5,337
edits
TensorFlow: Difference between revisions
→Matrix Multiplication
| Line 128: | Line 128: | ||
===Matrix Multiplication=== | ===Matrix Multiplication=== | ||
The two matrix multiplication operators are: | The two matrix multiplication operators are: | ||
* <code>tf.linalg.matmul</code> (also aliased as <code>tf.matmul</code>) | * [https://www.tensorflow.org/api_docs/python/tf/linalg/matmul <code>tf.linalg.matmul</code>] (also aliased as <code>tf.matmul</code>) | ||
* <code>tf.linalg.matvec</code> | * [https://www.tensorflow.org/api_docs/python/tf/linalg/matvec <code>tf.linalg.matvec</code>] | ||
New: With both operators, the first few dimensions can now be the batch size. | New: With both operators, the first few dimensions can now be the batch size. | ||
E.g. If A is \(b_1 \times b_2 \times 3 \times 3\) and \(B\) is \(b_1 \times b_2 \times 3\), you can multiply them with \(C = \operatorname{tf.linalg.matvec}(A,B)\) and \(C\) will be \(b_1 \times b_2 \times 3\). | E.g. If \(A\) is \(b_1 \times b_2 \times 3 \times 3\) and \(B\) is \(b_1 \times b_2 \times 3\), you can multiply them with \(C = \operatorname{tf.linalg.matvec}(A,B)\) and \(C\) will be \(b_1 \times b_2 \times 3\). | ||
Also the batch size in A can be 1 and it will properly broadcast to the same size as \(B\). | Also the batch size in A can be 1 and it will properly broadcast to the same size as \(B\). | ||