avg_pool1d_op

→TensorImplPtr

int avg_pool1d_op(const int & x, int KL, int stride_l, int pad_l)

One-dimensional average pooling over a batch of sequences.

Emits the arithmetic mean of each sliding window of length KL.

xTensorImplPtr

Input of shape (B, C, L).

KLint

Window length.

stride_lint= None

Stride. 0 is a sentinel meaning "use KL". Default: 0.

pad_lint= None

Zero-padding added to both ends. Default: 0.

TensorImplPtr

Output of shape (B, C, L_out) where $L_\text{out} = \lfloor (L + 2 p - KL)/s + 1 \rfloor$ .

Loading…