conv

hypercoil.functional.tsconv.conv(input: Tensor, weight: Tensor, bias: Tensor | None = None, stride: int | Sequence[int] = 1, padding: int | Sequence[Tuple[int, int]] = 0, dilation: int | Sequence[int] = 1) → Tensor

torch-like API for convolution. The implementation is basically pilfered from https://stackoverflow.com/questions/69571976/ … … how-to-use-grad-convolution-in-google-jax