max_pool3d_op

→TensorImplPtr

int max_pool3d_op(const int & x, int KD, int KH, int KW, int stride_d, int stride_h, int stride_w, int pad_d, int pad_h, int pad_w)

Three-dimensional max pooling over a batch of volumes.

Emits the maximum of each $KD \times KH \times KW$ window. Used in video classification and volumetric (CT / MRI) models.

xTensorImplPtr

Input of shape (B, C, D, H, W).

KD, KH, KWint

Per-axis window size.

stride_d, stride_h, stride_wint= None

Per-axis stride. 0 is a sentinel for non-overlapping windows. Default: 0.

pad_d, pad_h, pad_wint= None

Per-axis zero-padding. Default: 0.

TensorImplPtr

Output of shape (B, C, D_out, H_out, W_out).