← OpenFluke

III · Layers

Chapter 20

layers/cnn1 · cnn2 · cnn3

github.com/openfluke/welvet/layers/cnn2✅

Why it exists

Conv nets must sit on the same dtype×quant×backend matrix as Dense. im2col → Dense GEMV is the intentional first cut.

What it is

cnn1/cnn2/cnn3: host im2col then Proj Dense. Full timed matrices. Tiled conv shaders still ⬜.

Go example

examples/20-cnn/main.go

Run:cd welvet/examples/20-cnn && source ../env.sh && go run .
package main

import (
	"fmt"

	"github.com/openfluke/welvet/core"
	"github.com/openfluke/welvet/layers/cnn2"
)

func main() {
	l, err := cnn2.New(cnn2.Config{
		InChannels: 1, Filters: 4, Height: 8, Width: 8, Kernel: 3, Stride: 1,
	})
	if err != nil {
		panic(err)
	}
	x := core.NewTensor[float32](1, 1, 8, 8)
	_, y, err := cnn2.Forward(l, x)
	fmt.Println(y.Shape, err)
}

Output

exit 0 · last run via go run .

[1 4 6 6] <nil>