[object Object]

[object Object][object Object]undefined[object Object]

• Description: Performs two-dimensional and three-dimensional convolution for per-channel quantization. The convolution process is the same as that of aclnnConvolution.

• Formula: Assume that the input shape is $(N, C_{\text{in}}, D, H, W)$, the weight shape is $(C_{\text{out}}, C_{\text{in}}, K_d, K_h, K_w)$, the scale shape is $(C_{\text{out}})$, the bias shape is $C_{\text{out}}$, and the output shape is $(N, C_{\text{out}}, D_{\text{out}}, H_{\text{out}}, W_{\text{out}})$, where $N$ indicates the batch size, $C$ indicates the number of channels, $D$, $H$, and $W$ indicate the depth, height, and width of the sample, respectively, and $K_d$, $K_h$, and $K_w$ indicate the depth, height, and width of the convolution kernel, respectively. Then, the output is expressed as follows:

  $$\text{output}(N_i, C_{\text{out}_j}, D_{\text{out}}, H_{\text{out}}, W_{\text{out}}) = \left[\sum_{k = 0}^{C_{\text{in}} - 1} \text{weight}(C_{\text{out}_j}, k) \star \text{input}(N_i, k)\right] \times \text{scale}(C_{\text{out}_j}) + \text{bias}(C_{\text{out}_j})$$

  where $\star$ indicates convolution compute, which is based on dimension of the convolution input and the convolution type (atrous convolution or group convolution). $N$ indicates the batch size, $C$ indicates the number of channels, and $D$, $H$, and $W$ indicate the depth, height, and width, respectively. The formulas for computing the corresponding output dimensions are as follows:

  $$D_{\text{out}}=[(D + 2 \times padding[0] - dilation[0] \times (K_d - 1) - 1 ) / stride[0]] + 1 \\ H_{\text{out}}=[(H + 2 \times padding[1] - dilation[1] \times (K_h - 1) - 1 ) / stride[1]] + 1 \\ W_{\text{out}}=[(W + 2 \times padding[2] - dilation[2] \times (K_w - 1) - 1 ) / stride[2]] + 1$$

[object Object]

Each operator has [object Object]two-phase API][object Object]. First, [object Object] is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, [object Object] is called to perform computation.

[object Object]

• Parameters

  [object Object]

• Returns

  aclnnStatus: status code. For details, see [object Object]aclnn Return Codes[object Object].

  The first-phase API implements input parameter verification. The following errors may be thrown.

  [object Object]

[object Object]

• Parameters

  [object Object]

• Returns

  aclnnStatus: status code. For details, see [object Object]aclnn Return Codes[object Object].

[object Object]

• Deterministic compute
  • aclnnQuantConvolution defaults to a deterministic implementation.

[object Object][object Object]

The following example is for reference only. For details, see .

For different product models, use different main functions.