ggml_conv_2d_dw_direct

Direct depthwise 2D convolution without an explicit im2col intermediate.

Provides 'R' bindings to the 'GGML' tensor library for machine
learning, optimized for 'Vulkan' GPU acceleration with a transparent CPU
fallback. The package features a 'Keras'-like sequential API and a
'PyTorch'-style 'autograd' engine for building, training, and deploying
neural networks. Key capabilities include high-performance 5D tensor
operations, 'f16' precision, and efficient quantization. It supports
native 'ONNX' model import (50+ operators) and 'GGUF' weight loading
from the 'llama.cpp' and 'Hugging Face' ecosystems. Designed for
zero-overhead inference via dedicated weight buffering, it integrates
seamlessly as a 'parsnip' engine for 'tidymodels' and provides
first-class learners for the 'mlr3' framework.
See <https://github.com/ggml-org/ggml> for more information about the
underlying library.

Yuri Baramykov

ggmlR

'GGML' Tensor Operations for Machine Learning

ggml_conv_2d_dw_direct function

<dl><dt>ctx</dt>
<dd>GGML context</dd>
<dt>a</dt>
<dd>Convolution kernel tensor</dd>
<dt>b</dt>
<dd>Input data tensor</dd>
<dt>s0, s1</dt>
<dd>Strides along dim 0 and 1 (default 1)</dd>
<dt>p0, p1</dt>
<dd>Padding along dim 0 and 1 (default 0)</dd>
<dt>d0, d1</dt>
<dd>Dilation along dim 0 and 1 (default 1)</dd></dl>

Arguments

Depthwise 2D Convolution, direct (Graph) — ggml_conv_2d_dw_direct

<dl>

<dt>ctx</dt>
<dd>GGML context</dd>


<dt>a</dt>
<dd>Convolution kernel tensor</dd>


<dt>b</dt>
<dd>Input data tensor</dd>


<dt>s0, s1</dt>
<dd>Strides along dim 0 and 1 (default 1)</dd>


<dt>p0, p1</dt>
<dd>Padding along dim 0 and 1 (default 0)</dd>


<dt>d0, d1</dt>
<dd>Dilation along dim 0 and 1 (default 1)</dd>

</dl>

ggml_conv_2d_dw_direct: Depthwise 2D Convolution, direct (Graph)

Description

Usage

Value

Arguments