Documentation
¶
Overview ¶
Package conv2d implements a 2D bit-convolution layer and combiner
Index ¶
- type Conv2D
- type Conv2DLayer
- func MustNew(width, height, subwidth, subheight, repeat int) *Conv2DLayer
- func MustNew2(width, height, subwidth, subheight, repeat int, shift int) *Conv2DLayer
- func New(width, height, subwidth, subheight, repeat int) (o *Conv2DLayer, err error)
- func New2(width, height, subwidth, subheight, repeat int, shift int) (o *Conv2DLayer, err error)
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Conv2D ¶
type Conv2D struct {
// contains filtered or unexported fields
}
func (*Conv2D) Disregard ¶
Disregard tells whether putting value false at position n would not affect any feature output (as opposed to putting value true at position n). This excludes training samples early which would have no impact, because the next layer would see the same thing regardless of what we put.
type Conv2DLayer ¶
type Conv2DLayer struct {
// contains filtered or unexported fields
}
func MustNew ¶
func MustNew(width, height, subwidth, subheight, repeat int) *Conv2DLayer
MustNew creates a new Conv2D layer with size, subsize and repeat
func MustNew2 ¶ added in v0.0.4
func MustNew2(width, height, subwidth, subheight, repeat int, shift int) *Conv2DLayer
MustNew/ creates a new Conv2D layer with size, subsize and repeat
func New ¶
func New(width, height, subwidth, subheight, repeat int) (o *Conv2DLayer, err error)
New creates a new Conv2D layer with size, subsize and repeat
func New2 ¶ added in v0.0.4
func New2(width, height, subwidth, subheight, repeat int, shift int) (o *Conv2DLayer, err error)
New/ creates a new Conv2D layer with size, subsize and repeat
func (*Conv2DLayer) Lay ¶
func (i *Conv2DLayer) Lay() layer.Combiner
Lay turns Conv2D layer into a combiner