parent
9c28d21b4f
commit
d5649da5f8
@ -1388,7 +1388,7 @@ class Merge(Layer):
|
||||
masks = [K.expand_dims(m, 0) for m in mask if m is not None]
|
||||
return K.all(K.concatenate(masks, axis=0), axis=0, keepdims=False)
|
||||
elif self.mode == 'concat':
|
||||
# Make a list of masks while making sure the dimensionality of each mask
|
||||
# Make a list of masks while making sure the dimensionality of each mask
|
||||
# is the same as the corresponding input.
|
||||
masks = []
|
||||
for input_i, mask_i in zip(inputs, mask):
|
||||
|
@ -517,7 +517,7 @@ class Deconvolution2D(Convolution2D):
|
||||
raise Exception('Invalid dim_ordering: ' + self.dim_ordering)
|
||||
|
||||
def call(self, x, mask=None):
|
||||
output = K.deconv2d(x, self.W, self.output_shape_,
|
||||
output = K.deconv2d(x, self.W, self.output_shape_,
|
||||
strides=self.subsample,
|
||||
border_mode=self.border_mode,
|
||||
dim_ordering=self.dim_ordering,
|
||||
@ -1544,13 +1544,13 @@ class Cropping2D(Layer):
|
||||
def call(self, x, mask=None):
|
||||
input_shape = self.input_spec[0].shape
|
||||
if self.dim_ordering == 'th':
|
||||
return x[:,
|
||||
:,
|
||||
return x[:,
|
||||
:,
|
||||
self.cropping[0][0]:input_shape[2]-self.cropping[0][1],
|
||||
self.cropping[1][0]:input_shape[3]-self.cropping[1][1]]
|
||||
elif self.dim_ordering == 'tf':
|
||||
return x[:,
|
||||
self.cropping[0][0]:input_shape[1]-self.cropping[0][1],
|
||||
return x[:,
|
||||
self.cropping[0][0]:input_shape[1]-self.cropping[0][1],
|
||||
self.cropping[1][0]:input_shape[2]-self.cropping[1][1],
|
||||
:]
|
||||
|
||||
@ -1624,16 +1624,16 @@ class Cropping3D(Layer):
|
||||
def call(self, x, mask=None):
|
||||
input_shape = self.input_spec[0].shape
|
||||
if self.dim_ordering == 'th':
|
||||
return x[:,
|
||||
:,
|
||||
self.cropping[0][0]:input_shape[2]-self.cropping[0][1],
|
||||
self.cropping[1][0]:input_shape[3]-self.cropping[1][1],
|
||||
return x[:,
|
||||
:,
|
||||
self.cropping[0][0]:input_shape[2]-self.cropping[0][1],
|
||||
self.cropping[1][0]:input_shape[3]-self.cropping[1][1],
|
||||
self.cropping[2][0]:input_shape[4]-self.cropping[2][1]]
|
||||
elif self.dim_ordering == 'tf':
|
||||
return x[:,
|
||||
self.cropping[0][0]:input_shape[1]-self.cropping[0][1],
|
||||
self.cropping[1][0]:input_shape[2]-self.cropping[1][1],
|
||||
self.cropping[2][0]:input_shape[3]-self.cropping[2][1],
|
||||
return x[:,
|
||||
self.cropping[0][0]:input_shape[1]-self.cropping[0][1],
|
||||
self.cropping[1][0]:input_shape[2]-self.cropping[1][1],
|
||||
self.cropping[2][0]:input_shape[3]-self.cropping[2][1],
|
||||
:]
|
||||
|
||||
def get_config(self):
|
||||
|
@ -487,13 +487,13 @@ class Lambda(Layer):
|
||||
Takes input tensor as first argument.
|
||||
output_shape: Expected output shape from function.
|
||||
Can be a tuple or function.
|
||||
If a tuple, it only specifies the first dimension onward;
|
||||
If a tuple, it only specifies the first dimension onward;
|
||||
sample dimension is assumed either the same as the input:
|
||||
`output_shape = (input_shape[0], ) + output_shape`
|
||||
or, the input is `None` and the sample dimension is also `None`:
|
||||
`output_shape = (None, ) + output_shape`
|
||||
If a function, it specifies the entire shape as a function of
|
||||
the input shape: `output_shape = f(input_shape)`
|
||||
If a function, it specifies the entire shape as a function of the
|
||||
input shape: `output_shape = f(input_shape)`
|
||||
arguments: optional dictionary of keyword arguments to be passed
|
||||
to the function.
|
||||
|
||||
|
@ -138,7 +138,7 @@ def skipgrams(sequence, vocabulary_size,
|
||||
continue
|
||||
couples.append([wi, wj])
|
||||
if categorical:
|
||||
labels.append([0,1])
|
||||
labels.append([0, 1])
|
||||
else:
|
||||
labels.append(1)
|
||||
|
||||
@ -149,12 +149,12 @@ def skipgrams(sequence, vocabulary_size,
|
||||
|
||||
couples += [[words[i %len(words)], random.randint(1, vocabulary_size-1)] for i in range(nb_negative_samples)]
|
||||
if categorical:
|
||||
labels += [[1,0]]*nb_negative_samples
|
||||
labels += [[1, 0]]*nb_negative_samples
|
||||
else:
|
||||
labels += [0]*nb_negative_samples
|
||||
|
||||
if shuffle:
|
||||
seed = random.randint(0,10e6)
|
||||
seed = random.randint(0, 10e6)
|
||||
random.seed(seed)
|
||||
random.shuffle(couples)
|
||||
random.seed(seed)
|
||||
|
@ -65,7 +65,7 @@ def get_file(fname, origin, untar=False,
|
||||
download = True
|
||||
|
||||
if download:
|
||||
print('Downloading data from', origin)
|
||||
print('Downloading data from', origin)
|
||||
global progbar
|
||||
progbar = None
|
||||
|
||||
|
@ -13,26 +13,20 @@ norecursedirs= build
|
||||
# E251 unexpected spaces around keyword / parameter equals
|
||||
# E225 missing whitespace around operator
|
||||
# E226 missing whitespace around arithmetic operator
|
||||
# W291 trailing whitespace
|
||||
# W293 blank line contains whitespace
|
||||
# E501 line too long (82 > 79 characters)
|
||||
# E402 module level import not at top of file - temporary measure to coninue adding ros python packaged in sys.path
|
||||
# E731 do not assign a lambda expression, use a def
|
||||
# E302 two blank lines between the functions
|
||||
# E231 missing whitespace after ,
|
||||
# E241 multiple spaces after ','
|
||||
# E261 at least two spaces before inline comment
|
||||
|
||||
|
||||
pep8ignore=* E251 \
|
||||
* E225 \
|
||||
* E226 \
|
||||
* W291 \
|
||||
* W293 \
|
||||
* E501 \
|
||||
* E402 \
|
||||
* E731 \
|
||||
* E302 \
|
||||
* E231 \
|
||||
* E241 \
|
||||
* E261
|
||||
|
@ -63,7 +63,7 @@ def test_pad_sequences_vector():
|
||||
|
||||
def test_make_sampling_table():
|
||||
a = make_sampling_table(3)
|
||||
assert_allclose(a, np.asarray([0.00315225, 0.00315225, 0.00547597]),
|
||||
assert_allclose(a, np.asarray([0.00315225, 0.00315225, 0.00547597]),
|
||||
rtol=.1)
|
||||
|
||||
|
||||
|
@ -48,7 +48,7 @@ def test_softplus():
|
||||
return np.log(np.ones_like(x) + np.exp(x))
|
||||
|
||||
x = K.placeholder(ndim=2)
|
||||
f = K.function([x], [activations.softplus(x)])
|
||||
f = K.function([x], [activations.softplus(x)])
|
||||
test_values = get_standard_values()
|
||||
|
||||
result = f([test_values])[0]
|
||||
@ -64,7 +64,7 @@ def test_softsign():
|
||||
return np.divide(x, np.ones_like(x) + np.absolute(x))
|
||||
|
||||
x = K.placeholder(ndim=2)
|
||||
f = K.function([x], [activations.softsign(x)])
|
||||
f = K.function([x], [activations.softsign(x)])
|
||||
test_values = get_standard_values()
|
||||
|
||||
result = f([test_values])[0]
|
||||
@ -85,7 +85,7 @@ def test_sigmoid():
|
||||
sigmoid = np.vectorize(ref_sigmoid)
|
||||
|
||||
x = K.placeholder(ndim=2)
|
||||
f = K.function([x], [activations.sigmoid(x)])
|
||||
f = K.function([x], [activations.sigmoid(x)])
|
||||
test_values = get_standard_values()
|
||||
|
||||
result = f([test_values])[0]
|
||||
@ -108,7 +108,7 @@ def test_hard_sigmoid():
|
||||
hard_sigmoid = np.vectorize(ref_hard_sigmoid)
|
||||
|
||||
x = K.placeholder(ndim=2)
|
||||
f = K.function([x], [activations.hard_sigmoid(x)])
|
||||
f = K.function([x], [activations.hard_sigmoid(x)])
|
||||
test_values = get_standard_values()
|
||||
|
||||
result = f([test_values])[0]
|
||||
|
Loading…
Reference in New Issue
Block a user