III · Layers

Chapter 25

layers/convt1 · convt2 · convt3

github.com/openfluke/welvet/layers/convt1✅

Why it exists

Generators and U-Nets need transposed convolution as a peer of CNN, on the same Dense proj surface.

What it is

Scatter upsample + Dense Proj. Full timed matrix + train grids (tiled transpose shaders still §12).

Go example

examples/25-convt/main.go

Run:cd welvet/examples/25-convt && source ../env.sh && go run .
package main

import (
	"fmt"

	"github.com/openfluke/welvet/core"
	"github.com/openfluke/welvet/layers/convt1"
)

func main() {
	l, err := convt1.New(convt1.Config{InChannels: 4, Filters: 2, SeqLen: 8, Kernel: 3, Stride: 2})
	if err != nil {
		panic(err)
	}
	x := core.NewTensor[float32](1, 4, 8)
	_, y, err := convt1.Forward(l, x)
	fmt.Println(y.Shape, err)
}

Output

exit 0 · last run via go run .

[1 2 17] <nil>