def _testKerasLayer(self, layer_class):
def kernel_posterior_fn(dtype, shape, name, trainable,
add_variable_fn):
"""Set trivially. The function is required to instantiate layer."""
del name, trainable, add_variable_fn # unused
# Deserialized Keras objects do not perform lexical scoping. Any modules
# that the function requires must be imported within the function.
import tensorflow as tf # pylint: disable=g-import-not-at-top,redefined-outer-name
tfd = tf.contrib.distributions # pylint: disable=redefined-outer-name
loc = tf.zeros(shape, dtype=dtype)
scale = tf.ones(shape, dtype=dtype)
return tfd.Independent(tfd.Normal(loc=loc, scale=scale))
kwargs = {
'units': 3,
'kernel_posterior_fn': kernel_posterior_fn,
'kernel_prior_fn': None,
'bias_posterior_fn': None,
'bias_prior_fn': None
}
with tf.keras.utils.CustomObjectScope(
{layer_class.__name__: layer_class}):
with self.test_session():
testing_utils.layer_test(layer_class,
kwargs=kwargs,
input_shape=(3, 2))
testing_utils.layer_test(layer_class,
kwargs=kwargs,
input_shape=(None, None, 2))
def test_separable_conv_2d(self):
num_samples = 2
filters = 6
stack_size = 3
num_row = 7
num_col = 6
for padding in ['valid', 'same']:
for strides in [(1, 1), (2, 2)]:
for multiplier in [1, 2]:
if padding == 'same' and strides != (1, 1):
continue
with self.test_session(use_gpu=True):
testing_utils.layer_test(keras.layers.SeparableConv2D,
kwargs={
'filters': filters,
'kernel_size': (3, 3),
'padding': padding,
'strides': strides,
'depth_multiplier':
multiplier
},
input_shape=(num_samples,
num_row, num_col,
stack_size))
def test_cropping_2d(self):
num_samples = 2
stack_size = 2
input_len_dim1 = 9
input_len_dim2 = 9
cropping = ((2, 2), (3, 3))
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size, input_len_dim1,
input_len_dim2)
else:
inputs = np.random.rand(num_samples, input_len_dim1, input_len_dim2,
stack_size)
# basic test
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.Cropping2D,
kwargs={'cropping': cropping,
'data_format': data_format},
input_shape=inputs.shape)
# correctness test
with self.test_session(use_gpu=True):
layer = keras.layers.Cropping2D(
cropping=cropping, data_format=data_format)
layer.build(inputs.shape)
output = layer(keras.backend.variable(inputs))
np_output = keras.backend.eval(output)
# compare with numpy
if data_format == 'channels_first':
expected_out = inputs[:, :, cropping[0][0]:-cropping[0][1], cropping[
1][0]:-cropping[1][1]]
else:
expected_out = inputs[:, cropping[0][0]:-cropping[0][1], cropping[1][
0]:-cropping[1][1], :]
np.testing.assert_allclose(np_output, expected_out)
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size, input_len_dim1,
input_len_dim2)
else:
inputs = np.random.rand(num_samples, input_len_dim1, input_len_dim2,
stack_size)
# another correctness test (no cropping)
with self.test_session(use_gpu=True):
cropping = ((0, 0), (0, 0))
layer = keras.layers.Cropping2D(
cropping=cropping, data_format=data_format)
layer.build(inputs.shape)
output = layer(keras.backend.variable(inputs))
np_output = keras.backend.eval(output)
# compare with input
np.testing.assert_allclose(np_output, inputs)
# test incorrect use
with self.assertRaises(ValueError):
keras.layers.Cropping2D(cropping=(1, 1, 1))
with self.assertRaises(ValueError):
keras.layers.Cropping2D(cropping=None)
def test_locallyconnected_2d(self):
num_samples = 8
filters = 3
stack_size = 4
num_row = 6
num_col = 10
for padding in ['valid']:
for strides in [(1, 1), (2, 2)]:
if padding == 'same' and strides != (1, 1):
continue
with self.test_session():
testing_utils.layer_test(
keras.layers.LocallyConnected2D,
kwargs={
'filters': filters,
'kernel_size': 3,
'padding': padding,
'kernel_regularizer': 'l2',
'bias_regularizer': 'l2',
'activity_regularizer': 'l2',
'strides': strides,
'data_format': 'channels_last'
},
input_shape=(num_samples, num_row, num_col, stack_size))
def test_zero_padding_3d(self):
num_samples = 2
stack_size = 2
input_len_dim1 = 4
input_len_dim2 = 5
input_len_dim3 = 3
inputs = np.ones((num_samples, input_len_dim1, input_len_dim2,
input_len_dim3, stack_size))
# basic test
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.ZeroPadding3D,
kwargs={'padding': (2, 2, 2)},
input_shape=inputs.shape)
# correctness test
with self.test_session(use_gpu=True):
layer = keras.layers.ZeroPadding3D(padding=(2, 2, 2))
layer.build(inputs.shape)
output = layer(keras.backend.variable(inputs))
np_output = keras.backend.eval(output)
for offset in [0, 1, -1, -2]:
np.testing.assert_allclose(np_output[:, offset, :, :, :], 0.)
np.testing.assert_allclose(np_output[:, :, offset, :, :], 0.)
np.testing.assert_allclose(np_output[:, :, :, offset, :], 0.)
np.testing.assert_allclose(np_output[:, 2:-2, 2:-2, 2:-2, :], 1.)
# test incorrect use
with self.assertRaises(ValueError):
keras.layers.ZeroPadding3D(padding=(1, 1))
with self.assertRaises(ValueError):
keras.layers.ZeroPadding3D(padding=None)
def test_locallyconnected_2d(self):
num_samples = 8
filters = 3
stack_size = 4
num_row = 6
num_col = 10
for padding in ['valid']:
for strides in [(1, 1), (2, 2)]:
if padding == 'same' and strides != (1, 1):
continue
with self.test_session():
testing_utils.layer_test(keras.layers.LocallyConnected2D,
kwargs={
'filters': filters,
'kernel_size': 3,
'padding': padding,
'kernel_regularizer': 'l2',
'bias_regularizer': 'l2',
'activity_regularizer': 'l2',
'strides': strides,
'data_format': 'channels_last'
},
input_shape=(num_samples, num_row,
num_col, stack_size))
def test_convolution_2d(self):
num_samples = 2
filters = 2
stack_size = 3
kernel_size = (3, 2)
num_row = 7
num_col = 6
for padding in ['valid', 'same']:
for strides in [(1, 1), (2, 2)]:
if padding == 'same' and strides != (1, 1):
continue
with self.test_session(use_gpu=True):
# Only runs on GPU with CUDA, channels_first is not supported on CPU.
# TODO(b/62340061): Support channels_first on CPU.
if test.is_gpu_available(cuda_only=True):
testing_utils.layer_test(
keras.layers.Conv2D,
kwargs={
'filters': filters,
'kernel_size': kernel_size,
'padding': padding,
'strides': strides,
'data_format': 'channels_first'
},
input_shape=(num_samples, stack_size, num_row, num_col))
def test_convolution_3d(self):
num_samples = 2
filters = 2
stack_size = 3
input_len_dim1 = 9
input_len_dim2 = 8
input_len_dim3 = 8
for padding in ['valid', 'same']:
for strides in [(1, 1, 1), (2, 2, 2)]:
if padding == 'same' and strides != (1, 1, 1):
continue
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.Convolution3D,
kwargs={
'filters': filters,
'kernel_size': 3,
'padding': padding,
'strides': strides
},
input_shape=(num_samples, input_len_dim1, input_len_dim2,
input_len_dim3, stack_size))
def test_spatial_dropout(self):
testing_utils.layer_test(
keras.layers.SpatialDropout1D,
kwargs={'rate': 0.5},
input_shape=(2, 3, 4))
testing_utils.layer_test(
keras.layers.SpatialDropout2D,
kwargs={'rate': 0.5},
input_shape=(2, 3, 4, 5))
testing_utils.layer_test(
keras.layers.SpatialDropout2D,
kwargs={'rate': 0.5, 'data_format': 'channels_first'},
input_shape=(2, 3, 4, 5))
testing_utils.layer_test(
keras.layers.SpatialDropout3D,
kwargs={'rate': 0.5},
input_shape=(2, 3, 4, 4, 5))
testing_utils.layer_test(
keras.layers.SpatialDropout3D,
kwargs={'rate': 0.5, 'data_format': 'channels_first'},
input_shape=(2, 3, 4, 4, 5))
def test_lambda(self):
testing_utils.layer_test(
keras.layers.Lambda,
kwargs={'function': lambda x: x + 1},
input_shape=(3, 2))
testing_utils.layer_test(
keras.layers.Lambda,
kwargs={
'function': lambda x, a, b: x * a + b,
'arguments': {
'a': 0.6,
'b': 0.4
}
},
input_shape=(3, 2))
# test serialization with function
def f(x):
return x + 1
ld = keras.layers.Lambda(f)
config = ld.get_config()
ld = keras.layers.deserialize({
'class_name': 'Lambda',
'config': config
})
# test with lambda
ld = keras.layers.Lambda(
lambda x: keras.backend.concatenate([math_ops.square(x), x]))
config = ld.get_config()
ld = keras.layers.Lambda.from_config(config)
def test_globalpooling_1d(self):
with self.test_session(use_gpu=True):
testing_utils.layer_test(keras.layers.pooling.GlobalMaxPooling1D,
input_shape=(3, 4, 5))
testing_utils.layer_test(
keras.layers.pooling.GlobalAveragePooling1D,
input_shape=(3, 4, 5))
def test_conv3d_transpose(self):
num_samples = 2
filters = 2
stack_size = 3
num_row = 5
num_col = 6
depth = 4
for padding in ['valid', 'same']:
for strides in [(1, 1, 1), (2, 2, 2)]:
if padding == 'same' and strides != (1, 1, 1):
continue
with self.test_session(use_gpu=True):
testing_utils.layer_test(keras.layers.Conv3DTranspose,
kwargs={
'filters': filters,
'kernel_size': 3,
'padding': padding,
'strides': strides,
'data_format': 'channels_last'
},
input_shape=(num_samples, depth,
num_row, num_col,
stack_size))
def test_cudnn_rnn_basics(self):
if test.is_gpu_available(cuda_only=True):
with self.test_session(use_gpu=True):
input_size = 10
timesteps = 6
units = 2
num_samples = 32
for layer_class in [keras.layers.CuDNNGRU, keras.layers.CuDNNLSTM]:
for return_sequences in [True, False]:
with keras.utils.CustomObjectScope(
{'keras.layers.CuDNNGRU': keras.layers.CuDNNGRU,
'keras.layers.CuDNNLSTM': keras.layers.CuDNNLSTM}):
testing_utils.layer_test(
layer_class,
kwargs={'units': units,
'return_sequences': return_sequences},
input_shape=(num_samples, timesteps, input_size))
for go_backwards in [True, False]:
with keras.utils.CustomObjectScope(
{'keras.layers.CuDNNGRU': keras.layers.CuDNNGRU,
'keras.layers.CuDNNLSTM': keras.layers.CuDNNLSTM}):
testing_utils.layer_test(
layer_class,
kwargs={'units': units,
'go_backwards': go_backwards},
input_shape=(num_samples, timesteps, input_size))
def test_upsampling_2d(self):
num_samples = 2
stack_size = 2
input_num_row = 11
input_num_col = 12
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size, input_num_row,
input_num_col)
else:
inputs = np.random.rand(num_samples, input_num_row,
input_num_col, stack_size)
# basic test
with self.test_session(use_gpu=True):
testing_utils.layer_test(keras.layers.UpSampling2D,
kwargs={
'size': (2, 2),
'data_format': data_format
},
input_shape=inputs.shape)
for length_row in [2]:
for length_col in [2, 3]:
layer = keras.layers.UpSampling2D(
size=(length_row, length_col),
data_format=data_format)
layer.build(inputs.shape)
output = layer(keras.backend.variable(inputs))
np_output = keras.backend.eval(output)
if data_format == 'channels_first':
assert np_output.shape[
2] == length_row * input_num_row
assert np_output.shape[
3] == length_col * input_num_col
else: # tf
assert np_output.shape[
1] == length_row * input_num_row
assert np_output.shape[
2] == length_col * input_num_col
# compare with numpy
if data_format == 'channels_first':
expected_out = np.repeat(inputs,
length_row,
axis=2)
expected_out = np.repeat(expected_out,
length_col,
axis=3)
else: # tf
expected_out = np.repeat(inputs,
length_row,
axis=1)
expected_out = np.repeat(expected_out,
length_col,
axis=2)
np.testing.assert_allclose(np_output, expected_out)
def test_averagepooling_1d(self):
for padding in ['valid', 'same']:
for stride in [1, 2]:
testing_utils.layer_test(
keras.layers.AveragePooling1D,
kwargs={'strides': stride,
'padding': padding},
input_shape=(3, 5, 4))
def test_cropping_3d(self):
num_samples = 2
stack_size = 2
input_len_dim1 = 8
input_len_dim2 = 8
input_len_dim3 = 8
croppings = [((2, 2), (1, 1), (2, 3)), 3, (0, 1, 1)]
for cropping in croppings:
for data_format in ['channels_last', 'channels_first']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size,
input_len_dim1, input_len_dim2,
input_len_dim3)
else:
inputs = np.random.rand(num_samples, input_len_dim1,
input_len_dim2, input_len_dim3,
stack_size)
# basic test
with self.test_session(use_gpu=True):
testing_utils.layer_test(keras.layers.Cropping3D,
kwargs={
'cropping': cropping,
'data_format': data_format
},
input_shape=inputs.shape)
if len(croppings) == 3 and len(croppings[0]) == 2:
# correctness test
with self.test_session(use_gpu=True):
layer = keras.layers.Cropping3D(
cropping=cropping, data_format=data_format)
layer.build(inputs.shape)
output = layer(keras.backend.variable(inputs))
if context.executing_eagerly():
np_output = output.numpy()
else:
np_output = keras.backend.eval(output)
# compare with numpy
if data_format == 'channels_first':
expected_out = inputs[:, :, cropping[0][0]:
-cropping[0][1], cropping[1]
[0]:-cropping[1][1],
cropping[2][0]:
-cropping[2][1]]
else:
expected_out = inputs[:, cropping[0][0]:
-cropping[0][1], cropping[1]
[0]:-cropping[1][1],
cropping[2][0]:
-cropping[2][1], :]
np.testing.assert_allclose(np_output, expected_out)
# test incorrect use
with self.assertRaises(ValueError):
keras.layers.Cropping3D(cropping=(1, 1))
with self.assertRaises(ValueError):
keras.layers.Cropping3D(cropping=None)
def test_maxpooling_1d(self):
with self.test_session(use_gpu=True):
for padding in ['valid', 'same']:
for stride in [1, 2]:
testing_utils.layer_test(
keras.layers.MaxPooling1D,
kwargs={'strides': stride,
'padding': padding},
input_shape=(3, 5, 4))
def test_conv_lstm(self):
num_row = 3
num_col = 3
filters = 2
num_samples = 1
input_channel = 2
input_num_row = 5
input_num_col = 5
sequence_len = 2
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, sequence_len,
input_channel, input_num_row,
input_num_col)
else:
inputs = np.random.rand(num_samples, sequence_len,
input_num_row, input_num_col,
input_channel)
for return_sequences in [True, False]:
with self.test_session():
# test for return state:
x = keras.Input(batch_shape=inputs.shape)
kwargs = {
'data_format': data_format,
'return_sequences': return_sequences,
'return_state': True,
'stateful': True,
'filters': filters,
'kernel_size': (num_row, num_col),
'padding': 'valid'
}
layer = keras.layers.ConvLSTM2D(**kwargs)
layer.build(inputs.shape)
outputs = layer(x)
_, states = outputs[0], outputs[1:]
self.assertEqual(len(states), 2)
model = keras.models.Model(x, states[0])
state = model.predict(inputs)
self.assertAllClose(keras.backend.eval(layer.states[0]),
state,
atol=1e-4)
# test for output shape:
testing_utils.layer_test(keras.layers.ConvLSTM2D,
kwargs={
'data_format': data_format,
'return_sequences':
return_sequences,
'filters': filters,
'kernel_size':
(num_row, num_col),
'padding': 'valid'
},
input_shape=inputs.shape)
def test_return_sequences_GRU(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
testing_utils.layer_test(
keras.layers.GRU,
kwargs={'units': units,
'return_sequences': True},
input_shape=(num_samples, timesteps, embedding_dim))
def test_maxpooling_2d(self):
pool_size = (3, 3)
for strides in [(1, 1), (2, 2)]:
testing_utils.layer_test(keras.layers.MaxPooling2D,
kwargs={
'strides': strides,
'padding': 'valid',
'pool_size': pool_size
},
input_shape=(3, 5, 6, 4))
def test_return_sequences_LSTM(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
testing_utils.layer_test(
keras.layers.LSTM,
kwargs={'units': units,
'return_sequences': True},
input_shape=(num_samples, timesteps, embedding_dim))
def test_activation(self):
# with string argument
testing_utils.layer_test(keras.layers.Activation,
kwargs={'activation': 'relu'},
input_shape=(3, 2))
# with function argument
testing_utils.layer_test(keras.layers.Activation,
kwargs={'activation': keras.backend.relu},
input_shape=(3, 2))
def test_maxpooling_1d(self):
with self.test_session(use_gpu=True):
for padding in ['valid', 'same']:
for stride in [1, 2]:
testing_utils.layer_test(keras.layers.MaxPooling1D,
kwargs={
'strides': stride,
'padding': padding
},
input_shape=(3, 5, 4))
def test_upsampling_3d(self):
num_samples = 2
stack_size = 2
input_len_dim1 = 10
input_len_dim2 = 11
input_len_dim3 = 12
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size, input_len_dim1,
input_len_dim2, input_len_dim3)
else:
inputs = np.random.rand(num_samples, input_len_dim1, input_len_dim2,
input_len_dim3, stack_size)
# basic test
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.UpSampling3D,
kwargs={'size': (2, 2, 2),
'data_format': data_format},
input_shape=inputs.shape)
for length_dim1 in [2, 3]:
for length_dim2 in [2]:
for length_dim3 in [3]:
layer = keras.layers.UpSampling3D(
size=(length_dim1, length_dim2, length_dim3),
data_format=data_format)
layer.build(inputs.shape)
output = layer(keras.backend.variable(inputs))
if context.executing_eagerly():
np_output = output.numpy()
else:
np_output = keras.backend.eval(output)
if data_format == 'channels_first':
assert np_output.shape[2] == length_dim1 * input_len_dim1
assert np_output.shape[3] == length_dim2 * input_len_dim2
assert np_output.shape[4] == length_dim3 * input_len_dim3
else: # tf
assert np_output.shape[1] == length_dim1 * input_len_dim1
assert np_output.shape[2] == length_dim2 * input_len_dim2
assert np_output.shape[3] == length_dim3 * input_len_dim3
# compare with numpy
if data_format == 'channels_first':
expected_out = np.repeat(inputs, length_dim1, axis=2)
expected_out = np.repeat(expected_out, length_dim2, axis=3)
expected_out = np.repeat(expected_out, length_dim3, axis=4)
else: # tf
expected_out = np.repeat(inputs, length_dim1, axis=1)
expected_out = np.repeat(expected_out, length_dim2, axis=2)
expected_out = np.repeat(expected_out, length_dim3, axis=3)
np.testing.assert_allclose(np_output, expected_out)
def test_maxpooling_2d(self):
pool_size = (3, 3)
for strides in [(1, 1), (2, 2)]:
testing_utils.layer_test(
keras.layers.MaxPooling2D,
kwargs={
'strides': strides,
'padding': 'valid',
'pool_size': pool_size
},
input_shape=(3, 5, 6, 4))
def test_dropout_LSTM(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
testing_utils.layer_test(
keras.layers.LSTM,
kwargs={'units': units,
'dropout': 0.1,
'recurrent_dropout': 0.1},
input_shape=(num_samples, timesteps, embedding_dim))
def test_implementation_mode_LSTM(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
for mode in [0, 1, 2]:
testing_utils.layer_test(
keras.layers.LSTM,
kwargs={'units': units,
'implementation': mode},
input_shape=(num_samples, timesteps, embedding_dim))
def test_return_sequences_GRU(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
with self.test_session():
testing_utils.layer_test(
keras.layers.GRU,
kwargs={'units': units,
'return_sequences': True},
input_shape=(num_samples, timesteps, embedding_dim))
def test_dropout_GRU(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
testing_utils.layer_test(
keras.layers.GRU,
kwargs={'units': units,
'dropout': 0.1,
'recurrent_dropout': 0.1},
input_shape=(num_samples, timesteps, embedding_dim))
def test_return_sequences_LSTM(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
with self.test_session():
testing_utils.layer_test(
keras.layers.LSTM,
kwargs={'units': units,
'return_sequences': True},
input_shape=(num_samples, timesteps, embedding_dim))
def test_implementation_mode_GRU(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
for mode in [0, 1, 2]:
testing_utils.layer_test(
keras.layers.GRU,
kwargs={'units': units,
'implementation': mode},
input_shape=(num_samples, timesteps, embedding_dim))
def test_implementation_mode_SimpleRNN(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
with self.test_session():
for mode in [0, 1, 2]:
testing_utils.layer_test(
keras.layers.SimpleRNN,
kwargs={'units': units,
'implementation': mode},
input_shape=(num_samples, timesteps, embedding_dim))
def test_dropout_GRU(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
with self.test_session():
testing_utils.layer_test(
keras.layers.GRU,
kwargs={'units': units,
'dropout': 0.1,
'recurrent_dropout': 0.1},
input_shape=(num_samples, timesteps, embedding_dim))
def test_cropping_3d(self):
num_samples = 2
stack_size = 2
input_len_dim1 = 8
input_len_dim2 = 8
input_len_dim3 = 8
croppings = [((2, 2), (1, 1), (2, 3)), 3, (0, 1, 1)]
for cropping in croppings:
for data_format in ['channels_last', 'channels_first']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size, input_len_dim1,
input_len_dim2, input_len_dim3)
else:
inputs = np.random.rand(num_samples, input_len_dim1, input_len_dim2,
input_len_dim3, stack_size)
# basic test
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.Cropping3D,
kwargs={'cropping': cropping,
'data_format': data_format},
input_shape=inputs.shape)
if len(croppings) == 3 and len(croppings[0]) == 2:
# correctness test
with self.test_session(use_gpu=True):
layer = keras.layers.Cropping3D(
cropping=cropping, data_format=data_format)
layer.build(inputs.shape)
output = layer(keras.backend.variable(inputs))
if context.executing_eagerly():
np_output = output.numpy()
else:
np_output = keras.backend.eval(output)
# compare with numpy
if data_format == 'channels_first':
expected_out = inputs[:, :,
cropping[0][0]:-cropping[0][1],
cropping[1][0]:-cropping[1][1],
cropping[2][0]:-cropping[2][1]]
else:
expected_out = inputs[:,
cropping[0][0]:-cropping[0][1],
cropping[1][0]:-cropping[1][1],
cropping[2][0]:-cropping[2][1], :]
np.testing.assert_allclose(np_output, expected_out)
# test incorrect use
with self.assertRaises(ValueError):
keras.layers.Cropping3D(cropping=(1, 1))
with self.assertRaises(ValueError):
keras.layers.Cropping3D(cropping=None)
def test_dropout_LSTM(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
with self.test_session():
testing_utils.layer_test(
keras.layers.LSTM,
kwargs={'units': units,
'dropout': 0.1,
'recurrent_dropout': 0.1},
input_shape=(num_samples, timesteps, embedding_dim))
def test_activation(self):
# with string argument
testing_utils.layer_test(
keras.layers.Activation,
kwargs={'activation': 'relu'},
input_shape=(3, 2))
# with function argument
testing_utils.layer_test(
keras.layers.Activation,
kwargs={'activation': keras.backend.relu},
input_shape=(3, 2))
def test_upsampling_3d(self):
num_samples = 2
stack_size = 2
input_len_dim1 = 10
input_len_dim2 = 11
input_len_dim3 = 12
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size, input_len_dim1,
input_len_dim2, input_len_dim3)
else:
inputs = np.random.rand(num_samples, input_len_dim1, input_len_dim2,
input_len_dim3, stack_size)
# basic test
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.UpSampling3D,
kwargs={'size': (2, 2, 2),
'data_format': data_format},
input_shape=inputs.shape)
for length_dim1 in [2, 3]:
for length_dim2 in [2]:
for length_dim3 in [3]:
layer = keras.layers.UpSampling3D(
size=(length_dim1, length_dim2, length_dim3),
data_format=data_format)
layer.build(inputs.shape)
output = layer(keras.backend.variable(inputs))
np_output = keras.backend.eval(output)
if data_format == 'channels_first':
assert np_output.shape[2] == length_dim1 * input_len_dim1
assert np_output.shape[3] == length_dim2 * input_len_dim2
assert np_output.shape[4] == length_dim3 * input_len_dim3
else: # tf
assert np_output.shape[1] == length_dim1 * input_len_dim1
assert np_output.shape[2] == length_dim2 * input_len_dim2
assert np_output.shape[3] == length_dim3 * input_len_dim3
# compare with numpy
if data_format == 'channels_first':
expected_out = np.repeat(inputs, length_dim1, axis=2)
expected_out = np.repeat(expected_out, length_dim2, axis=3)
expected_out = np.repeat(expected_out, length_dim3, axis=4)
else: # tf
expected_out = np.repeat(inputs, length_dim1, axis=1)
expected_out = np.repeat(expected_out, length_dim2, axis=2)
expected_out = np.repeat(expected_out, length_dim3, axis=3)
np.testing.assert_allclose(np_output, expected_out)
def _run_test(self, kwargs, arg, values):
num_samples = 2
stack_size = 3
length = 7
test_kwargs = copy.copy(kwargs)
for value in values:
test_kwargs[arg] = value
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.Conv1D,
kwargs=test_kwargs,
input_shape=(num_samples, length, stack_size))
def test_conv_lstm_dropout(self):
# check dropout
with self.test_session():
testing_utils.layer_test(
keras.layers.ConvLSTM2D,
kwargs={'data_format': 'channels_last',
'return_sequences': False,
'filters': 2,
'kernel_size': (3, 3),
'padding': 'same',
'dropout': 0.1,
'recurrent_dropout': 0.1},
input_shape=(1, 2, 5, 5, 2))
def _run_test(self, kwargs, arg, values):
num_samples = 2
stack_size = 3
length = 7
test_kwargs = copy.copy(kwargs)
for value in values:
test_kwargs[arg] = value
with self.test_session(use_gpu=True):
testing_utils.layer_test(keras.layers.Conv1D,
kwargs=test_kwargs,
input_shape=(num_samples, length,
stack_size))
def test_implementation_mode_SimpleRNN(self):
num_samples = 2
timesteps = 3
embedding_dim = 4
units = 2
with self.test_session():
for mode in [0, 1, 2]:
testing_utils.layer_test(keras.layers.SimpleRNN,
kwargs={
'units': units,
'implementation': mode
},
input_shape=(num_samples, timesteps,
embedding_dim))
def test_dilated_conv1d(self):
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.Conv1D,
input_data=np.reshape(np.arange(4, dtype='float32'), (1, 4, 1)),
kwargs={
'filters': 1,
'kernel_size': 2,
'dilation_rate': 1,
'padding': 'valid',
'kernel_initializer': 'ones',
'use_bias': False,
},
expected_output=[[[1], [3], [5]]])
def test_zero_padding_1d(self):
num_samples = 2
input_dim = 2
num_steps = 5
shape = (num_samples, num_steps, input_dim)
inputs = np.ones(shape)
# basic test
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.ZeroPadding1D,
kwargs={'padding': 2},
input_shape=inputs.shape)
testing_utils.layer_test(
keras.layers.ZeroPadding1D,
kwargs={'padding': (1, 2)},
input_shape=inputs.shape)
# correctness test
with self.test_session(use_gpu=True):
layer = keras.layers.ZeroPadding1D(padding=2)
layer.build(shape)
output = layer(keras.backend.variable(inputs))
if context.executing_eagerly():
np_output = output.numpy()
else:
np_output = keras.backend.eval(output)
for offset in [0, 1, -1, -2]:
np.testing.assert_allclose(np_output[:, offset, :], 0.)
np.testing.assert_allclose(np_output[:, 2:-2, :], 1.)
layer = keras.layers.ZeroPadding1D(padding=(1, 2))
layer.build(shape)
output = layer(keras.backend.variable(inputs))
if context.executing_eagerly():
np_output = output.numpy()
else:
np_output = keras.backend.eval(output)
for left_offset in [0]:
np.testing.assert_allclose(np_output[:, left_offset, :], 0.)
for right_offset in [-1, -2]:
np.testing.assert_allclose(np_output[:, right_offset, :], 0.)
np.testing.assert_allclose(np_output[:, 1:-2, :], 1.)
layer.get_config()
# test incorrect use
with self.assertRaises(ValueError):
keras.layers.ZeroPadding1D(padding=(1, 1, 1))
with self.assertRaises(ValueError):
keras.layers.ZeroPadding1D(padding=None)
def test_conv_lstm_dropout(self):
# check dropout
with self.test_session():
testing_utils.layer_test(keras.layers.ConvLSTM2D,
kwargs={
'data_format': 'channels_last',
'return_sequences': False,
'filters': 2,
'kernel_size': (3, 3),
'padding': 'same',
'dropout': 0.1,
'recurrent_dropout': 0.1
},
input_shape=(1, 2, 5, 5, 2))
def _run_test(self, kwargs, arg, values):
num_samples = 2
stack_size = 3
num_row = 7
num_col = 6
test_kwargs = copy.copy(kwargs)
for value in values:
test_kwargs[arg] = value
with self.test_session(use_gpu=True):
testing_utils.layer_test(keras.layers.SeparableConv2D,
kwargs=test_kwargs,
input_shape=(num_samples, num_row,
num_col, stack_size))
def test_conv_lstm(self):
num_row = 3
num_col = 3
filters = 2
num_samples = 1
input_channel = 2
input_num_row = 5
input_num_col = 5
sequence_len = 2
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, sequence_len,
input_channel,
input_num_row, input_num_col)
else:
inputs = np.random.rand(num_samples, sequence_len,
input_num_row, input_num_col,
input_channel)
for return_sequences in [True, False]:
with self.test_session():
# test for return state:
x = keras.Input(batch_shape=inputs.shape)
kwargs = {'data_format': data_format,
'return_sequences': return_sequences,
'return_state': True,
'stateful': True,
'filters': filters,
'kernel_size': (num_row, num_col),
'padding': 'valid'}
layer = keras.layers.ConvLSTM2D(**kwargs)
layer.build(inputs.shape)
outputs = layer(x)
_, states = outputs[0], outputs[1:]
self.assertEqual(len(states), 2)
model = keras.models.Model(x, states[0])
state = model.predict(inputs)
self.assertAllClose(
keras.backend.eval(layer.states[0]), state, atol=1e-4)
# test for output shape:
testing_utils.layer_test(
keras.layers.ConvLSTM2D,
kwargs={'data_format': data_format,
'return_sequences': return_sequences,
'filters': filters,
'kernel_size': (num_row, num_col),
'padding': 'valid'},
input_shape=inputs.shape)
def _run_test(self, kwargs, arg, values):
num_samples = 2
stack_size = 3
num_row = 7
num_col = 6
test_kwargs = copy.copy(kwargs)
for value in values:
test_kwargs[arg] = value
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.DepthwiseConv2D,
kwargs=test_kwargs,
input_shape=(num_samples, num_row, num_col, stack_size))
def test_upsampling_2d(self):
num_samples = 2
stack_size = 2
input_num_row = 11
input_num_col = 12
for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size, input_num_row,
input_num_col)
else:
inputs = np.random.rand(num_samples, input_num_row, input_num_col,
stack_size)
# basic test
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.UpSampling2D,
kwargs={'size': (2, 2),
'data_format': data_format},
input_shape=inputs.shape)
for length_row in [2]:
for length_col in [2, 3]:
layer = keras.layers.UpSampling2D(
size=(length_row, length_col), data_format=data_format)
layer.build(inputs.shape)
output = layer(keras.backend.variable(inputs))
if context.in_eager_mode():
np_output = output.numpy()
else:
np_output = keras.backend.eval(output)
if data_format == 'channels_first':
assert np_output.shape[2] == length_row * input_num_row
assert np_output.shape[3] == length_col * input_num_col
else: # tf
assert np_output.shape[1] == length_row * input_num_row
assert np_output.shape[2] == length_col * input_num_col
# compare with numpy
if data_format == 'channels_first':
expected_out = np.repeat(inputs, length_row, axis=2)
expected_out = np.repeat(expected_out, length_col, axis=3)
else: # tf
expected_out = np.repeat(inputs, length_row, axis=1)
expected_out = np.repeat(expected_out, length_col, axis=2)
np.testing.assert_allclose(np_output, expected_out)
def test_dropout(self):
with self.test_session():
testing_utils.layer_test(
keras.layers.Dropout, kwargs={'rate': 0.5}, input_shape=(3, 2))
with self.test_session():
testing_utils.layer_test(
keras.layers.Dropout,
kwargs={'rate': 0.5,
'noise_shape': [3, 1]},
input_shape=(3, 2))
# https://github.com/tensorflow/tensorflow/issues/14819
with self.test_session():
dropout = keras.layers.Dropout(0.5)
self.assertEqual(True, dropout.supports_masking)
def test_locallyconnected_2d_channels_first(self):
num_samples = 8
filters = 3
stack_size = 4
num_row = 6
num_col = 10
with self.test_session():
testing_utils.layer_test(
keras.layers.LocallyConnected2D,
kwargs={
'filters': filters,
'kernel_size': 3,
'data_format': 'channels_first'
},
input_shape=(num_samples, num_row, num_col, stack_size))
def test_averagepooling_3d(self):
pool_size = (3, 3, 3)
testing_utils.layer_test(
keras.layers.AveragePooling3D,
kwargs={'strides': 2,
'padding': 'valid',
'pool_size': pool_size},
input_shape=(3, 11, 12, 10, 4))
testing_utils.layer_test(
keras.layers.AveragePooling3D,
kwargs={
'strides': 3,
'padding': 'valid',
'data_format': 'channels_first',
'pool_size': pool_size
},
input_shape=(3, 4, 11, 12, 10))
def test_cropping_1d(self):
num_samples = 2
time_length = 4
input_len_dim1 = 2
inputs = np.random.rand(num_samples, time_length, input_len_dim1)
with self.test_session(use_gpu=True):
testing_utils.layer_test(
keras.layers.Cropping1D,
kwargs={'cropping': (2, 2)},
input_shape=inputs.shape)
# test incorrect use
with self.assertRaises(ValueError):
keras.layers.Cropping1D(cropping=(1, 1, 1))
with self.assertRaises(ValueError):
keras.layers.Cropping1D(cropping=None)
