def test_zero_padding_1d():
num_samples = 2
input_dim = 2
num_steps = 5
shape = (num_samples, num_steps, input_dim)
inputs = np.ones(shape)
# basic test
layer_test(convolutional.ZeroPadding1D,
kwargs={'padding': 2},
input_shape=inputs.shape)
layer_test(convolutional.ZeroPadding1D,
kwargs={'padding': (1, 2)},
input_shape=inputs.shape)
# correctness test
layer = convolutional.ZeroPadding1D(padding=2)
layer.build(shape)
outputs = layer(K.variable(inputs))
np_output = K.eval(outputs)
for offset in [0, 1, -1, -2]:
assert_allclose(np_output[:, offset, :], 0.)
assert_allclose(np_output[:, 2:-2, :], 1.)
layer = convolutional.ZeroPadding1D(padding=(1, 2))
layer.build(shape)
outputs = layer(K.variable(inputs))
np_output = K.eval(outputs)
for left_offset in [0]:
assert_allclose(np_output[:, left_offset, :], 0.)
for right_offset in [-1, -2]:
assert_allclose(np_output[:, right_offset, :], 0.)
assert_allclose(np_output[:, 1:-2, :], 1.)
layer.get_config()
def test_zero_padding_1d():
nb_samples = 2
input_dim = 2
nb_steps = 5
input = np.ones((nb_samples, nb_steps, input_dim))
# basic test
layer_test(convolutional.ZeroPadding1D,
kwargs={'padding': 2},
input_shape=input.shape)
layer_test(convolutional.ZeroPadding1D,
kwargs={'padding': (1, 2)},
input_shape=input.shape)
layer_test(convolutional.ZeroPadding1D,
kwargs={'padding': {
'left_pad': 1,
'right_pad': 2
}},
input_shape=input.shape)
# correctness test
layer = convolutional.ZeroPadding1D(padding=2)
layer.set_input(K.variable(input), shape=input.shape)
out = K.eval(layer.output)
for offset in [0, 1, -1, -2]:
assert_allclose(out[:, offset, :], 0.)
assert_allclose(out[:, 2:-2, :], 1.)
layer = convolutional.ZeroPadding1D(padding=(1, 2))
layer.set_input(K.variable(input), shape=input.shape)
out = K.eval(layer.output)
for left_offset in [0]:
assert_allclose(out[:, left_offset, :], 0.)
for right_offset in [-1, -2]:
assert_allclose(out[:, right_offset, :], 0.)
assert_allclose(out[:, 1:-2, :], 1.)
layer.get_config()
