Documentation ¶
Overview ¶
Package mnist loads the MNist dataset of handwritten digits.
Index ¶
- Constants
- type Classify
- type Loader
- func (*Loader) Config() *network.Config
- func (*Loader) CreateNetwork(cfg *network.Config, d *network.Dataset) *network.Network
- func (l *Loader) Debug(on bool)
- func (l *Loader) Distort(in, out blas.Matrix, mask int, severity float32)
- func (l *Loader) DistortTypes() []network.Distortion
- func (Loader) Load(samples int) (*network.Dataset, error)
- func (l *Loader) Release()
- type Loader2
Constants ¶
View Source
const ( Scale = 1 Rotate = 2 Elastic = 4 )
supported types of distortion
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Loader ¶
type Loader struct {
// contains filtered or unexported fields
}
func (*Loader) CreateNetwork ¶
func (*Loader) Distort ¶
Distort method is used to apply distortions to a batch of images. mask of -1 indicates all distortions are to be applied.
func (*Loader) DistortTypes ¶
func (l *Loader) DistortTypes() []network.Distortion
DistortTypes returns the supported types of distortions
Click to show internal directories.
Click to hide internal directories.