diff options
| -rw-r--r-- | tensorflow/contrib/layers/python/layers/layers.py | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/tensorflow/contrib/layers/python/layers/layers.py b/tensorflow/contrib/layers/python/layers/layers.py index 350bcb3bca..10d7f6d076 100644 --- a/tensorflow/contrib/layers/python/layers/layers.py +++ b/tensorflow/contrib/layers/python/layers/layers.py @@ -3045,16 +3045,16 @@ def legacy_fully_connected(x, `activation_fn` is `None`, the result of `y = w * x + b` is returned. - If `x` has shape [\\\(\\text{dim}_0, \\text{dim}_1, ..., \\text{dim}_n\\\)] - with more than 2 dimensions (\\\(n > 1\\\)), then we repeat the matrix + If `x` has shape [\\(\text{dim}_0, \text{dim}_1, ..., \text{dim}_n\\)] + with more than 2 dimensions (\\(n > 1\\)), then we repeat the matrix multiply along the first dimensions. The result r is a tensor of shape - [\\\(\\text{dim}_0, ..., \\text{dim}_{n-1},\\\) `num_output_units`], - where \\\( r_{i_0, ..., i_{n-1}, k} = - \\sum_{0 \\leq j < \\text{dim}_n} x_{i_0, ... i_{n-1}, j} \cdot w_{j, k}\\\). + [\\(\text{dim}_0, ..., \text{dim}_{n-1},\\) `num_output_units`], + where \\( r_{i_0, ..., i_{n-1}, k} = + \sum_{0 \leq j < \text{dim}_n} x_{i_0, ... i_{n-1}, j} \cdot w_{j, k}\\). This is accomplished by reshaping `x` to 2-D - [\\\(\\text{dim}_0 \\cdot ... \\cdot \\text{dim}_{n-1}, \\text{dim}_n\\\)] + [\\(\text{dim}_0 \cdot ... \cdot \text{dim}_{n-1}, \text{dim}_n\\)] before the matrix multiply and afterwards reshaping it to - [\\\(\\text{dim}_0, ..., \\text{dim}_{n-1},\\\) `num_output_units`]. + [\\(\text{dim}_0, ..., \text{dim}_{n-1},\\) `num_output_units`]. This op creates `w` and optionally `b`. Bias (`b`) can be disabled by setting `bias_init` to `None`. |