Conv2d
2-D convolution, matching torch.nn.Conv2d.
class Conv2d : Module— python/vkml/nn.py:659
Calls conv2d, which lowers to im2col followed by matmul — so every GEMM improvement reaches this layer for free, and so does the im2col memory expansion.
⚠ Warning
Grouped and depthwise convolution are not supported; the weight's input channels must equal the input's.
Construction¶
__init__¶
def __init__self, in_channels: int, out_channels: int, kernel_size, stride=1, padding=0, dilation=1, bias: bool=True— python/vkml/nn.py:670
Forward¶
forward¶
def forwardself, x: V.Tensor -> V.Tensor— python/vkml/nn.py:693