fn
avg_pool3d_op
→TensorImplPtrint avg_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)Python wrappers
Public Python APIs implemented by this engine symbol.Three-dimensional average pooling over a batch of volumes.
The natural extension of 2-D average pooling for video and volumetric data.
Parameters
xTensorImplPtrInput of shape
(B, C, D, H, W).KD, KH, KWintPer-axis window size.
stride_d, stride_h, stride_wint= NonePer-axis stride;
0 ⇒ K. Default: 0.pad_d, pad_h, pad_wint= NonePer-axis zero-padding. Default:
0.Returns
TensorImplPtrOutput of shape (B, C, D_out, H_out, W_out).