resnet_arg_scope()): with slim.arg_scope([slim.batch_norm], is_training=False): for output_stride in [1, 2, 4, 8, None]: with tf.Graph().as_default(): with self.test_session() as sess: tf.set_random_seed(0) inputs = create_test_input(1, height, width, 3) # Dense feature extraction followed by subsampling. output = resnet_utils.stack_blocks_dense(inputs, blocks, output_stride) if output_stride is None: factor = 1 else: factor = nominal_stride // output_stride output = resnet_utils.subsample(output, factor) # Make the two networks use the same weights. tf.get_variable_scope().reuse_variables() # Feature extraction at the nominal network rate. expected = self._stack_blocks_nondense(inputs, blocks) sess.run(tf.global_variables_initializer()) output, expected = sess.run([output, expected]) self.assertAllClose(output, expected, atol=1e-4, rtol=1e-4)
def testConv2DSameEven(self): n, n2 = 4, 2 # Input image. x = create_test_input(1, n, n, 1) # Convolution kernel. w = create_test_input(1, 3, 3, 1) w = tf.reshape(w, [3, 3, 1, 1]) tf.get_variable('Conv/weights', initializer=w) tf.get_variable('Conv/biases', initializer=tf.zeros([1])) tf.get_variable_scope().reuse_variables() y1 = slim.conv2d(x, 1, [3, 3], stride=1, scope='Conv') y1_expected = tf.to_float([[14, 28, 43, 26], [28, 48, 66, 37], [43, 66, 84, 46], [26, 37, 46, 22]]) y1_expected = tf.reshape(y1_expected, [1, n, n, 1]) y2 = resnet_utils.subsample(y1, 2) y2_expected = tf.to_float([[14, 43], [43, 84]]) y2_expected = tf.reshape(y2_expected, [1, n2, n2, 1]) y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv') y3_expected = y2_expected y4 = slim.conv2d(x, 1, [3, 3], stride=2, scope='Conv') y4_expected = tf.to_float([[48, 37], [37, 22]]) y4_expected = tf.reshape(y4_expected, [1, n2, n2, 1]) with self.test_session() as sess: sess.run(tf.global_variables_initializer()) self.assertAllClose(y1.eval(), y1_expected.eval()) self.assertAllClose(y2.eval(), y2_expected.eval()) self.assertAllClose(y3.eval(), y3_expected.eval()) self.assertAllClose(y4.eval(), y4_expected.eval())
def testSubsampleFourByFour(self): x = tf.reshape(tf.to_float(tf.range(16)), [1, 4, 4, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 8, 10]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())
def testSubsampleThreeByThree(self): x = tf.reshape(tf.to_float(tf.range(9)), [1, 3, 3, 1]) x = resnet_utils.subsample(x, 2) expected = tf.reshape(tf.constant([0, 2, 6, 8]), [1, 2, 2, 1]) with self.test_session(): self.assertAllClose(x.eval(), expected.eval())