def test_gradient(self):
val = np.random.random((4, 2))
xth = KTH.variable(val)
xtf = KTF.variable(val)
expth = xth * KTH.exp(xth)
exptf = xtf * KTF.exp(xtf)
lossth = KTH.sum(expth)
losstf = KTF.sum(exptf)
zero_lossth = KTH.stop_gradient(lossth)
zero_losstf = KTF.stop_gradient(losstf)
gradth = KTH.gradients(lossth, [expth])
gradtf = KTF.gradients(losstf, [exptf])
zero_gradth = KTH.gradients(lossth + zero_lossth, [expth])
zero_gradtf = KTF.gradients(losstf + zero_losstf, [exptf])
zth = KTH.eval(gradth[0])
ztf = KTF.eval(gradtf[0])
zero_zth = KTH.eval(zero_gradth[0])
zero_ztf = KTF.eval(zero_gradtf[0])
assert zth.shape == ztf.shape
assert zero_zth.shape == zero_ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
assert_allclose(zero_zth, zero_ztf, atol=1e-05)
assert_allclose(zero_zth, zth, atol=1e-05)
assert_allclose(zero_ztf, ztf, atol=1e-05)
def test_ctc_decode_greedy(self):
# Test adapted from tensorflow
"""Test two batch entries - best path decoder."""
max_time_steps = 6
seq_len_0 = 4
input_prob_matrix_0 = np.asarray(
[
[1.0, 0.0, 0.0, 0.0], # t=0
[0.0, 0.0, 0.4, 0.6], # t=1
[0.0, 0.0, 0.4, 0.6], # t=2
[0.0, 0.9, 0.1, 0.0], # t=3
[0.0, 0.0, 0.0, 0.0], # t=4 (ignored)
[0.0, 0.0, 0.0, 0.0],
], # t=5 (ignored)
dtype=np.float32,
)
input_log_prob_matrix_0 = np.log(input_prob_matrix_0)
seq_len_1 = 5
# dimensions are time x depth
input_prob_matrix_1 = np.asarray(
[
[0.1, 0.9, 0.0, 0.0], # t=0
[0.0, 0.9, 0.1, 0.0], # t=1
[0.0, 0.0, 0.1, 0.9], # t=2
[0.0, 0.9, 0.1, 0.1], # t=3
[0.9, 0.1, 0.0, 0.0], # t=4
[0.0, 0.0, 0.0, 0.0],
], # t=5 (ignored)
dtype=np.float32,
)
# len max_time_steps array of batch_size x depth matrices
inputs = [np.vstack([input_prob_matrix_0[t, :], input_prob_matrix_1[t, :]]) for t in range(max_time_steps)]
# change tensorflow order to keras backend order
inputs = KTF.variable(np.asarray(inputs).transpose((1, 0, 2)))
# batch_size length vector of sequence_lengths
input_length = KTF.variable(np.array([seq_len_0, seq_len_1], dtype=np.int32))
# batch_size length vector of negative log probabilities
log_prob_truth = np.array(
[np.sum(-np.log([1.0, 0.6, 0.6, 0.9])), np.sum(-np.log([0.9, 0.9, 0.9, 0.9, 0.9]))], np.float32
)[:, np.newaxis]
# keras output, unlike tensorflow, is a dense (not sparse) tensor
decode_truth = np.array([[0, 1, -1], [1, 1, 0]])
decode_pred_tf, log_prob_pred_tf = KTF.ctc_decode(inputs, input_length, greedy=True)
assert len(decode_pred_tf) == 1
decode_pred = KTF.eval(decode_pred_tf[0])
log_prob_pred = KTF.eval(log_prob_pred_tf)
assert np.alltrue(decode_truth == decode_pred)
assert np.allclose(log_prob_truth, log_prob_pred)
def test_ctc_decode_beam_search(self):
"""Test one batch, two beams - hibernating beam search."""
depth = 6
seq_len_0 = 5
input_prob_matrix_0 = np.asarray(
[[0.30999, 0.309938, 0.0679938, 0.0673362, 0.0708352, 0.173908],
[0.215136, 0.439699, 0.0370931, 0.0393967, 0.0381581, 0.230517],
[0.199959, 0.489485, 0.0233221, 0.0251417, 0.0233289, 0.238763],
[0.279611, 0.452966, 0.0204795, 0.0209126, 0.0194803, 0.20655],
[0.51286, 0.288951, 0.0243026, 0.0220788, 0.0219297, 0.129878],
# Random entry added in at time=5
[0.155251, 0.164444, 0.173517, 0.176138, 0.169979, 0.160671]],
dtype=np.float32)
# len max_time_steps array of batch_size x depth matrices
inputs = ([input_prob_matrix_0[t, :][np.newaxis, :]
for t in range(seq_len_0)] + # Pad to max_time_steps = 8
2 * [np.zeros((1, depth), dtype=np.float32)])
inputs = KTF.variable(np.asarray(inputs).transpose((1, 0, 2)))
# batch_size length vector of sequence_lengths
input_length = KTF.variable(np.array([seq_len_0], dtype=np.int32))
# batch_size length vector of negative log probabilities
log_prob_truth = np.array([
0.584855, # output beam 0
0.389139 # output beam 1
], np.float32)[np.newaxis, :]
decode_truth = [np.array([1, 0]), np.array([0, 1, 0])]
beam_width = 2
top_paths = 2
decode_pred_tf, log_prob_pred_tf = KTF.ctc_decode(inputs,
input_length,
greedy=False,
beam_width=beam_width,
top_paths=top_paths)
assert len(decode_pred_tf) == top_paths
log_prob_pred = KTF.eval(log_prob_pred_tf)
for i in range(top_paths):
assert np.alltrue(decode_truth[i] == KTF.eval(decode_pred_tf[i]))
assert np.allclose(log_prob_truth, log_prob_pred)
def test_batch_dot_shape(self):
x_batch = KTF.ones(shape=(32, 20))
y_batch = KTF.ones(shape=(32, 20))
xy_batch_dot = KTF.batch_dot(x_batch, y_batch, axes=1)
assert_allclose(KTF.eval(xy_batch_dot), np.ones((32, 1)) * 20, atol=1e-05)
xy_batch_dot = KTF.batch_dot(x_batch, y_batch, axes=0)
assert_allclose(KTF.eval(xy_batch_dot), np.ones((20, 1)) * 32, atol=1e-05)
# making sure swapping axes when ndim == 2 works
x_batch = KTF.ones(shape=(32, 20))
y_batch = KTF.ones(shape=(20, 32))
xy_batch_dot = KTF.batch_dot(x_batch, y_batch, axes=(0, 1))
assert_allclose(KTF.eval(xy_batch_dot), np.ones((20, 1)) * 32, atol=1e-05)
xy_batch_dot = KTF.batch_dot(x_batch, y_batch, axes=(1, 0))
assert_allclose(KTF.eval(xy_batch_dot), np.ones((32, 1)) * 20, atol=1e-05)
def test_rnn(self):
# implement a simple RNN
input_dim = 8
output_dim = 4
timesteps = 5
input_val = np.random.random((32, timesteps, input_dim))
init_state_val = np.random.random((32, output_dim))
W_i_val = np.random.random((input_dim, output_dim))
W_o_val = np.random.random((output_dim, output_dim))
def rnn_step_fn(input_dim, output_dim, K):
W_i = K.variable(W_i_val)
W_o = K.variable(W_o_val)
def step_function(x, states):
assert len(states) == 1
prev_output = states[0]
output = K.dot(x, W_i) + K.dot(prev_output, W_o)
return output, [output]
return step_function
th_rnn_step_fn = rnn_step_fn(input_dim, output_dim, KTH)
inputs = KTH.variable(input_val)
initial_states = [KTH.variable(init_state_val)]
last_output, outputs, new_states = KTH.rnn(th_rnn_step_fn, inputs,
initial_states,
go_backwards=False,
masking=False)
th_last_output = KTH.eval(last_output)
th_outputs = KTH.eval(outputs)
assert len(new_states) == 1
th_state = KTH.eval(new_states[0])
tf_rnn_step_fn = rnn_step_fn(input_dim, output_dim, KTF)
inputs = KTF.variable(input_val)
initial_states = [KTF.variable(init_state_val)]
last_output, outputs, new_states = KTF.rnn(tf_rnn_step_fn, inputs,
initial_states,
go_backwards=False,
masking=False)
tf_last_output = KTF.eval(last_output)
tf_outputs = KTF.eval(outputs)
assert len(new_states) == 1
tf_state = KTF.eval(new_states[0])
assert_allclose(tf_last_output, th_last_output, atol=1e-04)
assert_allclose(tf_outputs, th_outputs, atol=1e-04)
assert_allclose(tf_state, th_state, atol=1e-04)
def test_shape_operations(self):
# concatenate
xval = np.random.random((4, 3))
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
yval = np.random.random((4, 2))
yth = KTH.variable(yval)
ytf = KTF.variable(yval)
zth = KTH.eval(KTH.concatenate([xth, yth], axis=-1))
ztf = KTF.eval(KTF.concatenate([xtf, ytf], axis=-1))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
check_single_tensor_operation('reshape', (4, 2), shape=(8, 1))
check_single_tensor_operation('permute_dimensions', (4, 2, 3),
pattern=(2, 0, 1))
check_single_tensor_operation('repeat', (4, 1), n=3)
check_single_tensor_operation('flatten', (4, 1))
check_single_tensor_operation('expand_dims', (4, 3), dim=-1)
check_single_tensor_operation('expand_dims', (4, 3, 2), dim=1)
check_single_tensor_operation('squeeze', (4, 3, 1), axis=2)
check_single_tensor_operation('squeeze', (4, 1, 1), axis=1)
check_composed_tensor_operations('reshape', {'shape': (4, 3, 1, 1)},
'squeeze', {'axis': 2},
(4, 3, 1, 1))
def test_nn_operations(self):
check_single_tensor_operation('relu', (4, 2), alpha=0.1, max_value=0.5)
check_single_tensor_operation('softmax', (4, 10))
check_single_tensor_operation('softplus', (4, 10))
check_single_tensor_operation('sigmoid', (4, 2))
check_single_tensor_operation('hard_sigmoid', (4, 2))
check_single_tensor_operation('tanh', (4, 2))
# dropout
val = np.random.random((100, 100))
xth = KTH.variable(val)
xtf = KTF.variable(val)
zth = KTH.eval(KTH.dropout(xth, level=0.2))
ztf = KTF.eval(KTF.dropout(xtf, level=0.2))
assert zth.shape == ztf.shape
# dropout patterns are different, only check mean
assert np.abs(zth.mean() - ztf.mean()) < 0.05
check_two_tensor_operation('binary_crossentropy', (4, 2), (4, 2),
from_logits=True)
check_two_tensor_operation('categorical_crossentropy', (4, 2), (4, 2),
from_logits=True)
check_two_tensor_operation('binary_crossentropy', (4, 2), (4, 2),
from_logits=False)
check_two_tensor_operation('categorical_crossentropy', (4, 2), (4, 2),
from_logits=False)
check_single_tensor_operation('l2_normalize', (4, 3), axis=-1)
check_single_tensor_operation('l2_normalize', (4, 3), axis=1)
def reset_states(self, states_value=None):
if len(self.states) == 0:
return
if not self.stateful:
raise AttributeError('Layer must be stateful.')
if not hasattr(self, 'states') or self.states[0] is None:
state_shapes = list(map(K.int_shape, self.model.input[1:]))
self.states = list(map(K.zeros, state_shapes))
if states_value is not None:
if type(states_value) not in (list, tuple):
states_value = [states_value] * len(self.states)
assert len(states_value) == len(
self.states), 'Your RNN has ' + str(len(
self.states)) + ' states, but was provided ' + str(
len(states_value)) + ' state values.'
if 'numpy' not in type(states_value[0]):
states_value = list(map(np.array, states_value))
if states_value[0].shape == tuple():
for state, val in zip(self.states, states_value):
K.set_value(state, K.get_value(state) * 0. + val)
else:
for state, val in zip(self.states, states_value):
K.set_value(state, val)
else:
if self.state_initializer:
for state, init in zip(self.states, self.state_initializer):
if isinstance(init, initializers.Zeros):
K.set_value(state, 0 * K.get_value(state))
else:
K.set_value(state,
K.eval(init(K.get_value(state).shape)))
else:
for state in self.states:
K.set_value(state, 0 * K.get_value(state))
def test_gather(self):
shape = (10, 2, 3)
ref = np.arange(np.prod(shape)).reshape(shape)
ref_th = KTH.variable(ref)
ref_tf = KTF.variable(ref)
inds = [1, 3, 7, 9]
inds_th = KTH.variable(inds, dtype='int32')
inds_tf = KTF.variable(inds, dtype='int32')
th_z = KTH.gather(ref_th, inds_th)
th_result = KTH.eval(th_z)
tf_result = KTF.eval(KTF.gather(ref_tf, inds_tf))
assert_allclose(tf_result, th_result, atol=1e-05)
if hasattr(th_z, '_keras_shape'):
assert th_z._keras_shape == th_result.shape
# test theano shape inference when
# input shape has None entries
if K.backend() == 'theano':
x = K.placeholder(shape=(None, 3, 4))
indices = K.placeholder(shape=(5, 6), dtype='int32')
y = K.gather(x, indices)
assert y._keras_shape == (5, 6, 3, 4)
def test_repeat_elements(self):
reps = 3
for ndims in [1, 2, 3]:
shape = np.arange(2, 2 + ndims)
arr = np.arange(np.prod(shape)).reshape(shape)
arr_th = KTH.variable(arr)
arr_tf = KTF.variable(arr)
for rep_axis in range(ndims):
np_rep = np.repeat(arr, reps, axis=rep_axis)
th_z = KTH.repeat_elements(arr_th, reps, axis=rep_axis)
th_rep = KTH.eval(th_z)
tf_rep = KTF.eval(
KTF.repeat_elements(arr_tf, reps, axis=rep_axis))
assert th_rep.shape == np_rep.shape
assert tf_rep.shape == np_rep.shape
assert_allclose(np_rep, th_rep, atol=1e-05)
assert_allclose(np_rep, tf_rep, atol=1e-05)
if hasattr(th_z, '_keras_shape'):
assert th_z._keras_shape == th_rep.shape
# test theano shape inference when
# input shape has None entries
if K.backend() == 'theano':
shape = list(shape)
shape[rep_axis] = None
x = K.placeholder(shape=shape)
y = K.repeat_elements(x, reps, axis=rep_axis)
assert y._keras_shape == tuple(shape)
def test_repeat_elements(self):
reps = 3
for ndims in [1, 2, 3]:
shape = np.arange(2, 2 + ndims)
arr = np.arange(np.prod(shape)).reshape(shape)
arr_th = KTH.variable(arr)
arr_tf = KTF.variable(arr)
for rep_axis in range(ndims):
np_rep = np.repeat(arr, reps, axis=rep_axis)
th_z = KTH.repeat_elements(arr_th, reps, axis=rep_axis)
th_rep = KTH.eval(th_z)
tf_rep = KTF.eval(
KTF.repeat_elements(arr_tf, reps, axis=rep_axis))
assert th_rep.shape == np_rep.shape
assert tf_rep.shape == np_rep.shape
assert_allclose(np_rep, th_rep, atol=1e-05)
assert_allclose(np_rep, tf_rep, atol=1e-05)
if hasattr(th_z, '_keras_shape'):
assert th_z._keras_shape == th_rep.shape
# test theano shape inference when
# input shape has None entries
if K.backend() == 'theano':
shape = list(shape)
shape[rep_axis] = None
x = K.placeholder(shape=shape)
y = K.repeat_elements(x, reps, axis=rep_axis)
assert y._keras_shape == tuple(shape)
def test_depth_to_space(self, batch_size, scale, channels, rows, cols):
if K.image_data_format() == 'channels_first':
arr = np.arange(batch_size * channels * scale * scale * rows * cols)\
.reshape((batch_size, channels * scale * scale, rows, cols))
elif K.image_data_format() == 'channels_last':
arr = np.arange(batch_size * rows * cols * scale * scale * channels) \
.reshape((batch_size, rows, cols, channels * scale * scale))
arr_tf = KTF.variable(arr)
arr_th = KTH.variable(arr)
if K.image_data_format() == 'channels_first':
expected = arr.reshape((batch_size, scale, scale, channels, rows, cols))\
.transpose((0, 3, 4, 1, 5, 2))\
.reshape((batch_size, channels, rows * scale, cols * scale))
elif K.image_data_format() == 'channels_last':
expected = arr.reshape((batch_size, rows, cols, scale, scale, channels))\
.transpose((0, 1, 3, 2, 4, 5))\
.reshape((batch_size, rows * scale, cols * scale, channels))
tf_ans = KTF.eval(KCTF.depth_to_space(arr_tf, scale))
th_ans = KTH.eval(KCTH.depth_to_space(arr_th, scale))
assert tf_ans.shape == expected.shape
assert th_ans.shape == expected.shape
assert_allclose(expected, tf_ans, atol=1e-05)
assert_allclose(expected, th_ans, atol=1e-05)
def binary_loss(y_true, y_pred, labels):
y_p = to_categorical(y_pred, labels)
y_t = to_categorical(y_true, labels)
y_pred = tf.convert_to_tensor(y_p)
y_true = tf.convert_to_tensor(y_t)
loss = binary_crossentropy(y_true, y_pred)
return K.eval(loss)
def check_composed_tensor_operations(
first_function_name,
first_function_args,
second_function_name,
second_function_args,
input_shape,
):
""" Creates a random tensor t0 with shape input_shape and compute
t1 = first_function_name(t0, **first_function_args)
t2 = second_function_name(t1, **second_function_args)
with both Theano and TensorFlow backends and ensures the answers match.
"""
val = np.random.random(input_shape) - 0.5
xth = KTH.variable(val)
xtf = KTF.variable(val)
yth = getattr(KCTH, first_function_name)(xth, **first_function_args)
ytf = getattr(KCTF, first_function_name)(xtf, **first_function_args)
zth = KTH.eval(
getattr(KCTH, second_function_name)(yth, **second_function_args))
ztf = KTF.eval(
getattr(KCTF, second_function_name)(ytf, **second_function_args))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_nn_operations(self):
check_single_tensor_operation('relu', (4, 2), alpha=0.1, max_value=0.5)
check_single_tensor_operation('softmax', (4, 10))
check_single_tensor_operation('softplus', (4, 10))
check_single_tensor_operation('sigmoid', (4, 2))
check_single_tensor_operation('hard_sigmoid', (4, 2))
check_single_tensor_operation('tanh', (4, 2))
# dropout
val = np.random.random((100, 100))
xth = KTH.variable(val)
xtf = KTF.variable(val)
zth = KTH.eval(KTH.dropout(xth, level=0.2))
ztf = KTF.eval(KTF.dropout(xtf, level=0.2))
assert zth.shape == ztf.shape
# dropout patterns are different, only check mean
assert np.abs(zth.mean() - ztf.mean()) < 0.05
check_two_tensor_operation('binary_crossentropy', (4, 2), (4, 2), from_logits=True)
check_two_tensor_operation('categorical_crossentropy', (4, 2), (4, 2), from_logits=True)
check_two_tensor_operation('binary_crossentropy', (4, 2), (4, 2), from_logits=False)
check_two_tensor_operation('categorical_crossentropy', (4, 2), (4, 2), from_logits=False)
check_single_tensor_operation('l2_normalize', (4, 3), axis=-1)
check_single_tensor_operation('l2_normalize', (4, 3), axis=1)
def test_gather(self):
shape = (10, 2, 3)
ref = np.arange(np.prod(shape)).reshape(shape)
ref_th = KTH.variable(ref)
ref_tf = KTF.variable(ref)
inds = [1, 3, 7, 9]
inds_th = KTH.variable(inds, dtype='int32')
inds_tf = KTF.variable(inds, dtype='int32')
th_z = KTH.gather(ref_th, inds_th)
th_result = KTH.eval(th_z)
tf_result = KTF.eval(KTF.gather(ref_tf, inds_tf))
assert_allclose(tf_result, th_result, atol=1e-05)
if hasattr(th_z, '_keras_shape'):
assert th_z._keras_shape == th_result.shape
# test theano shape inference when
# input shape has None entries
if K.backend() == 'theano':
x = K.placeholder(shape=(None, 3, 4))
indices = K.placeholder(shape=(5, 6), dtype='int32')
y = K.gather(x, indices)
assert y._keras_shape == (5, 6, 3, 4)
def test_shape_operations(self):
# concatenate
xval = np.random.random((4, 3))
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
yval = np.random.random((4, 2))
yth = KTH.variable(yval)
ytf = KTF.variable(yval)
zth = KTH.eval(KTH.concatenate([xth, yth], axis=-1))
ztf = KTF.eval(KTF.concatenate([xtf, ytf], axis=-1))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
check_single_tensor_operation('reshape', (4, 2), shape=(8, 1))
check_single_tensor_operation('permute_dimensions', (4, 2, 3),
pattern=(2, 0, 1))
check_single_tensor_operation('repeat', (4, 1), n=3)
check_single_tensor_operation('flatten', (4, 1))
check_single_tensor_operation('expand_dims', (4, 3), dim=-1)
check_single_tensor_operation('expand_dims', (4, 3, 2), dim=1)
check_single_tensor_operation('squeeze', (4, 3, 1), axis=2)
check_single_tensor_operation('squeeze', (4, 1, 1), axis=1)
check_composed_tensor_operations('reshape', {'shape': (4, 3, 1, 1)},
'squeeze', {'axis': 2},
(4, 3, 1, 1))
def test_conv2d(self):
# TF kernel shape: (rows, cols, input_depth, depth)
# channels_first input shape: (n, input_depth, rows, cols)
for input_shape in [(2, 3, 4, 5), (2, 3, 5, 6)]:
for kernel_shape in [(2, 2, 3, 4), (4, 3, 3, 4)]:
for padding in ['valid', 'same']:
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(
KTH.conv2d(xth,
kernel_th,
data_format='channels_first'))
ztf = KTF.eval(
KTF.conv2d(xtf,
kernel_tf,
data_format='channels_first'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
input_shape = (1, 6, 5, 3)
kernel_shape = (3, 3, 3, 2)
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv2d(xth, kernel_th, data_format='channels_last'))
ztf = KTF.eval(KTF.conv2d(xtf, kernel_tf, data_format='channels_last'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_rnn_no_states(self):
# implement a simple RNN without states
input_dim = 8
output_dim = 4
timesteps = 5
input_val = np.random.random((32, timesteps, input_dim))
W_i_val = np.random.random((input_dim, output_dim))
def rnn_step_fn(input_dim, output_dim, K):
W_i = K.variable(W_i_val)
def step_function(x, states):
assert len(states) == 0
output = K.dot(x, W_i)
return output, []
return step_function
# test default setup
th_rnn_step_fn = rnn_step_fn(input_dim, output_dim, KTH)
th_inputs = KTH.variable(input_val)
th_initial_states = []
last_output, outputs, new_states = KTH.rnn(th_rnn_step_fn,
th_inputs,
th_initial_states,
go_backwards=False,
mask=None)
th_last_output = KTH.eval(last_output)
th_outputs = KTH.eval(outputs)
assert len(new_states) == 0
tf_rnn_step_fn = rnn_step_fn(input_dim, output_dim, KTF)
tf_inputs = KTF.variable(input_val)
tf_initial_states = []
last_output, outputs, new_states = KTF.rnn(tf_rnn_step_fn,
tf_inputs,
tf_initial_states,
go_backwards=False,
mask=None)
tf_last_output = KTF.eval(last_output)
tf_outputs = KTF.eval(outputs)
assert len(new_states) == 0
assert_allclose(tf_last_output, th_last_output, atol=1e-04)
assert_allclose(tf_outputs, th_outputs, atol=1e-04)
def test_conv3d(self):
# TH input shape: (samples, input_depth, conv_dim1, conv_dim2, conv_dim3)
# TF input shape: (samples, conv_dim1, conv_dim2, conv_dim3, input_depth)
# TH kernel shape: (depth, input_depth, x, y, z)
# TF kernel shape: (x, y, z, input_depth, depth)
# test in data_format = channels_first
for input_shape in [(2, 3, 4, 5, 4), (2, 3, 5, 4, 6)]:
for kernel_shape in [(2, 2, 2, 3, 4), (3, 2, 4, 3, 4)]:
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(
KTH.conv3d(xth, kernel_th, data_format='channels_first'))
ztf = KTF.eval(
KTF.conv3d(xtf, kernel_tf, data_format='channels_first'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
# test in data_format = channels_last
input_shape = (1, 2, 2, 2, 1)
kernel_shape = (2, 2, 2, 1, 1)
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv3d(xth, kernel_th, data_format='channels_last'))
ztf = KTF.eval(KTF.conv3d(xtf, kernel_tf, data_format='channels_last'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_extract(self):
for input_shape in [(1, 3, 40, 40), (1, 3, 10, 10)]:
for kernel_shape in [2, 5]:
xval = np.random.random(input_shape)
kernel = [kernel_shape, kernel_shape]
strides = [kernel_shape, kernel_shape]
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
ztf = KTF.eval(
KCTF.extract_image_patches(xtf,
kernel,
strides,
dim_ordering='th',
border_mode="valid"))
zth = KTH.eval(
KCTH.extract_image_patches(xth,
kernel,
strides,
dim_ordering='th',
border_mode="valid"))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-02)
for input_shape in [(1, 40, 40, 3), (1, 10, 10, 3)]:
for kernel_shape in [2, 5]:
xval = np.random.random(input_shape)
kernel = [kernel_shape, kernel_shape]
strides = [kernel_shape, kernel_shape]
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
ztf = KTF.eval(
KCTF.extract_image_patches(xtf,
kernel,
strides,
dim_ordering='tf',
border_mode="same"))
zth = KTH.eval(
KCTH.extract_image_patches(xth,
kernel,
strides,
dim_ordering='tf',
border_mode="same"))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-02)
def test_extract(self):
for input_shape in [(1, 3, 40, 40), (1, 3, 10, 10)]:
for kernel_shape in [2, 5]:
xval = np.random.random(input_shape)
kernel = [kernel_shape, kernel_shape]
strides = [kernel_shape, kernel_shape]
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
ztf = KTF.eval(
KCTF.extract_image_patches(xtf,
kernel,
strides,
data_format='channels_first',
padding='valid'))
zth = KTH.eval(
KCTH.extract_image_patches(xth,
kernel,
strides,
data_format='channels_first',
padding='valid'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-02)
for input_shape in [(1, 40, 40, 3), (1, 10, 10, 3)]:
for kernel_shape in [2, 5]:
xval = np.random.random(input_shape)
kernel = [kernel_shape, kernel_shape]
strides = [kernel_shape, kernel_shape]
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
ztf = KTF.eval(
KCTF.extract_image_patches(xtf,
kernel,
strides,
data_format='channels_last',
padding='same'))
zth = KTH.eval(
KCTH.extract_image_patches(xth,
kernel,
strides,
data_format='channels_last',
padding='same'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-02)
def test_in_top_k(self):
batch_size = 20
num_classes = 10
# Random prediction test case
predictions = np.random.random(
(batch_size, num_classes)).astype('float32')
targets = np.random.randint(num_classes,
size=batch_size,
dtype='int32')
predictions_th = KTH.variable(predictions, dtype='float32')
targets_th = KTH.variable(targets, dtype='int32')
predictions_tf = KTF.variable(predictions, dtype='float32')
targets_tf = KTF.variable(targets, dtype='int32')
for k in range(1, num_classes + 1):
res_th = KTH.eval(KTH.in_top_k(predictions_th, targets_th, k))
res_tf = KTF.eval(KTF.in_top_k(predictions_tf, targets_tf, k))
assert res_th.shape == res_tf.shape
assert_allclose(res_th, res_tf, atol=1e-05)
# Identical prediction test case:
# randomly set half of the predictions to an identical value
num_identical = num_classes // 2
for i in range(batch_size):
idx_identical = np.random.choice(num_classes,
size=num_identical,
replace=False)
predictions[i, idx_identical] = predictions[i, 0]
targets = np.zeros(batch_size, dtype='int32')
predictions_th = KTH.variable(predictions, dtype='float32')
targets_th = KTH.variable(targets, dtype='int32')
predictions_tf = KTF.variable(predictions, dtype='float32')
targets_tf = KTF.variable(targets, dtype='int32')
for k in range(1, num_classes + 1):
res_th = KTH.eval(KTH.in_top_k(predictions_th, targets_th, k))
res_tf = KTF.eval(KTF.in_top_k(predictions_tf, targets_tf, k))
assert res_th.shape == res_tf.shape
assert_allclose(res_th, res_tf, atol=1e-05)
def test_conv3d(self):
# TH input shape: (samples, input_depth, conv_dim1, conv_dim2, conv_dim3)
# TF input shape: (samples, conv_dim1, conv_dim2, conv_dim3, input_depth)
# TH kernel shape: (depth, input_depth, x, y, z)
# TF kernel shape: (x, y, z, input_depth, depth)
# test in dim_ordering = th
for input_shape in [(2, 3, 4, 5, 4), (2, 3, 5, 4, 6)]:
for kernel_shape in [(4, 3, 2, 2, 2), (4, 3, 3, 2, 4)]:
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv3d(xth, kernel_th))
ztf = KTF.eval(KTF.conv3d(xtf, kernel_tf))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
# test in dim_ordering = tf
input_shape = (1, 2, 2, 2, 1)
kernel_shape = (2, 2, 2, 1, 1)
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val, dim_ordering='tf'))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv3d(xth, kernel_th, dim_ordering='tf'))
ztf = KTF.eval(KTF.conv3d(xtf, kernel_tf, dim_ordering='tf'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_ctc(self):
# simplified version of TensorFlow's test
label_lens = np.expand_dims(np.asarray([5, 4]), 1)
input_lens = np.expand_dims(np.asarray([5, 5]),
1) # number of timesteps
# the Theano and Tensorflow CTC code use different methods to ensure
# numerical stability. The Theano code subtracts out the max
# before the final log, so the results are different but scale
# identically and still train properly
loss_log_probs_tf = [3.34211, 5.42262]
loss_log_probs_th = [1.73308, 3.81351]
# dimensions are batch x time x categories
labels = np.asarray([[0, 1, 2, 1, 0], [0, 1, 1, 0, -1]])
inputs = np.asarray(
[[[0.633766, 0.221185, 0.0917319, 0.0129757, 0.0142857, 0.0260553],
[0.111121, 0.588392, 0.278779, 0.0055756, 0.00569609, 0.010436],
[
0.0357786, 0.633813, 0.321418, 0.00249248, 0.00272882,
0.0037688
],
[
0.0663296, 0.643849, 0.280111, 0.00283995, 0.0035545,
0.00331533
],
[
0.458235, 0.396634, 0.123377, 0.00648837, 0.00903441,
0.00623107
]],
[[0.30176, 0.28562, 0.0831517, 0.0862751, 0.0816851, 0.161508],
[0.24082, 0.397533, 0.0557226, 0.0546814, 0.0557528, 0.19549],
[0.230246, 0.450868, 0.0389607, 0.038309, 0.0391602, 0.202456],
[0.280884, 0.429522, 0.0326593, 0.0339046, 0.0326856, 0.190345],
[0.423286, 0.315517, 0.0338439, 0.0393744, 0.0339315, 0.154046]]
],
dtype=np.float32)
labels_tf = KTF.variable(labels, dtype="int32")
inputs_tf = KTF.variable(inputs, dtype="float32")
input_lens_tf = KTF.variable(input_lens, dtype="int32")
label_lens_tf = KTF.variable(label_lens, dtype="int32")
res = KTF.eval(
KTF.ctc_batch_cost(labels_tf, inputs_tf, input_lens_tf,
label_lens_tf))
assert_allclose(res[:, 0], loss_log_probs_tf, atol=1e-05)
labels_th = KTH.variable(labels, dtype="int32")
inputs_th = KTH.variable(inputs, dtype="float32")
input_lens_th = KTH.variable(input_lens, dtype="int32")
label_lens_th = KTH.variable(label_lens, dtype="int32")
res = KTH.eval(
KTH.ctc_batch_cost(labels_th, inputs_th, input_lens_th,
label_lens_th))
assert_allclose(res[0, :], loss_log_probs_th, atol=1e-05)
def check_single_tensor_operation(function_name, input_shape, **kwargs):
val = np.random.random(input_shape) - 0.5
xth = KTH.variable(val)
xtf = KTF.variable(val)
zth = KTH.eval(getattr(KCTH, function_name)(xth, **kwargs))
ztf = KTF.eval(getattr(KCTF, function_name)(xtf, **kwargs))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_tile(self):
shape = (3, 4)
arr = np.arange(np.prod(shape)).reshape(shape)
arr_th = KTH.variable(arr)
arr_tf = KTF.variable(arr)
n = (2, 1)
th_rep = KTH.eval(KTH.tile(arr_th, n))
tf_rep = KTF.eval(KTF.tile(arr_tf, n))
assert_allclose(tf_rep, th_rep, atol=1e-05)
def test_tile(self):
shape = (3, 4)
arr = np.arange(np.prod(shape)).reshape(shape)
arr_th = KTH.variable(arr)
arr_tf = KTF.variable(arr)
n = (2, 1)
th_rep = KTH.eval(KTH.tile(arr_th, n))
tf_rep = KTF.eval(KTF.tile(arr_tf, n))
assert_allclose(tf_rep, th_rep, atol=1e-05)
def test_rnn_no_states(self):
# implement a simple RNN without states
input_dim = 8
output_dim = 4
timesteps = 5
input_val = np.random.random((32, timesteps, input_dim))
W_i_val = np.random.random((input_dim, output_dim))
def rnn_step_fn(input_dim, output_dim, K):
W_i = K.variable(W_i_val)
def step_function(x, states):
assert len(states) == 0
output = K.dot(x, W_i)
return output, []
return step_function
# test default setup
th_rnn_step_fn = rnn_step_fn(input_dim, output_dim, KTH)
th_inputs = KTH.variable(input_val)
th_initial_states = []
last_output, outputs, new_states = KTH.rnn(th_rnn_step_fn, th_inputs,
th_initial_states,
go_backwards=False,
mask=None)
th_last_output = KTH.eval(last_output)
th_outputs = KTH.eval(outputs)
assert len(new_states) == 0
tf_rnn_step_fn = rnn_step_fn(input_dim, output_dim, KTF)
tf_inputs = KTF.variable(input_val)
tf_initial_states = []
last_output, outputs, new_states = KTF.rnn(tf_rnn_step_fn, tf_inputs,
tf_initial_states,
go_backwards=False,
mask=None)
tf_last_output = KTF.eval(last_output)
tf_outputs = KTF.eval(outputs)
assert len(new_states) == 0
assert_allclose(tf_last_output, th_last_output, atol=1e-04)
assert_allclose(tf_outputs, th_outputs, atol=1e-04)
def check_single_tensor_operation(function_name, input_shape, **kwargs):
val = np.random.random(input_shape) - 0.5
xth = KTH.variable(val)
xtf = KTF.variable(val)
zth = KTH.eval(getattr(KTH, function_name)(xth, **kwargs))
ztf = KTF.eval(getattr(KTF, function_name)(xtf, **kwargs))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_arange(self):
for test_value in (-20, 0, 1, 10):
t_a = KTF.arange(test_value)
a = KTF.eval(t_a)
assert np.array_equal(a, np.arange(test_value))
t_b = KTH.arange(test_value)
b = KTH.eval(t_b)
assert np.array_equal(b, np.arange(test_value))
assert np.array_equal(a, b)
assert KTF.dtype(t_a) == KTH.dtype(t_b)
for start, stop, step in ((0, 5, 1), (-5, 5, 2), (0, 1, 2)):
a = KTF.eval(KTF.arange(start, stop, step))
assert np.array_equal(a, np.arange(start, stop, step))
b = KTH.eval(KTH.arange(start, stop, step))
assert np.array_equal(b, np.arange(start, stop, step))
assert np.array_equal(a, b)
for dtype in ('int32', 'int64', 'float32', 'float64'):
for backend in (KTF, KTH):
t = backend.arange(10, dtype=dtype)
assert backend.dtype(t) == dtype
def test_arange(self):
for test_value in (-20, 0, 1, 10):
t_a = KTF.arange(test_value)
a = KTF.eval(t_a)
assert np.array_equal(a, np.arange(test_value))
t_b = KTH.arange(test_value)
b = KTH.eval(t_b)
assert np.array_equal(b, np.arange(test_value))
assert np.array_equal(a, b)
assert KTF.dtype(t_a) == KTH.dtype(t_b)
for start, stop, step in ((0, 5, 1), (-5, 5, 2), (0, 1, 2)):
a = KTF.eval(KTF.arange(start, stop, step))
assert np.array_equal(a, np.arange(start, stop, step))
b = KTH.eval(KTH.arange(start, stop, step))
assert np.array_equal(b, np.arange(start, stop, step))
assert np.array_equal(a, b)
for dtype in ('int32', 'int64', 'float32', 'float64'):
for backend in (KTF, KTH):
t = backend.arange(10, dtype=dtype)
assert backend.dtype(t) == dtype
def test_conv2d(self):
# TF kernel shape: (rows, cols, input_depth, depth)
# channels_first input shape: (n, input_depth, rows, cols)
for input_shape in [(2, 3, 4, 5), (2, 3, 5, 6)]:
for kernel_shape in [(2, 2, 3, 4), (4, 3, 3, 4)]:
for padding in ['valid', 'same']:
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv2d(xth, kernel_th, data_format='channels_first'))
ztf = KTF.eval(KTF.conv2d(xtf, kernel_tf, data_format='channels_first'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
input_shape = (1, 6, 5, 3)
kernel_shape = (3, 3, 3, 2)
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv2d(xth, kernel_th, data_format='channels_last'))
ztf = KTF.eval(KTF.conv2d(xtf, kernel_tf, data_format='channels_last'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_conv2d(self):
# TH kernel shape: (depth, input_depth, rows, cols)
# TF kernel shape: (rows, cols, input_depth, depth)
for input_shape in [(2, 3, 4, 5), (2, 3, 5, 6)]:
for kernel_shape in [(4, 3, 2, 2), (4, 3, 3, 4)]:
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(
convert_kernel(kernel_val, dim_ordering='th'))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv2d(xth, kernel_th, dim_ordering='th'))
ztf = KTF.eval(KTF.conv2d(xtf, kernel_tf, dim_ordering='th'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
input_shape = (1, 6, 5, 3)
kernel_shape = (3, 3, 3, 2)
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val, dim_ordering='tf'))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv2d(xth, kernel_th, dim_ordering='tf'))
ztf = KTF.eval(KTF.conv2d(xtf, kernel_tf, dim_ordering='tf'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_random_normal(self):
mean = 0.
std = 1.
rand = KTF.eval(KTF.random_normal((1000, 1000), mean=mean, stddev=std))
assert rand.shape == (1000, 1000)
assert np.abs(np.mean(rand) - mean) < 0.01
assert np.abs(np.std(rand) - std) < 0.01
rand = KTH.eval(KTH.random_normal((1000, 1000), mean=mean, stddev=std))
assert rand.shape == (1000, 1000)
assert np.abs(np.mean(rand) - mean) < 0.01
assert np.abs(np.std(rand) - std) < 0.01
def test_random_normal(self):
mean = 0.
std = 1.
rand = KTF.eval(KTF.random_normal((1000, 1000), mean=mean, std=std))
assert(rand.shape == (1000, 1000))
assert(np.abs(np.mean(rand) - mean) < 0.01)
assert(np.abs(np.std(rand) - std) < 0.01)
rand = KTH.eval(KTH.random_normal((1000, 1000), mean=mean, std=std))
assert(rand.shape == (1000, 1000))
assert(np.abs(np.mean(rand) - mean) < 0.01)
assert(np.abs(np.std(rand) - std) < 0.01)
def test_conv2d(self):
# TH kernel shape: (depth, input_depth, rows, cols)
# TF kernel shape: (rows, cols, input_depth, depth)
for input_shape in [(2, 3, 4, 5), (2, 3, 5, 6)]:
for kernel_shape in [(4, 3, 2, 2), (4, 3, 3, 4)]:
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv2d(xth, kernel_th))
ztf = KTF.eval(KTF.conv2d(xtf, kernel_tf))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
input_shape = (1, 6, 5, 3)
kernel_shape = (3, 3, 3, 2)
xval = np.random.random(input_shape)
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
kernel_val = np.random.random(kernel_shape) - 0.5
kernel_th = KTH.variable(convert_kernel(kernel_val, dim_ordering='tf'))
kernel_tf = KTF.variable(kernel_val)
zth = KTH.eval(KTH.conv2d(xth, kernel_th, dim_ordering='tf'))
ztf = KTF.eval(KTF.conv2d(xtf, kernel_tf, dim_ordering='tf'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_random_binomial(self):
p = 0.5
rand = KTF.eval(KTF.random_binomial((1000, 1000), p))
assert(rand.shape == (1000, 1000))
assert(np.abs(np.mean(rand) - p) < 0.01)
assert(np.max(rand) == 1)
assert(np.min(rand) == 0)
rand = KTH.eval(KTH.random_binomial((1000, 1000), p))
assert(rand.shape == (1000, 1000))
assert(np.abs(np.mean(rand) - p) < 0.01)
assert(np.max(rand) == 1)
assert(np.min(rand) == 0)
def test_tile(self):
shape = (3, 4)
arr = np.arange(np.prod(shape)).reshape(shape)
arr_th = KTH.variable(arr)
arr_tf = KTF.variable(arr)
n = (2, 1)
th_z = KTH.tile(arr_th, n)
th_rep = KTH.eval(th_z)
tf_rep = KTF.eval(KTF.tile(arr_tf, n))
assert_allclose(tf_rep, th_rep, atol=1e-05)
if hasattr(th_z, '_keras_shape'):
assert th_z._keras_shape == th_rep.shape
def test_in_top_k(self):
batch_size = 20
num_classes = 10
# Random prediction test case
predictions = np.random.random((batch_size, num_classes)).astype('float32')
targets = np.random.randint(num_classes, size=batch_size, dtype='int32')
predictions_th = KTH.variable(predictions, dtype='float32')
targets_th = KTH.variable(targets, dtype='int32')
predictions_tf = KTF.variable(predictions, dtype='float32')
targets_tf = KTF.variable(targets, dtype='int32')
for k in range(1, num_classes + 1):
res_th = KTH.eval(KTH.in_top_k(predictions_th, targets_th, k))
res_tf = KTF.eval(KTF.in_top_k(predictions_tf, targets_tf, k))
assert res_th.shape == res_tf.shape
assert_allclose(res_th, res_tf, atol=1e-05)
# Identical prediction test case:
# randomly set half of the predictions to an identical value
num_identical = num_classes // 2
for i in range(batch_size):
idx_identical = np.random.choice(num_classes, size=num_identical, replace=False)
predictions[i, idx_identical] = predictions[i, 0]
targets = np.zeros(batch_size, dtype='int32')
predictions_th = KTH.variable(predictions, dtype='float32')
targets_th = KTH.variable(targets, dtype='int32')
predictions_tf = KTF.variable(predictions, dtype='float32')
targets_tf = KTF.variable(targets, dtype='int32')
for k in range(1, num_classes + 1):
res_th = KTH.eval(KTH.in_top_k(predictions_th, targets_th, k))
res_tf = KTF.eval(KTF.in_top_k(predictions_tf, targets_tf, k))
assert res_th.shape == res_tf.shape
assert_allclose(res_th, res_tf, atol=1e-05)
def test_switch(self):
val = np.random.random()
xth = KTH.variable(val)
xth = KTH.switch(xth >= 0.5, xth * 0.1, xth * 0.2)
xtf = KTF.variable(val)
xtf = KTF.switch(xtf >= 0.5, xtf * 0.1, xtf * 0.2)
zth = KTH.eval(xth)
ztf = KTF.eval(xtf)
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_random_binomial(self):
p = 0.5
rand = KTF.eval(KTF.random_binomial((1000, 1000), p))
assert rand.shape == (1000, 1000)
assert np.abs(np.mean(rand) - p) < 0.01
assert np.max(rand) == 1
assert np.min(rand) == 0
rand = KTH.eval(KTH.random_binomial((1000, 1000), p))
assert rand.shape == (1000, 1000)
assert np.abs(np.mean(rand) - p) < 0.01
assert np.max(rand) == 1
assert np.min(rand) == 0
def test_switch(self):
val = np.random.random()
xth = KTH.variable(val)
xth = KTH.switch(xth >= 0.5, xth * 0.1, xth * 0.2)
xtf = KTF.variable(val)
xtf = KTF.switch(xtf >= 0.5, xtf * 0.1, xtf * 0.2)
zth = KTH.eval(xth)
ztf = KTF.eval(xtf)
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_batch_dot_shape(self):
x_batch = KTF.ones(shape=(32, 20))
y_batch = KTF.ones(shape=(32, 20))
xy_batch_dot = KTF.batch_dot(x_batch, y_batch, axes=1)
assert_allclose(KTF.eval(xy_batch_dot),
np.ones((32, 1)) * 20,
atol=1e-05)
xy_batch_dot = KTF.batch_dot(x_batch, y_batch, axes=0)
assert_allclose(KTF.eval(xy_batch_dot),
np.ones((20, 1)) * 32,
atol=1e-05)
# making sure swapping axes when ndim == 2 works
x_batch = KTF.ones(shape=(32, 20))
y_batch = KTF.ones(shape=(20, 32))
xy_batch_dot = KTF.batch_dot(x_batch, y_batch, axes=(0, 1))
assert_allclose(KTF.eval(xy_batch_dot),
np.ones((20, 1)) * 32,
atol=1e-05)
xy_batch_dot = KTF.batch_dot(x_batch, y_batch, axes=(1, 0))
assert_allclose(KTF.eval(xy_batch_dot),
np.ones((32, 1)) * 20,
atol=1e-05)
def test_random_uniform(self):
min_val = -1.
max_val = 1.
rand = KTF.eval(KTF.random_uniform((1000, 1000), min_val, max_val))
assert rand.shape == (1000, 1000)
assert np.abs(np.mean(rand)) < 0.01
assert np.max(rand) <= max_val
assert np.min(rand) >= min_val
rand = KTH.eval(KTH.random_uniform((1000, 1000), min_val, max_val))
assert rand.shape == (1000, 1000)
assert np.abs(np.mean(rand)) < 0.01
assert np.max(rand) <= max_val
assert np.min(rand) >= min_val
def test_random_uniform(self):
min_val = -1.
max_val = 1.
rand = KTF.eval(KTF.random_uniform((1000, 1000), min_val, max_val))
assert rand.shape == (1000, 1000)
assert np.abs(np.mean(rand)) < 0.01
assert np.max(rand) <= max_val
assert np.min(rand) >= min_val
rand = KTH.eval(KTH.random_uniform((1000, 1000), min_val, max_val))
assert rand.shape == (1000, 1000)
assert np.abs(np.mean(rand)) < 0.01
assert np.max(rand) <= max_val
assert np.min(rand) >= min_val
def test_random_uniform(self):
min = -1.
max = 1.
rand = KTF.eval(KTF.random_uniform((1000, 1000), min, max))
assert (rand.shape == (1000, 1000))
assert (np.abs(np.mean(rand)) < 0.01)
assert (np.max(rand) <= max)
assert (np.min(rand) >= min)
rand = KTH.eval(KTH.random_uniform((1000, 1000), min, max))
assert (rand.shape == (1000, 1000))
assert (np.abs(np.mean(rand)) < 0.01)
assert (np.max(rand) <= max)
assert (np.min(rand) >= min)
def check_two_tensor_operation(function_name, x_input_shape, y_input_shape, **kwargs):
xval = np.random.random(x_input_shape) - 0.5
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
yval = np.random.random(y_input_shape) - 0.5
yth = KTH.variable(yval)
ytf = KTF.variable(yval)
zth = KTH.eval(getattr(KTH, function_name)(xth, yth, **kwargs))
ztf = KTF.eval(getattr(KTF, function_name)(xtf, ytf, **kwargs))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_random_uniform(self):
min = -1.
max = 1.
rand = KTF.eval(KTF.random_uniform((1000, 1000), min, max))
assert(rand.shape == (1000, 1000))
assert(np.abs(np.mean(rand)) < 0.01)
assert(np.max(rand) <= max)
assert(np.min(rand) >= min)
rand = KTH.eval(KTH.random_uniform((1000, 1000), min, max))
assert(rand.shape == (1000, 1000))
assert(np.abs(np.mean(rand)) < 0.01)
assert(np.max(rand) <= max)
assert(np.min(rand) >= min)
def test_extract(self, input_shape, kernel_shape):
xval = np.random.random(input_shape)
kernel = [kernel_shape, kernel_shape]
strides = [kernel_shape, kernel_shape]
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
ztf = KTF.eval(KCTF.extract_image_patches(xtf, kernel, strides,
data_format='channels_first',
padding='valid'))
zth = KTH.eval(KCTH.extract_image_patches(xth, kernel, strides,
data_format='channels_first',
padding='valid'))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-02)
def check_two_tensor_operation(function_name, x_input_shape, y_input_shape,
**kwargs):
xval = np.random.random(x_input_shape) - 0.5
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
yval = np.random.random(y_input_shape) - 0.5
yth = KTH.variable(yval)
ytf = KTF.variable(yval)
zth = KTH.eval(getattr(KTH, function_name)(xth, yth, **kwargs))
ztf = KTF.eval(getattr(KTF, function_name)(xtf, ytf, **kwargs))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_moments(self):
input_shape = (10, 10, 10, 10)
x_0 = np.zeros(input_shape)
x_1 = np.ones(input_shape)
x_random = np.random.random(input_shape)
th_axes = [0, 2, 3]
tf_axes = [0, 1, 2]
for ip in [x_0, x_1, x_random]:
for axes in [th_axes, tf_axes]:
for keep_dims in [True, False]:
ip_th = KTH.variable(ip)
th_mean, th_var = KCTH.moments(ip_th,
axes,
keep_dims=keep_dims)
ip_tf = KTF.variable(ip)
tf_mean, tf_var = KCTF.moments(ip_tf,
axes,
keep_dims=keep_dims)
th_mean_val = KTH.eval(th_mean)
tf_mean_val = KTF.eval(tf_mean)
th_var_val = KTH.eval(th_var)
tf_var_val = KTF.eval(tf_var)
# absolute tolerance needed when working with zeros
assert_allclose(th_mean_val,
tf_mean_val,
rtol=1e-4,
atol=1e-10)
assert_allclose(th_var_val,
tf_var_val,
rtol=1e-4,
atol=1e-10)
def test_ctc(self):
# simplified version of TensorFlow's test
label_lens = np.expand_dims(np.asarray([5, 4]), 1)
input_lens = np.expand_dims(np.asarray([5, 5]), 1) # number of timesteps
# the Theano and Tensorflow CTC code use different methods to ensure
# numerical stability. The Theano code subtracts out the max
# before the final log, so the results are different but scale
# identically and still train properly
loss_log_probs_tf = [3.34211, 5.42262]
loss_log_probs_th = [1.73308, 3.81351]
# dimensions are batch x time x categories
labels = np.asarray([[0, 1, 2, 1, 0], [0, 1, 1, 0, -1]])
inputs = np.asarray(
[
[
[0.633766, 0.221185, 0.0917319, 0.0129757, 0.0142857, 0.0260553],
[0.111121, 0.588392, 0.278779, 0.0055756, 0.00569609, 0.010436],
[0.0357786, 0.633813, 0.321418, 0.00249248, 0.00272882, 0.0037688],
[0.0663296, 0.643849, 0.280111, 0.00283995, 0.0035545, 0.00331533],
[0.458235, 0.396634, 0.123377, 0.00648837, 0.00903441, 0.00623107],
],
[
[0.30176, 0.28562, 0.0831517, 0.0862751, 0.0816851, 0.161508],
[0.24082, 0.397533, 0.0557226, 0.0546814, 0.0557528, 0.19549],
[0.230246, 0.450868, 0.0389607, 0.038309, 0.0391602, 0.202456],
[0.280884, 0.429522, 0.0326593, 0.0339046, 0.0326856, 0.190345],
[0.423286, 0.315517, 0.0338439, 0.0393744, 0.0339315, 0.154046],
],
],
dtype=np.float32,
)
labels_tf = KTF.variable(labels, dtype="int32")
inputs_tf = KTF.variable(inputs, dtype="float32")
input_lens_tf = KTF.variable(input_lens, dtype="int32")
label_lens_tf = KTF.variable(label_lens, dtype="int32")
res = KTF.eval(KTF.ctc_batch_cost(labels_tf, inputs_tf, input_lens_tf, label_lens_tf))
assert_allclose(res[:, 0], loss_log_probs_tf, atol=1e-05)
labels_th = KTH.variable(labels, dtype="int32")
inputs_th = KTH.variable(inputs, dtype="float32")
input_lens_th = KTH.variable(input_lens, dtype="int32")
label_lens_th = KTH.variable(label_lens, dtype="int32")
res = KTH.eval(KTH.ctc_batch_cost(labels_th, inputs_th, input_lens_th, label_lens_th))
assert_allclose(res[0, :], loss_log_probs_th, atol=1e-05)
def test_gradient(self):
val = np.random.random((4, 2))
xth = KTH.variable(val)
xtf = KTF.variable(val)
expth = xth * KTH.exp(xth)
exptf = xtf * KTF.exp(xtf)
lossth = KTH.sum(expth)
losstf = KTF.sum(exptf)
gradth = KTH.gradients(lossth, [expth])
gradtf = KTF.gradients(losstf, [exptf])
zth = KTH.eval(gradth[0])
ztf = KTF.eval(gradtf[0])
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_repeat_elements(self):
reps = 3
for ndims in [1, 2, 3]:
shape = np.arange(2, 2 + ndims)
arr = np.arange(np.prod(shape)).reshape(shape)
arr_th = KTH.variable(arr)
arr_tf = KTF.variable(arr)
for rep_axis in range(ndims):
np_rep = np.repeat(arr, reps, axis=rep_axis)
th_rep = KTH.eval(KTH.repeat_elements(arr_th, reps, axis=rep_axis))
tf_rep = KTF.eval(KTF.repeat_elements(arr_tf, reps, axis=rep_axis))
assert th_rep.shape == np_rep.shape
assert tf_rep.shape == np_rep.shape
assert_allclose(np_rep, th_rep, atol=1e-05)
assert_allclose(np_rep, tf_rep, atol=1e-05)
def test_gather(self):
shape = (10, 2, 3)
ref = np.arange(np.prod(shape)).reshape(shape)
ref_th = KTH.variable(ref)
ref_tf = KTF.variable(ref)
inds = [1, 3, 7, 9]
inds_th = KTH.variable(inds, dtype='int32')
inds_tf = KTF.variable(inds, dtype='int32')
th_z = KTH.gather(ref_th, inds_th)
th_result = KTH.eval(th_z)
tf_result = KTF.eval(KTF.gather(ref_tf, inds_tf))
assert_allclose(tf_result, th_result, atol=1e-05)
if hasattr(th_z, '_keras_shape'):
assert th_z._keras_shape == th_result.shape
def test_shape_operations(self):
# concatenate
xval = np.random.random((4, 3))
xth = KTH.variable(xval)
xtf = KTF.variable(xval)
yval = np.random.random((4, 2))
yth = KTH.variable(yval)
ytf = KTF.variable(yval)
zth = KTH.eval(KTH.concatenate([xth, yth], axis=-1))
ztf = KTF.eval(KTF.concatenate([xtf, ytf], axis=-1))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
check_single_tensor_operation("reshape", (4, 2), shape=(8, 1))
check_single_tensor_operation("permute_dimensions", (4, 2, 3), pattern=(2, 0, 1))
check_single_tensor_operation("repeat", (4, 1), n=3)
check_single_tensor_operation("flatten", (4, 1))
check_single_tensor_operation("expand_dims", (4, 3), dim=-1)
check_single_tensor_operation("expand_dims", (4, 3, 2), dim=1)
check_single_tensor_operation("squeeze", (4, 3, 1), axis=2)
def check_composed_tensor_operations(first_function_name, first_function_args,
second_function_name, second_function_args,
input_shape):
''' Creates a random tensor t0 with shape input_shape and compute
t1 = first_function_name(t0, **first_function_args)
t2 = second_function_name(t1, **second_function_args)
with both Theano and TensorFlow backends and ensures the answers match.
'''
val = np.random.random(input_shape) - 0.5
xth = KTH.variable(val)
xtf = KTF.variable(val)
yth = getattr(KTH, first_function_name)(xth, **first_function_args)
ytf = getattr(KTF, first_function_name)(xtf, **first_function_args)
zth = KTH.eval(getattr(KTH, second_function_name)(yth, **second_function_args))
ztf = KTF.eval(getattr(KTF, second_function_name)(ytf, **second_function_args))
assert zth.shape == ztf.shape
assert_allclose(zth, ztf, atol=1e-05)
def test_tile(self):
shape = (3, 4)
arr = np.arange(np.prod(shape)).reshape(shape)
arr_th = KTH.variable(arr)
arr_tf = KTF.variable(arr)
n = (2, 1)
th_z = KTH.tile(arr_th, n)
th_rep = KTH.eval(th_z)
tf_rep = KTF.eval(KTF.tile(arr_tf, n))
assert_allclose(tf_rep, th_rep, atol=1e-05)
if hasattr(th_z, '_keras_shape'):
assert th_z._keras_shape == th_rep.shape
# test theano shape inference when
# input shape has None entries
if K.backend() == 'theano':
x = K.placeholder(shape=(None, 4))
n = 2
y = KTH.tile(x, n)
assert y._keras_shape == (None, 8)
n = (4, 3)
y = K.tile(x, n)
assert y._keras_shape == (None, 12)
