conv3d() — pytorch Function Reference

Architecture documentation for the conv3d() function in generate_test_torchscripts.py from the pytorch codebase.

Function python CoreTensor Registration calls 1

Entity Profile

CoreTensor→ Registration→ conv3d() — pytorch Function Reference

Dependency Diagram

graph TD
  efb2e7f7_3652_f8c8_a80d_9d8d754ac1a9["conv3d()"]
  c800a173_9551_2901_c091_d157ae22ae5a["contiguous()"]
  efb2e7f7_3652_f8c8_a80d_9d8d754ac1a9 -->|calls| c800a173_9551_2901_c091_d157ae22ae5a
  style efb2e7f7_3652_f8c8_a80d_9d8d754ac1a9 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

android/pytorch_android/generate_test_torchscripts.py lines 133–139

    def conv3d(self, x: Tensor, w: Tensor, toChannelsLast: bool) -> Tensor:
        r = torch.nn.functional.conv3d(x, w)
        if toChannelsLast:
            r = r.contiguous(memory_format=torch.channels_last_3d)
        else:
            r = r.contiguous()
        return r