Python tensorflow.contrib.slim.python.slim.nets.resnet_utils.resnet_arg_scope() Examples

The following are 30 code examples of tensorflow.contrib.slim.python.slim.nets.resnet_utils.resnet_arg_scope(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow.contrib.slim.python.slim.nets.resnet_utils , or try the search function .
Example #1
Source File: resnet_v1_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testFullyConvolutionalEndpointShapes(self):
    global_pool = False
    num_classes = 10
    inputs = create_test_input(2, 321, 321, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 41, 41, 4],
          'resnet/block2': [2, 21, 21, 8],
          'resnet/block3': [2, 11, 11, 16],
          'resnet/block4': [2, 11, 11, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #2
Source File: resnet_v2_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testAtrousFullyConvolutionalValues(self):
    """Verify dense feature extraction with atrous convolution."""
    nominal_stride = 32
    for output_stride in [4, 8, 16, 32, None]:
      with arg_scope(resnet_utils.resnet_arg_scope(is_training=False)):
        with ops.Graph().as_default():
          with self.test_session() as sess:
            random_seed.set_random_seed(0)
            inputs = create_test_input(2, 81, 81, 3)
            # Dense feature extraction followed by subsampling.
            output, _ = self._resnet_small(
                inputs, None, 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.
            variable_scope.get_variable_scope().reuse_variables()
            # Feature extraction at the nominal network rate.
            expected, _ = self._resnet_small(inputs, None, global_pool=False)
            sess.run(variables.global_variables_initializer())
            self.assertAllClose(
                output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #3
Source File: resnet_v2_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testAtrousFullyConvolutionalEndpointShapes(self):
    global_pool = False
    num_classes = 10
    output_stride = 8
    inputs = create_test_input(2, 321, 321, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs,
          num_classes,
          global_pool,
          output_stride=output_stride,
          scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 41, 41, 4],
          'resnet/block2': [2, 41, 41, 8],
          'resnet/block3': [2, 41, 41, 16],
          'resnet/block4': [2, 41, 41, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #4
Source File: resnet_v2_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testFullyConvolutionalEndpointShapes(self):
    global_pool = False
    num_classes = 10
    inputs = create_test_input(2, 321, 321, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 41, 41, 4],
          'resnet/block2': [2, 21, 21, 8],
          'resnet/block3': [2, 11, 11, 16],
          'resnet/block4': [2, 11, 11, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #5
Source File: resnet_v2_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testClassificationShapes(self):
    global_pool = True
    num_classes = 10
    inputs = create_test_input(2, 224, 224, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 28, 28, 4],
          'resnet/block2': [2, 14, 14, 8],
          'resnet/block3': [2, 7, 7, 16],
          'resnet/block4': [2, 7, 7, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #6
Source File: resnet_v2_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testUnknownBatchSize(self):
    batch = 2
    height, width = 65, 65
    global_pool = True
    num_classes = 10
    inputs = create_test_input(None, height, width, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      logits, _ = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
    self.assertTrue(logits.op.name.startswith('resnet/logits'))
    self.assertListEqual(logits.get_shape().as_list(),
                         [None, 1, 1, num_classes])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(logits, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 1, 1, num_classes))
Example #7
Source File: resnet_v1_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testClassificationShapes(self):
    global_pool = True
    num_classes = 10
    inputs = create_test_input(2, 224, 224, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 28, 28, 4],
          'resnet/block2': [2, 14, 14, 8],
          'resnet/block3': [2, 7, 7, 16],
          'resnet/block4': [2, 7, 7, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #8
Source File: resnet_v1_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testUnknownBatchSize(self):
    batch = 2
    height, width = 65, 65
    global_pool = True
    num_classes = 10
    inputs = create_test_input(None, height, width, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      logits, _ = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
    self.assertTrue(logits.op.name.startswith('resnet/logits'))
    self.assertListEqual(logits.get_shape().as_list(),
                         [None, 1, 1, num_classes])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(logits, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 1, 1, num_classes))
Example #9
Source File: resnet_v1_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testAtrousFullyConvolutionalValues(self):
    """Verify dense feature extraction with atrous convolution."""
    nominal_stride = 32
    for output_stride in [4, 8, 16, 32, None]:
      with arg_scope(resnet_utils.resnet_arg_scope(is_training=False)):
        with ops.Graph().as_default():
          with self.test_session() as sess:
            random_seed.set_random_seed(0)
            inputs = create_test_input(2, 81, 81, 3)
            # Dense feature extraction followed by subsampling.
            output, _ = self._resnet_small(
                inputs, None, 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.
            variable_scope.get_variable_scope().reuse_variables()
            # Feature extraction at the nominal network rate.
            expected, _ = self._resnet_small(inputs, None, global_pool=False)
            sess.run(variables.global_variables_initializer())
            self.assertAllClose(
                output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #10
Source File: resnet_v1_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testRootlessFullyConvolutionalEndpointShapes(self):
    global_pool = False
    num_classes = 10
    inputs = create_test_input(2, 128, 128, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs,
          num_classes,
          global_pool,
          include_root_block=False,
          scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 64, 64, 4],
          'resnet/block2': [2, 32, 32, 8],
          'resnet/block3': [2, 16, 16, 16],
          'resnet/block4': [2, 16, 16, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #11
Source File: resnet_v1_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testClassificationShapes(self):
    global_pool = True
    num_classes = 10
    inputs = create_test_input(2, 224, 224, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 28, 28, 4],
          'resnet/block2': [2, 14, 14, 8],
          'resnet/block3': [2, 7, 7, 16],
          'resnet/block4': [2, 7, 7, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #12
Source File: resnet_v1_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testFullyConvolutionalEndpointShapes(self):
    global_pool = False
    num_classes = 10
    inputs = create_test_input(2, 321, 321, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 41, 41, 4],
          'resnet/block2': [2, 21, 21, 8],
          'resnet/block3': [2, 11, 11, 16],
          'resnet/block4': [2, 11, 11, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #13
Source File: resnet_v1_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testRootlessFullyConvolutionalEndpointShapes(self):
    global_pool = False
    num_classes = 10
    inputs = create_test_input(2, 128, 128, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs,
          num_classes,
          global_pool,
          include_root_block=False,
          scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 64, 64, 4],
          'resnet/block2': [2, 32, 32, 8],
          'resnet/block3': [2, 16, 16, 16],
          'resnet/block4': [2, 16, 16, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #14
Source File: resnet_v1_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testAtrousFullyConvolutionalValues(self):
    """Verify dense feature extraction with atrous convolution."""
    nominal_stride = 32
    for output_stride in [4, 8, 16, 32, None]:
      with arg_scope(resnet_utils.resnet_arg_scope(is_training=False)):
        with ops.Graph().as_default():
          with self.test_session() as sess:
            random_seed.set_random_seed(0)
            inputs = create_test_input(2, 81, 81, 3)
            # Dense feature extraction followed by subsampling.
            output, _ = self._resnet_small(
                inputs, None, 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.
            variable_scope.get_variable_scope().reuse_variables()
            # Feature extraction at the nominal network rate.
            expected, _ = self._resnet_small(inputs, None, global_pool=False)
            sess.run(variables.global_variables_initializer())
            self.assertAllClose(
                output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #15
Source File: resnet_v1_test.py    From keras-lambda with MIT License 6 votes vote down vote up 
def testUnknownBatchSize(self):
    batch = 2
    height, width = 65, 65
    global_pool = True
    num_classes = 10
    inputs = create_test_input(None, height, width, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      logits, _ = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
    self.assertTrue(logits.op.name.startswith('resnet/logits'))
    self.assertListEqual(logits.get_shape().as_list(),
                         [None, 1, 1, num_classes])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(logits, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 1, 1, num_classes))
Example #16
Source File: resnet_v2_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testUnknownBatchSize(self):
    batch = 2
    height, width = 65, 65
    global_pool = True
    num_classes = 10
    inputs = create_test_input(None, height, width, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      logits, _ = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
    self.assertTrue(logits.op.name.startswith('resnet/logits'))
    self.assertListEqual(logits.get_shape().as_list(),
                         [None, 1, 1, num_classes])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(logits, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 1, 1, num_classes))
Example #17
Source File: resnet_v2_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testAtrousFullyConvolutionalValues(self):
    """Verify dense feature extraction with atrous convolution."""
    nominal_stride = 32
    for output_stride in [4, 8, 16, 32, None]:
      with arg_scope(resnet_utils.resnet_arg_scope(is_training=False)):
        with ops.Graph().as_default():
          with self.test_session() as sess:
            random_seed.set_random_seed(0)
            inputs = create_test_input(2, 81, 81, 3)
            # Dense feature extraction followed by subsampling.
            output, _ = self._resnet_small(
                inputs, None, 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.
            variable_scope.get_variable_scope().reuse_variables()
            # Feature extraction at the nominal network rate.
            expected, _ = self._resnet_small(inputs, None, global_pool=False)
            sess.run(variables.global_variables_initializer())
            self.assertAllClose(
                output.eval(), expected.eval(), atol=1e-4, rtol=1e-4)
Example #18
Source File: resnet_v2_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testAtrousFullyConvolutionalEndpointShapes(self):
    global_pool = False
    num_classes = 10
    output_stride = 8
    inputs = create_test_input(2, 321, 321, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs,
          num_classes,
          global_pool,
          output_stride=output_stride,
          scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 41, 41, 4],
          'resnet/block2': [2, 41, 41, 8],
          'resnet/block3': [2, 41, 41, 16],
          'resnet/block4': [2, 41, 41, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #19
Source File: resnet_v2_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testFullyConvolutionalEndpointShapes(self):
    global_pool = False
    num_classes = 10
    inputs = create_test_input(2, 321, 321, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 41, 41, 4],
          'resnet/block2': [2, 21, 21, 8],
          'resnet/block3': [2, 11, 11, 16],
          'resnet/block4': [2, 11, 11, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #20
Source File: resnet_v2_test.py    From auto-alt-text-lambda-api with MIT License 6 votes vote down vote up 
def testClassificationShapes(self):
    global_pool = True
    num_classes = 10
    inputs = create_test_input(2, 224, 224, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
      endpoint_to_shape = {
          'resnet/block1': [2, 28, 28, 4],
          'resnet/block2': [2, 14, 14, 8],
          'resnet/block3': [2, 7, 7, 16],
          'resnet/block4': [2, 7, 7, 32]
      }
      for endpoint in endpoint_to_shape:
        shape = endpoint_to_shape[endpoint]
        self.assertListEqual(end_points[endpoint].get_shape().as_list(), shape)
Example #21
Source File: resnet_v2_test.py    From keras-lambda with MIT License 5 votes vote down vote up 
def testEndPointsV2(self):
    """Test the end points of a tiny v2 bottleneck network."""
    bottleneck = resnet_v2.bottleneck
    blocks = [
        resnet_utils.Block('block1', bottleneck, [(4, 1, 1), (4, 1, 2)]),
        resnet_utils.Block('block2', bottleneck, [(8, 2, 1), (8, 2, 1)])
    ]
    inputs = create_test_input(2, 32, 16, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_plain(inputs, blocks, scope='tiny')
    expected = [
        'tiny/block1/unit_1/bottleneck_v2/shortcut',
        'tiny/block1/unit_1/bottleneck_v2/conv1',
        'tiny/block1/unit_1/bottleneck_v2/conv2',
        'tiny/block1/unit_1/bottleneck_v2/conv3',
        'tiny/block1/unit_2/bottleneck_v2/conv1',
        'tiny/block1/unit_2/bottleneck_v2/conv2',
        'tiny/block1/unit_2/bottleneck_v2/conv3',
        'tiny/block2/unit_1/bottleneck_v2/shortcut',
        'tiny/block2/unit_1/bottleneck_v2/conv1',
        'tiny/block2/unit_1/bottleneck_v2/conv2',
        'tiny/block2/unit_1/bottleneck_v2/conv3',
        'tiny/block2/unit_2/bottleneck_v2/conv1',
        'tiny/block2/unit_2/bottleneck_v2/conv2',
        'tiny/block2/unit_2/bottleneck_v2/conv3'
    ]
    self.assertItemsEqual(expected, end_points)
Example #22
Source File: resnet_v1_test.py    From keras-lambda with MIT License 5 votes vote down vote up 
def testClassificationEndPoints(self):
    global_pool = True
    num_classes = 10
    inputs = create_test_input(2, 224, 224, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      logits, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
    self.assertTrue(logits.op.name.startswith('resnet/logits'))
    self.assertListEqual(logits.get_shape().as_list(), [2, 1, 1, num_classes])
    self.assertTrue('predictions' in end_points)
    self.assertListEqual(end_points['predictions'].get_shape().as_list(),
                         [2, 1, 1, num_classes])
Example #23
Source File: resnet_v2_test.py    From keras-lambda with MIT License 5 votes vote down vote up 
def testAtrousFullyConvolutionalUnknownHeightWidth(self):
    batch = 2
    height, width = 65, 65
    global_pool = False
    output_stride = 8
    inputs = create_test_input(batch, None, None, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      output, _ = self._resnet_small(
          inputs, None, global_pool, output_stride=output_stride)
    self.assertListEqual(output.get_shape().as_list(), [batch, None, None, 32])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(output, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 9, 9, 32))
Example #24
Source File: resnet_v2_test.py    From keras-lambda with MIT License 5 votes vote down vote up 
def testFullyConvolutionalUnknownHeightWidth(self):
    batch = 2
    height, width = 65, 65
    global_pool = False
    inputs = create_test_input(batch, None, None, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      output, _ = self._resnet_small(inputs, None, global_pool)
    self.assertListEqual(output.get_shape().as_list(), [batch, None, None, 32])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(output, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 3, 3, 32))
Example #25
Source File: resnet_v1_test.py    From keras-lambda with MIT License 5 votes vote down vote up 
def testFullyConvolutionalUnknownHeightWidth(self):
    batch = 2
    height, width = 65, 65
    global_pool = False
    inputs = create_test_input(batch, None, None, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      output, _ = self._resnet_small(inputs, None, global_pool)
    self.assertListEqual(output.get_shape().as_list(), [batch, None, None, 32])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(output, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 3, 3, 32))
Example #26
Source File: resnet_v1_test.py    From keras-lambda with MIT License 5 votes vote down vote up 
def testAtrousFullyConvolutionalUnknownHeightWidth(self):
    batch = 2
    height, width = 65, 65
    global_pool = False
    output_stride = 8
    inputs = create_test_input(batch, None, None, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      output, _ = self._resnet_small(
          inputs, None, global_pool, output_stride=output_stride)
    self.assertListEqual(output.get_shape().as_list(), [batch, None, None, 32])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(output, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 9, 9, 32))
Example #27
Source File: resnet_v2_test.py    From keras-lambda with MIT License 5 votes vote down vote up 
def testClassificationEndPoints(self):
    global_pool = True
    num_classes = 10
    inputs = create_test_input(2, 224, 224, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      logits, end_points = self._resnet_small(
          inputs, num_classes, global_pool, scope='resnet')
    self.assertTrue(logits.op.name.startswith('resnet/logits'))
    self.assertListEqual(logits.get_shape().as_list(), [2, 1, 1, num_classes])
    self.assertTrue('predictions' in end_points)
    self.assertListEqual(end_points['predictions'].get_shape().as_list(),
                         [2, 1, 1, num_classes])
Example #28
Source File: resnet_v2_test.py    From auto-alt-text-lambda-api with MIT License 5 votes vote down vote up 
def testEndPointsV2(self):
    """Test the end points of a tiny v2 bottleneck network."""
    bottleneck = resnet_v2.bottleneck
    blocks = [
        resnet_utils.Block('block1', bottleneck, [(4, 1, 1), (4, 1, 2)]),
        resnet_utils.Block('block2', bottleneck, [(8, 2, 1), (8, 2, 1)])
    ]
    inputs = create_test_input(2, 32, 16, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      _, end_points = self._resnet_plain(inputs, blocks, scope='tiny')
    expected = [
        'tiny/block1/unit_1/bottleneck_v2/shortcut',
        'tiny/block1/unit_1/bottleneck_v2/conv1',
        'tiny/block1/unit_1/bottleneck_v2/conv2',
        'tiny/block1/unit_1/bottleneck_v2/conv3',
        'tiny/block1/unit_2/bottleneck_v2/conv1',
        'tiny/block1/unit_2/bottleneck_v2/conv2',
        'tiny/block1/unit_2/bottleneck_v2/conv3',
        'tiny/block2/unit_1/bottleneck_v2/shortcut',
        'tiny/block2/unit_1/bottleneck_v2/conv1',
        'tiny/block2/unit_1/bottleneck_v2/conv2',
        'tiny/block2/unit_1/bottleneck_v2/conv3',
        'tiny/block2/unit_2/bottleneck_v2/conv1',
        'tiny/block2/unit_2/bottleneck_v2/conv2',
        'tiny/block2/unit_2/bottleneck_v2/conv3'
    ]
    self.assertItemsEqual(expected, end_points)
Example #29
Source File: resnet_v1_test.py    From auto-alt-text-lambda-api with MIT License 5 votes vote down vote up 
def testAtrousFullyConvolutionalUnknownHeightWidth(self):
    batch = 2
    height, width = 65, 65
    global_pool = False
    output_stride = 8
    inputs = create_test_input(batch, None, None, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      output, _ = self._resnet_small(
          inputs, None, global_pool, output_stride=output_stride)
    self.assertListEqual(output.get_shape().as_list(), [batch, None, None, 32])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(output, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 9, 9, 32))
Example #30
Source File: resnet_v1_test.py    From auto-alt-text-lambda-api with MIT License 5 votes vote down vote up 
def testFullyConvolutionalUnknownHeightWidth(self):
    batch = 2
    height, width = 65, 65
    global_pool = False
    inputs = create_test_input(batch, None, None, 3)
    with arg_scope(resnet_utils.resnet_arg_scope()):
      output, _ = self._resnet_small(inputs, None, global_pool)
    self.assertListEqual(output.get_shape().as_list(), [batch, None, None, 32])
    images = create_test_input(batch, height, width, 3)
    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      output = sess.run(output, {inputs: images.eval()})
      self.assertEqual(output.shape, (batch, 3, 3, 32))