Keras deep clustering undefined errors in clustering custom layer - keras

Question

i was following this guide to implement a clustering into a deep model
https://ai-mrkogao.github.io/reinforcement%20learning/clusteringkeras/ but i got two errors :
The first one, on this line
clustering_layer = ClusteringLayer(n_clusters, name='clustering')(encoder.output)
it says
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 463, in __call__
self.build(unpack_singleton(input_shapes))
File "<stdin>", line 14, in build
TypeError: add_weight() got multiple values for argument 'name'
So i located
self.clusters = self.add_weight((self.n_clusters, input_dim), initializer='glorot_uniform', name='clusters')
from the class ClusteringLayer and i removed name='clusters' as follow
self.clusters = self.add_weight((self.n_clusters, input_dim), initializer='glorot_uniform')
But now it keeps giving me the following error
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 463, in __call__
self.build(unpack_singleton(input_shapes))
File "<stdin>", line 14, in build
File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 282, in add_weight
constraint=constraint)
File "/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py", line 620, in variable
value, dtype=dtype, name=name, constraint=constraint)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py", line 782, in variable
constraint=constraint)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 263, in __call__
return super(VariableMetaclass, cls).__call__(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py", line 460, in __init__
shape=shape)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py", line 582, in _init_from_args
if init_from_fn else [initial_value]) as name:
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 6513, in __enter__
return self._name_scope.__enter__()
File "/usr/lib/python3.6/contextlib.py", line 81, in __enter__
return next(self.gen)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 4306, in name_scope
if not _VALID_SCOPE_NAME_REGEX.match(name):
TypeError: expected string or bytes-like object
Here is the complete and reproducible code
import keras.backend as K
from keras.engine.topology import Layer, InputSpec
from keras.layers import Dense, Input
from keras.models import Model
from keras.optimizers import SGD
from keras import callbacks
from keras.initializers import VarianceScaling
from sklearn.cluster import KMeans
def autoencoder(dims, act='relu', init='glorot_uniform'):
n_stacks = len(dims) - 1
input_img = Input(shape=(dims[0],), name='input')
x = input_img
for i in range(n_stacks-1):
x = Dense(dims[i + 1], activation=act, kernel_initializer=init, name='encoder_%d' % i)(x)
encoded = Dense(dims[-1], kernel_initializer=init, name='encoder_%d' % (n_stacks - 1))(x) # hidden layer, features are extracted from here
x = encoded
for i in range(n_stacks-1, 0, -1):
x = Dense(dims[i], activation=act, kernel_initializer=init, name='decoder_%d' % i)(x)
x = Dense(dims[0], kernel_initializer=init, name='decoder_0')(x)
decoded = x
return Model(inputs=input_img, outputs=decoded, name='AE'), Model(inputs=input_img, outputs=encoded, name='encoder')
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x = np.concatenate((x_train, x_test))
y = np.concatenate((y_train, y_test))
x = x.reshape((x.shape[0], -1))
x = np.divide(x, 255.)
x_train.shape
x.shape
n_clusters = len(np.unique(y))
kmeans = KMeans(n_clusters=n_clusters, n_init=20, n_jobs=4)
y_pred_kmeans = kmeans.fit_predict(x)
y_pred_kmeans[:10]
dims = [x.shape[-1], 500, 500, 2000, 10]
init = VarianceScaling(scale=1. / 3., mode='fan_in',distribution='uniform')
pretrain_optimizer = SGD(lr=1, momentum=0.9)
autoencoder, encoder = autoencoder(dims, init=init)
autoencoder.compile(optimizer=pretrain_optimizer, loss='mse')
autoencoder.fit(x, x, batch_size=250, epochs=2) #, callbacks=cb)
autoencoder.save_weights( 'ae_weights.h5')
class ClusteringLayer(Layer):
def __init__(self, n_clusters, weights=None, alpha=1.0, **kwargs):
if 'input_shape' not in kwargs and 'input_dim' in kwargs:
kwargs['input_shape'] = (kwargs.pop('input_dim'),)
super(ClusteringLayer, self).__init__(**kwargs)
self.n_clusters = n_clusters
self.alpha = alpha
self.initial_weights = weights
self.input_spec = InputSpec(ndim=2)
def build(self, input_shape):
assert len(input_shape) == 2
input_dim = input_shape[1]
self.input_spec = InputSpec(dtype=K.floatx(), shape=(None, input_dim))
self.clusters = self.add_weight((self.n_clusters, input_dim), initializer='glorot_uniform')
if self.initial_weights is not None:
self.set_weights(self.initial_weights)
del self.initial_weights
self.built = True
def call(self, inputs, **kwargs):
q = 1.0 / (1.0 + (K.sum(K.square(K.expand_dims(inputs, axis=1) - self.clusters), axis=2) / self.alpha))
q **= (self.alpha + 1.0) / 2.0
q = K.transpose(K.transpose(q) / K.sum(q, axis=1)) # Make sure each sample's 10 values add up to 1.
return q
def compute_output_shape(self, input_shape):
assert input_shape and len(input_shape) == 2
return input_shape[0], self.n_clusters
def get_config(self):
config = {'n_clusters': self.n_clusters}
base_config = super(ClusteringLayer, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
clustering_layer = ClusteringLayer(n_clusters, name='clustering')(encoder.output)
model = Model(inputs=encoder.input, outputs=clustering_layer)
model.compile(optimizer=SGD(0.01, 0.9), loss='kld')
model.get_layer(name='clustering').set_weights([kmeans.cluster_centers_])
encoder.output
clustering_layer
784 image input -> 10 classification
The result of
from tensorflow.python import keras
print(keras.__version__)
is
2.2.4-tf
You can even download the docker with keras installation at repbioinfo/autoencoderforclustering

Answer 1

I have solved the error, just correct these line
self.clusters = self.add_weight(shape = (self.n_clusters, input_dim),
initializer='glorot_uniform', name='clusters')
instead of
self.clusters = self.add_weight((self.n_clusters, input_dim), initializer='glorot_uniform')