CODEWITHSUNDEEP
tensorflowmachine-learningkeras
Funzo
Funzo

Reputation: 1290

Keras' equivalent to Tensorflow's matmul function

I'm new to Keras and I can't seem to find an equivalent to Pytorchs bmm function or Tensorflows matmul function.

What would be the closest equivalent to this in Keras?

Upvotes: 2

Views: 1714

Answers (3)

KonstantinosKokos
KonstantinosKokos

Reputation: 3453

Backend functions simply point back to their tensorflow/theano sources and cannot be used as is. To use them you need to wrap them into a Lambda layer:

from keras.layers import Lambda
from keras import backend as K
# this is simply defining the function
matmul = Lambda ( lambda x: K.dot(x[0], x[1]) )
# this is applying the function
tensor_product = matmul([tensor1, tensor2])

Not wrapping backend functions into Lambda layers will result in TypeError. Alternatively you can use the Dot layer which computes the dot product across an axis of your choice:

from keras.layers import Dot
tensor_product = Dot(axes=-1)([tensor1, tensor2])

Upvotes: 0

Santi Iglesias
Santi Iglesias

Reputation: 464

Tecnically.. I think the direct equivalent to tf.matmul is K.batch_dot. this way you do not use the batch dimension.

Upvotes: 0

Jakub Bartczuk
Jakub Bartczuk

Reputation: 2378

keras.backend.dot

From the documentation:

Multiplies 2 tensors (and/or variables) and returns a tensor.

Upvotes: 2

Related Questions