[object Object]

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

• Description: Implements 1D convolution where the input and output dimensions are T (temporal or spatial), B (batch), and C (channel).
• Formula: Assume the input self has shape ($H_{\text{in}},N,C_{\text{in}}$) and the output out has shape ($H_{\text{out}},N,C_{\text{out}}$). The output is computed as:$$out_{N_i,C_{out j}} = bias(C_{out j}) + \sum_{k = 0}^{C_{in} - 1} weight(k, C_{out j}) \cdot self(N_i, k)$$ Where $N$ denotes the batch size, $C$ denotes the number of channels, and $H$ denotes the temporal or spatial dimension.

[object Object]

Each operator has [object Object]two-phase API calls[object Object]. You must call aclnnConvTbcGetWorkspaceSize to obtain the workspace size required for computation and the executor that contains the operator execution process, and then call aclnnConvTbc to perform the computation.

[object Object]

• Parameters

  [object Object]

• Return Value

  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]

• Return Value

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

[object Object]

• Deterministic computation:
  • aclnnConvTbc defaults to a deterministic implementation.

[object Object][object Object]

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