python - tensorflow efficient way for tensor multiplication -

i have 2 tensors in tensorflow, first tensor 3-d, , second 2d. , want multiply them this:

x = tf.placeholder(tf.float32, shape=[sequence_length, batch_size, hidden_num])  w = tf.get_variable("w", [hidden_num, 50])  b = tf.get_variable("b", [50])  output_list = [] step_index in range(sequence_length):     output = tf.matmul(x[step_index,  :,  :], w) + b     output_list.append(output) output = tf.pack(outputs_list) 

i use loop multiply operation, think slow. best way make process simple/clean possible?

you use batch_matmul. unfortunately doesn't seem batch_matmul supports broadcasting along batch dimension, have tile w matrix. use more memory, operations stay in tensorflow

a = tf.ones((5, 2, 3)) b = tf.ones((3, 1)) b = tf.reshape(b, (1, 3, 1)) b = tf.tile(b, [5, 1, 1]) c = tf.batch_matmul(a, b) # use tf.matmul in tf 1.0  sess = tf.interactivesession() sess.run(tf.shape(c)) 

this gives

array([5, 2, 1], dtype=int32)