[−][src]Function autograd::ops::batch_matmul_t
pub fn batch_matmul_t<T, A, B>(
a: A,
b: B,
trans_a: bool,
trans_b: bool
) -> Tensor<T> where
T: Float,
A: AsRef<Tensor<T>>,
B: AsRef<Tensor<T>>,
Batched matrix multiplication with inputs's transposition.
The rank of a
and b
must be equals.
extern crate autograd as ag; let ref a: ag::Tensor<f32> = ag::zeros(&[2, 3, 2, 4]); let ref b: ag::Tensor<f32> = ag::zeros(&[2, 3, 2, 3]); let ref c = ag::batch_matmul_t(a, b, true, false); assert_eq!(c.eval(&[]).unwrap().shape(), &[2, 3, 4, 3]);
This function supports only f32 and f64. For detailed description, see https://www.tensorflow.org/api_docs/python/tf/matmul