// NewNetworkBlock creates a NetworkBlock.
func NewNetworkBlock(n neuralnet.Network, stateSize int) *NetworkBlock {
return &NetworkBlock{
batcherBlock: &BatcherBlock{
B: n.BatchLearner(),
StateSize: stateSize,
Start: &autofunc.Variable{Vector: make(linalg.Vector, stateSize)},
},
network: n,
}
}
func TestStackedBlock(t *testing.T) {
testVars := []*autofunc.Variable{
{Vector: []float64{0.098591, -0.595453, -0.751214, 0.266051}},
{Vector: []float64{0.988517, 0.107284, -0.331529, 0.028565}},
{Vector: []float64{-0.150604, 0.889039, 0.120916, 0.240999}},
{Vector: []float64{0.961058, 0.878608, 0.052284, -0.635746}},
{Vector: []float64{0.31415, -0.2718}},
{Vector: []float64{-0.6}},
}
testSeqs := [][]*autofunc.Variable{
{testVars[0], testVars[2]},
{testVars[1]},
{testVars[2], testVars[1], testVars[3]},
}
testRV := autofunc.RVector{
testVars[0]: []float64{0.62524, 0.52979, 0.33020, 0.54462},
testVars[1]: []float64{0.13498, 0.12607, 0.35989, 0.23255},
testVars[2]: []float64{0.85996, 0.68435, 0.68506, 0.96907},
testVars[3]: []float64{0.79095, 0.33867, 0.86759, 0.16159},
testVars[4]: []float64{-0.79095, 0.33867},
testVars[5]: []float64{0.33867},
}
net1 := neuralnet.Network{
&neuralnet.DenseLayer{
InputCount: 6,
OutputCount: 6,
},
&neuralnet.HyperbolicTangent{},
}
net1.Randomize()
net2 := neuralnet.Network{
&neuralnet.DenseLayer{
InputCount: 5,
OutputCount: 5,
},
&neuralnet.HyperbolicTangent{},
}
net2.Randomize()
block := &rnn.StackedBlock{
&rnn.BatcherBlock{B: net1.BatchLearner(), StateSize: 2, Start: testVars[4]},
&rnn.BatcherBlock{B: net2.BatchLearner(), StateSize: 1, Start: testVars[5]},
}
checker := &BlockChecker{
B: block,
Input: testSeqs,
Vars: testVars,
RV: testRV,
}
checker.FullCheck(t)
}
func TestStateOutBlock(t *testing.T) {
net := neuralnet.Network{
&neuralnet.DenseLayer{
InputCount: 8,
OutputCount: 4,
},
&neuralnet.HyperbolicTangent{},
}
net.Randomize()
startVar := &autofunc.Variable{Vector: []float64{0.3, -0.3, 0.2, 0.5}}
block := &rnn.StateOutBlock{
Block: &rnn.BatcherBlock{
B: net.BatchLearner(),
StateSize: 4,
Start: startVar,
},
}
learner := append(stateOutBlockLearner{startVar}, net.Parameters()...)
NewChecker4In(block, learner).FullCheck(t)
}
func TestBaselineChecks(t *testing.T) {
network := neuralnet.Network{
&neuralnet.DenseLayer{
InputCount: 4,
OutputCount: 6,
},
neuralnet.HyperbolicTangent{},
}
network.Randomize()
for stateSize := 0; stateSize < 4; stateSize++ {
start := &autofunc.Variable{Vector: make(linalg.Vector, stateSize)}
for i := range start.Vector {
start.Vector[i] = rand.NormFloat64()
}
toTest := &rnn.BlockSeqFunc{
B: &rnn.BatcherBlock{
B: network.BatchLearner(),
StateSize: stateSize,
Start: start,
},
}
seqs, rv := randBaselineTestSeqs(network, 4-stateSize)
rv[start] = make(linalg.Vector, len(start.Vector))
for i := range rv[start] {
rv[start][i] = rand.NormFloat64()
}
vars := make([]*autofunc.Variable, 0, len(rv))
for v := range rv {
vars = append(vars, v)
}
checker := &functest.SeqRFuncChecker{
F: toTest,
Vars: vars,
Input: seqs,
RV: rv,
}
checker.FullCheck(t)
}
}
func trainClassifier(n neuralnet.Network, d mnist.DataSet) {
log.Println("Training classifier (ctrl+C to finish)...")
killChan := make(chan struct{})
go func() {
c := make(chan os.Signal, 1)
signal.Notify(c, os.Interrupt)
<-c
signal.Stop(c)
fmt.Println("\nCaught interrupt. Ctrl+C again to terminate.")
close(killChan)
}()
inputs := make([]linalg.Vector, len(d.Samples))
outputs := make([]linalg.Vector, len(d.Samples))
for i, x := range d.IntensityVectors() {
inputs[i] = x
}
for i, x := range d.LabelVectors() {
outputs[i] = x
}
samples := neuralnet.VectorSampleSet(inputs, outputs)
batcher := &neuralnet.BatchRGradienter{
Learner: n.BatchLearner(),
CostFunc: neuralnet.MeanSquaredCost{},
}
crossValidation := mnist.LoadTestingDataSet()
sgd.SGDInteractive(batcher, samples, ClassifierStepSize,
ClassifierBatchSize, func() bool {
printScore("Training", n, d)
printScore("Cross", n, crossValidation)
return true
})
}
func TrainCmd(netPath, dirPath string) {
log.Println("Loading samples...")
images, width, height, err := LoadTrainingImages(dirPath)
if err != nil {
fmt.Fprintln(os.Stderr, err)
os.Exit(1)
}
log.Println("Creating network...")
var network neuralnet.Network
networkData, err := ioutil.ReadFile(netPath)
if err == nil {
network, err = neuralnet.DeserializeNetwork(networkData)
if err != nil {
fmt.Fprintln(os.Stderr, "Failed to load network:", err)
os.Exit(1)
}
log.Println("Loaded network from file.")
} else {
mean, stddev := sampleStatistics(images)
convLayer := &neuralnet.ConvLayer{
FilterCount: FilterCount,
FilterWidth: 4,
FilterHeight: 4,
Stride: 2,
InputWidth: width,
InputHeight: height,
InputDepth: ImageDepth,
}
maxLayer := &neuralnet.MaxPoolingLayer{
XSpan: 3,
YSpan: 3,
InputWidth: convLayer.OutputWidth(),
InputHeight: convLayer.OutputHeight(),
InputDepth: convLayer.OutputDepth(),
}
convLayer1 := &neuralnet.ConvLayer{
FilterCount: FilterCount1,
FilterWidth: 3,
FilterHeight: 3,
Stride: 2,
InputWidth: maxLayer.OutputWidth(),
InputHeight: maxLayer.OutputHeight(),
InputDepth: maxLayer.InputDepth,
}
network = neuralnet.Network{
&neuralnet.RescaleLayer{
Bias: -mean,
Scale: 1 / stddev,
},
convLayer,
neuralnet.HyperbolicTangent{},
maxLayer,
neuralnet.HyperbolicTangent{},
convLayer1,
neuralnet.HyperbolicTangent{},
&neuralnet.DenseLayer{
InputCount: convLayer1.OutputWidth() * convLayer1.OutputHeight() *
convLayer1.OutputDepth(),
OutputCount: HiddenSize,
},
neuralnet.HyperbolicTangent{},
&neuralnet.DenseLayer{
InputCount: HiddenSize,
OutputCount: len(images),
},
&neuralnet.LogSoftmaxLayer{},
}
network.Randomize()
log.Println("Created new network.")
}
samples := neuralSamples(images)
sgd.ShuffleSampleSet(samples)
validationCount := int(ValidationFraction * float64(samples.Len()))
validationSamples := samples.Subset(0, validationCount)
trainingSamples := samples.Subset(validationCount, samples.Len())
costFunc := neuralnet.DotCost{}
gradienter := &sgd.Adam{
Gradienter: &neuralnet.BatchRGradienter{
Learner: network.BatchLearner(),
CostFunc: &neuralnet.RegularizingCost{
Variables: network.Parameters(),
Penalty: Regularization,
CostFunc: costFunc,
},
},
}
sgd.SGDInteractive(gradienter, trainingSamples, StepSize, BatchSize, func() bool {
log.Printf("Costs: validation=%d/%d cost=%f",
countCorrect(network, validationSamples), validationSamples.Len(),
neuralnet.TotalCost(costFunc, network, trainingSamples))
return true
})
data, _ := network.Serialize()
if err := ioutil.WriteFile(netPath, data, 0755); err != nil {
fmt.Fprintln(os.Stderr, "Failed to save:", err)
os.Exit(1)
}
}
// TestBaselineOutput makes sure that the BatcherBlock +
// BlockSeqFunc combo produces the right output, since
// that combo will be used for the rest of the tests.
func TestBaselineOutput(t *testing.T) {
network := neuralnet.Network{
&neuralnet.DenseLayer{
InputCount: 4,
OutputCount: 6,
},
neuralnet.HyperbolicTangent{},
}
network.Randomize()
for stateSize := 0; stateSize < 4; stateSize++ {
start := &autofunc.Variable{Vector: make(linalg.Vector, stateSize)}
for i := range start.Vector {
start.Vector[i] = rand.NormFloat64()
}
toTest := rnn.BlockSeqFunc{
B: &rnn.BatcherBlock{
B: network.BatchLearner(),
StateSize: stateSize,
Start: start,
},
}
seqs, rv := randBaselineTestSeqs(network, 4-stateSize)
rv[start] = make(linalg.Vector, len(start.Vector))
for i := range rv[start] {
rv[start][i] = rand.NormFloat64()
}
res := toTest.ApplySeqsR(rv, seqfunc.VarRResult(rv, seqs))
actual := res.OutputSeqs()
actualR := res.ROutputSeqs()
expected, expectedR := manualNetworkSeq(rv, network, start, seqs, stateSize)
if len(expected) != len(actual) {
t.Errorf("stateSize %d: len(expected) [%d] != len(actual) [%d]", stateSize,
len(expected), len(actual))
continue
}
for i, act := range actual {
actR := actualR[i]
exp := expected[i]
expR := expectedR[i]
if len(act) != len(exp) {
t.Errorf("stateSize %d seq %d: len(act) [%d] != len(exp) [%d]",
stateSize, i, len(act), len(act))
continue
}
for j, a := range act {
x := exp[j]
if len(a) != len(x) || x.Copy().Scale(-1).Add(a).MaxAbs() > 1e-5 {
t.Errorf("stateSize %d seq %d entry %d: expected %v got %v",
stateSize, i, j, x, a)
}
}
for j, a := range actR {
x := expR[j]
if len(a) != len(x) || x.Copy().Scale(-1).Add(a).MaxAbs() > 1e-5 {
t.Errorf("stateSize %d seq %d entry %d (R): expected %v got %v",
stateSize, i, j, x, a)
}
}
}
}
}