SliceOperation

Description

Extracts a slice with a specified size from a start location of the input tensor.

Operator Context

Figure 1 Context of the SliceOperation operator

Definition

struct SliceParam {
    SVector<int64_t> offsets;
    SVector<int64_t> size;
    uint8_t rsv[8] = {0};
};

Parameters

Input

Output

Restrictions

• If offsets[i] is less than 0, the access starts from the ith highest dimension. For example, if offsets is –1 and the dimension of input x is dimNum, the start position of the ith dimension slice is dimNum – 1.
• If offsets[i] is less than 0 and the dimension size of the ith dimension is dimNum, the sum of dimNum and offsets[i] must be greater than or equal to 0.
• When size[i] = -1, it indicates that the end of the slice is the last location of the ith dimension. If the dimension size of the ith dimension is dimNum, the end location is dimNum - 1.
• The element of size must be greater than or equal to -1. offsets[i] + size[i] must be within the range of the ith dimension of x.

Example API Call

• Input

  x = [[ -78.9,   78.8,  32.22,   49.7,  82.8, 24.77],
       [  72.2,  20.89,  55.16,   85.5,  72.8,  94.8],
      [ 11.36, -83.56,  65.94, -46.94, 72.44,  68.7]]
  offsets = [1, 2]
      
  size = [2, 4]

  In dimension 0, the slice length is 2 from index 1.

  In the first dimension, the slice length is 4 (2 + 4 < = 6) from index 2.

• Output

  y.dim = [2, 4]
  y = [[ 55.1562,  85.5000,  72.8125,  94.8125],
       [ 65.9375, -46.9375,  72.4375,  68.6875]]

  If the dimension of size is -1, the output shape is automatically derived.