README
¶
train
this is a simple go wrapper on TensorFlow trainer.
installation
install Go API for TensorFlow https://www.tensorflow.org/install/lang_go
$ go get github.com/sdeoras/comp/nn/nnl1
details
it implements a simple linear model in the form:
y = x * W + B
where, x is input, W is weights matrix and B is biases matrix
a new trainer can be initialized as follows:
func New(numFeatures, numClasses int, learningRate float64) (*Op, error) {...}
// numFeatures is the number of features per observation
// numClasses is the number of classes prediction is required for.
// and learning rate, (start with 0.0003)
Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Op ¶
func New ¶
func New(numFeatures, numClasses int, learningRate float64, name, logdir string, options *tf.SessionOptions) (*Op, error)
New provides a new trainer operator that can be used to feed taining data and step through training process.
func NewOperator ¶
func NewOperator(options *tf.SessionOptions) (*Op, error)
NewOperator provides an instance of new operator for interfacing with TF.
func (*Op) Load ¶
func (op *Op) Load(checkPoint *nn.CheckPoint) error
Load loads a given checkpoitn into current training session of receiver.
Source Files
Click to show internal directories.
Click to hide internal directories.