def call(self, u_vecs, mask=None):
if self.share_weights:
u_hat_vecs = K.conv1d(u_vecs, self.W)
else:
u_hat_vecs = K.local_conv1d(u_vecs, self.W, [1], [1])
batch_size = K.shape(u_vecs)[0]
input_num_capsule = K.shape(u_vecs)[1]
u_hat_vecs = K.reshape(u_hat_vecs,
(batch_size, input_num_capsule,
self.num_capsule, self.dim_capsule))
u_hat_vecs = K.permute_dimensions(u_hat_vecs, (0, 2, 1, 3))
# final u_hat_vecs.shape = [None, num_capsule, input_num_capsule, dim_capsule]
b = K.zeros_like(
u_hat_vecs[:, :, :,
0]) # shape = [None, num_capsule, input_num_capsule]
for i in range(self.routings):
b = K.permute_dimensions(
b, (0, 2, 1)) # shape = [None, input_num_capsule, num_capsule]
c = K.softmax(b)
c = K.permute_dimensions(c, (0, 2, 1))
b = K.permute_dimensions(b, (0, 2, 1))
outputs = self.activation(K.batch_dot(c, u_hat_vecs, [2, 2]))
if i < self.routings - 1:
b = K.batch_dot(outputs, u_hat_vecs, [2, 3])
return outputs
def call(self, u_vecs):
if self.share_weights:
u_hat_vecs = K.conv1d(u_vecs, self.W)
else:
u_hat_vecs = K.local_conv1d(u_vecs, self.W, [1], [1])
batch_size = K.shape(u_vecs)[0]
input_num_capsule = K.shape(u_vecs)[1]
u_hat_vecs = K.reshape(u_hat_vecs, (batch_size, input_num_capsule,
self.num_capsule, self.dim_capsule))
u_hat_vecs = K.permute_dimensions(u_hat_vecs, (0, 2, 1, 3))
# final u_hat_vecs.shape = [None, num_capsule, input_num_capsule, dim_capsule]
b = K.zeros_like(u_hat_vecs[:, :, :, 0]) # shape = [None, num_capsule, input_num_capsule]
for i in range(self.routings):
c = softmax(b, 1)
o = K.batch_dot(c, u_hat_vecs, [2, 2])
if K.backend() == 'theano':
o = K.sum(o, axis=1)
if i < self.routings - 1:
o = K.l2_normalize(o, -1)
b = K.batch_dot(o, u_hat_vecs, [2, 3])
if K.backend() == 'theano':
b = K.sum(b, axis=1)
return self.activation(o)
def call(self, inputs):
"""Following the routing algorithm from Hinton's paper,
but replace b = b + <u,v> with b = <u,v>.
This change can improve the feature representation of Capsule.
However, you can replace
b = K.batch_dot(outputs, hat_inputs, [2, 3])
with
b += K.batch_dot(outputs, hat_inputs, [2, 3])
to realize a standard routing.
"""
if self.share_weights:
hat_inputs = K.conv1d(inputs, self.kernel)
else:
hat_inputs = K.local_conv1d(inputs, self.kernel, [1], [1])
batch_size = K.shape(inputs)[0]
input_num_capsule = K.shape(inputs)[1]
hat_inputs = K.reshape(hat_inputs,
(batch_size, input_num_capsule,
self.num_capsule, self.dim_capsule))
hat_inputs = K.permute_dimensions(hat_inputs, (0, 2, 1, 3))
b = K.zeros_like(hat_inputs[:, :, :, 0])
for i in range(self.routings):
c = softmax(b, 1)
o = self.activation(K.batch_dot(c, hat_inputs, [2, 2]))
if i < self.routings - 1:
b += K.batch_dot(o, hat_inputs, [2, 3])
if K.backend() == 'theano':
o = K.sum(o, axis=1)
return o
def call(self, inputs):
if self.share_weights:
u_hat_vectors = K.conv1d(inputs, self.W)
else:
u_hat_vectors = K.local_conv1d(inputs, self.W, [1], [1])
# u_hat_vectors : The spatially transformed input vectors (with local_conv_1d)
batch_size = K.shape(inputs)[0]
input_num_capsule = K.shape(inputs)[1]
u_hat_vectors = K.reshape(u_hat_vectors,
(batch_size, input_num_capsule,
self.num_capsule, self.dim_capsule))
u_hat_vectors = K.permute_dimensions(u_hat_vectors, (0, 2, 1, 3))
routing_weights = K.zeros_like(u_hat_vectors[:, :, :, 0])
for i in range(self.routings):
capsule_weights = K.softmax(routing_weights)
outputs = K.batch_dot(capsule_weights, u_hat_vectors, [2, 2])
if K.ndim(outputs) == 4:
outputs = K.sum(outputs, axis=1)
if i < self.routings - 1:
outputs = K.l2_normalize(outputs, -1)
routing_weights = K.batch_dot(outputs, u_hat_vectors, [2, 3])
if K.ndim(routing_weights) == 4:
routing_weights = K.sum(routing_weights, axis=1)
return self.activation(outputs)
def call(self, inputs, **kwargs):
"""Following the routing algorithm from Hinton's paper,
but replace b = b + <u,v> with b = <u,v>.
This change can improve the feature representation of the capsule.
However, you can replace
b = K.batch_dot(outputs, hat_inputs, [2, 3])
with
b += K.batch_dot(outputs, hat_inputs, [2, 3])
to get standard routing.
"""
if self.share_weights:
hat_inputs = K.conv1d(inputs, self.kernel)
else:
hat_inputs = K.local_conv1d(inputs, self.kernel, [1], [1])
batch_size = K.shape(inputs)[0]
input_num_capsule = K.shape(inputs)[1]
hat_inputs = K.reshape(hat_inputs,
(batch_size, input_num_capsule,
self.num_capsule, self.dim_capsule))
hat_inputs = K.permute_dimensions(hat_inputs, (0, 2, 1, 3))
b = K.zeros_like(hat_inputs[:, :, :, 0])
print(self.routings)
for i in range(self.routings):
c = K.softmax(b, 1)
o = self.activation(K.batch_dot(c, hat_inputs, [2, 2]))
if i < self.routings - 1:
b = K.batch_dot(o, hat_inputs, [2, 3])
if K.backend() == 'theano':
o = K.sum(o, axis=1)
return o
def call(self, u_vecs):
if self.share_weights:
u_hat_vecs = K.conv1d(u_vecs, self.W) # bsz,200,160
else:
u_hat_vecs = K.local_conv1d(u_vecs, self.W, [1], [1])
batch_size = K.shape(u_vecs)[0]
input_num_capsule = K.shape(u_vecs)[1]
u_hat_vecs = K.reshape(
u_hat_vecs, (batch_size, input_num_capsule, self.num_capsule,
self.dim_capsule)) # bsz,200,10,16
u_hat_vecs = K.permute_dimensions(u_hat_vecs,
(0, 2, 1, 3)) # bsz,10,200,16
# final u_hat_vecs.shape = [None, num_capsule, input_num_capsule, dim_capsule]
b = K.zeros_like(u_hat_vecs[:, :, :, 0]) # bsz,10,200
for i in range(self.routings):
b = K.permute_dimensions(b, (0, 2, 1)) # bsz,200,10
c = K.softmax(b) # bsz,200,10, 对最后一个轴10维进行sofrmax
c = K.permute_dimensions(c, (0, 2, 1)) # bsz,10,200
b = K.permute_dimensions(b, (0, 2, 1)) # bsz,200,10
outputs = self.activation(K.batch_dot(c, u_hat_vecs,
[2, 2])) # bsz,10,16
if i < self.routings - 1:
b = K.batch_dot(outputs, u_hat_vecs, [2, 3]) # bsz,10,200
return outputs
def call(self, u_vecs):
if self.share_weights:
u_hat_vecs = K.conv1d(u_vecs,
self.W) #none*82*600 1*600*(32*300)
else:
u_hat_vecs = K.local_conv1d(u_vecs, self.W, [1], [1])
batch_size = K.shape(u_vecs)[0] #82*600, [0]=none
input_num_capsule = K.shape(u_vecs)[1] #[1]=82
u_hat_vecs = K.reshape(u_hat_vecs,
(batch_size, input_num_capsule,
self.num_capsule, self.dim_capsule))
u_hat_vecs = K.permute_dimensions(
u_hat_vecs, (0, 2, 1, 3)
) #final u_hat_vecs.shape = [None, num_capsule, input_num_capsule, dim_capsule]
b = K.zeros_like(
u_hat_vecs[:, :, :, 0]
) # shape = [None, num_capsule, input_num_capsule] 32*82
for i in range(self.routings):
b = K.permute_dimensions(
b, (0, 2,
1)) # shape = [None, input_num_capsule, num_capsule] 82*32
c = K.softmax(b)
c = K.permute_dimensions(c, (0, 2, 1)) #[32*82]
b = K.permute_dimensions(b, (0, 2, 1)) #[32*82]
outputs = self.activation(K.batch_dot(c, u_hat_vecs, [2, 2]))
if i < self.routings - 1:
b = K.batch_dot(outputs, u_hat_vecs,
[2, 3]) #[..*32*[128]] [?*32*82*[128]]=[32*82]
return outputs
def call(self, inputs, training=None):
if self.share_weights:
hat_inputs = K.conv1d(inputs, self.kernel)
else:
hat_inputs = K.local_conv1d(inputs, self.kernel, [1], [1])
batch_size = K.shape(inputs)[0]
input_num_capsule = K.shape(inputs)[1]
hat_inputs = K.reshape(hat_inputs,
(batch_size, input_num_capsule,
self.num_capsule, self.dim_capsule))
hat_inputs = K.permute_dimensions(hat_inputs, (0, 2, 1, 3))
b = K.zeros_like(hat_inputs[:, :, :, 0])
print("b:")
print(K.int_shape(b))
for i in range(self.routings):
c = tf.nn.softmax(b, dim=1)
print("c:")
print(K.int_shape(c))
print("hat_inputs:")
print(K.int_shape(hat_inputs))
o = tf.keras.backend.batch_dot(c, hat_inputs, [2, 2])
print("o:")
print(K.int_shape(o))
o = self.activation(o)
print("o:")
print(K.int_shape(o))
if i < self.routings - 1:
b += tf.keras.backend.batch_dot(o, hat_inputs, [2, 3])
return o
def call(self, u_vecs):
if self.share_weights:
u_hat_vecs = K.conv1d(u_vecs, self.W)
else:
u_hat_vecs = K.local_conv1d(u_vecs, self.W, [1], [1])
batch_size = K.shape(u_vecs)[0]
input_num_capsule = K.shape(u_vecs)[1]
u_hat_vecs = K.reshape(u_hat_vecs,
(batch_size, input_num_capsule,
self.num_capsule, self.dim_capsule))
u_hat_vecs = K.permute_dimensions(u_hat_vecs, (0, 2, 1, 3))
b = K.zeros_like(u_hat_vecs[:, :, :, 0])
for i in range(self.routings):
c = softmax(b, 1)
o = K.batch_dot(c, u_hat_vecs, [2, 2])
o = K.sum(
o, axis=1
) # the previous version does not have this op, due to the recent updates of keras
if i < self.routings - 1:
o = K.l2_normalize(
o, -1
) # here is for normalize if it not works, remove this line
b = K.batch_dot(o, u_hat_vecs, [2, 3])
b = K.sum(
b, axis=1
) # the previous version does not have this op, due to the recent updates of keras
return o
def call(self, inputs):
if self.share_weights:
hat_inputs = K.conv1d(inputs, self.kernel)
else:
hat_inputs = K.local_conv1d(inputs, self.kernel, [1], [1])
batch_size = K.shape(inputs)[0]
input_num_capsule = K.shape(inputs)[1]
hat_inputs = K.reshape(hat_inputs,
(batch_size, input_num_capsule,
self.num_capsule, self.dim_capsule))
hat_inputs = K.permute_dimensions(hat_inputs, (0, 2, 1, 3))
b = K.zeros_like(hat_inputs[:, :, :, 0])
for i in range(self.routings):
c = softmax(b, 1)
o = self.activation(K.batch_dot(c, hat_inputs, [2, 2]))
if i < self.routings - 1:
b = K.batch_dot(o, hat_inputs, [2, 3])
return o