Esempio n. 1
0
func TestHMMChain(t *testing.T) {

	r := rand.New(rand.NewSource(444))
	numModels := 20
	dim := 4 //8
	maxNumStates := 6
	iter0 := 1 // from alignments
	iter1 := 2 // FB
	ntrain0 := 1000
	ntrain1 := 20000
	maxChainLen := 8     // max number of nets in chain.
	numTestItems := 1000 // num test sequences.
	maxTestLen := 10

	// Create reference HMM to generate random sequences.
	ms0, _ := NewSet()
	for q := 0; q < numModels; q++ {
		ns := int(r.Intn(maxNumStates-2) + 3)
		id := "m" + strconv.FormatInt(int64(q), 10)
		net, e := addRandomNet(r, ms0, id, ns, dim)
		if e != nil {
			t.Fatal(e)
		}
		_ = net
	}
	hmm0 := NewModel(OSet(ms0), OAssign(DirectAssigner{}), UpdateTP(true), UpdateOP(true))
	t.Log("hmm0: ", hmm0)

	// Create random HMM and estimate params using the randomly generated sequences.
	ms, e := initRandomSet(r, ms0)
	if e != nil {
		t.Fatal(e)
	}
	//	hmm := NewModel(OSet(ms), OAssign(DirectAssigner{}), UpdateTP(true), UpdateOP(true))
	hmm := NewModel(OSet(ms), OAssign(DirectAssigner{}), UseAlignments(true))
	t.Log("initial hmm: ", hmm)

	numFrames := 0
	t0 := time.Now() // Start timer.
	t.Log("start training from alignments")
	for i := 0; i < iter0; i++ {
		t.Logf("iter [%d]", i)

		// Make sure we generate the same data in each iteration.
		r := rand.New(rand.NewSource(33))
		gen := newChainGen(r, true, maxChainLen, ms0.Nets...)

		// Reset all counters.
		hmm.Clear()

		// fix the seed to get the same sequence
		for j := 0; j < ntrain0; j++ {
			obs, states := gen.next("oid-" + fi(j))
			numFrames += len(states) - 2
			hmm.UpdateOne(obs, 1.0)
		}
		hmm.Estimate()
	}

	t.Log("start training using forward-backward algo")
	hmm.SetFlags(false, true, true)
	for i := 0; i < iter1; i++ {
		t.Logf("iter [%d]", i)

		// Make sure we generate the same data in each iteration.
		r := rand.New(rand.NewSource(55))
		gen := newChainGen(r, true, maxChainLen, ms0.Nets...)

		// Reset all counters.
		hmm.Clear()

		// fix the seed to get the same sequence
		for j := 0; j < ntrain1; j++ {
			obs, states := gen.next("oid-" + fi(j))
			numFrames += len(states) - 2
			hmm.UpdateOne(obs, 1.0)
		}
		hmm.Estimate()
	}

	dur := time.Now().Sub(t0)
	t.Log("dur: ", dur)

	for name, net0 := range ms0.byName {
		net := ms.byName[name]
		h0 := net0.A
		h := net.A
		tp0 := narray.Exp(nil, h0.Copy())
		tp := narray.Exp(nil, h.Copy())
		ns := tp.Shape[0]
		for i := 0; i < ns; i++ {
			for j := 0; j < ns; j++ {
				p0 := tp0.At(i, j)
				logp0 := h0.At(i, j)
				p := tp.At(i, j)
				logp := h.At(i, j)
				if p > smallNumber || p0 > smallNumber {
					t.Logf("name: %s, %d=>%d, p0:%5.2f, p:%5.2f, logp0:%8.5f, logp:%8.5f", name, i, j, p0, p, logp0, logp)
				}
			}
		}
		t.Log("")
		for i := 1; i < ns-1; i++ {
			t.Logf("hmm0 state:%d, %s", i, net0.B[i])
			t.Logf("hmm  state:%d, %s", i, net.B[i])
			t.Log("")
		}
	}

	t.Log("final hmm: ", hmm)

	// Print time stats.
	t.Log("")
	t.Logf("Total time: %v", dur)
	t.Logf("Time per iteration: %v", dur/time.Duration(iter1))
	t.Logf("Time per frame: %v", dur/time.Duration(iter1*numFrames*ntrain1))

	// Recognize.
	g := ms.SearchGraph()

	dec, e := graph.NewDecoder(g)
	if e != nil {
		t.Fatal(e)
	}

	r = rand.New(rand.NewSource(5151))
	gen := newChainGen(r, true, maxTestLen, ms0.Nets...)
	testDecoder(t, gen, dec, numTestItems)

}
Esempio n. 2
0
// should be equivalent to training a single gaussian, great for debugging.
func TestSingleState(t *testing.T) {

	// HMM to generate data.
	g01 := gm.NewModel(1, gm.Name("g01"), gm.Mean([]float64{0}), gm.StdDev([]float64{1}))

	h0 := narray.New(3, 3)
	h0.Set(1, 0, 1)
	h0.Set(.8, 1, 1)
	h0.Set(.2, 1, 2)
	h0 = narray.Log(nil, h0.Copy())

	ms0, _ := NewSet()
	net0, e0 := ms0.NewNet("hmm", h0,
		[]model.Modeler{nil, g01, nil})
	fatalIf(t, e0)
	hmm0 := NewModel(OSet(ms0))
	_ = hmm0

	// Create gaussian to estimate without using the HMM code.
	g := gm.NewModel(1, gm.Name("g1"), gm.Mean([]float64{-1}), gm.StdDev([]float64{2}))

	// Create initial HMM and estimate params from generated data.
	g1 := gm.NewModel(1, gm.Name("g1"), gm.Mean([]float64{-1}), gm.StdDev([]float64{2}))

	h := narray.New(3, 3)
	h.Set(1, 0, 1)
	h.Set(.5, 1, 1)
	h.Set(.5, 1, 2)
	h = narray.Log(nil, h.Copy())

	ms, _ = NewSet()
	net, e := ms.NewNet("hmm", h,
		[]model.Modeler{nil, g1, nil})
	fatalIf(t, e)
	hmm := NewModel(OSet(ms), UpdateTP(true), UpdateOP(true))

	iter := 5
	// number of sequences
	m := 1000
	numFrames := 0
	t0 := time.Now() // Start timer.
	for i := 0; i < iter; i++ {
		t.Logf("iter [%d]", i)

		// Make sure we generate the same data in each iteration.
		r := rand.New(rand.NewSource(33))
		gen := newGenerator(r, false, net0)

		// Reset all counters.
		hmm.Clear()
		g.Clear()

		// fix the seed to get the same sequence
		for j := 0; j < m; j++ {
			obs, states := gen.next("oid-" + fi(j))
			numFrames += len(states) - 2
			hmm.UpdateOne(obs, 1.0)

			// Update Gaussian
			for _, o := range obs.ValueAsSlice() {
				vec := o.([]float64)
				gobs := model.NewFloatObs(vec, model.SimpleLabel(""))
				g.UpdateOne(gobs, 1.0)
			}
		}
		hmm.Estimate()
		g.Estimate()
		t.Logf("iter:%d, hmm g1:   %+v", i, net.B[1])
		t.Logf("iter:%d, direct g1:%+v", i, g)
	}
	dur := time.Now().Sub(t0)
	tp0 := narray.Exp(nil, h0.Copy())
	tp := narray.Exp(nil, net.A.Copy())
	ns := tp.Shape[0]
	for i := 0; i < ns; i++ {
		for j := 0; j < ns; j++ {
			p0 := tp0.At(i, j)
			logp0 := h0.At(i, j)
			p := tp.At(i, j)
			logp := h.At(i, j)
			if p > smallNumber || p0 > smallNumber {
				t.Logf("TP: %d=>%d, p0:%5.2f, p:%5.2f, logp0:%8.5f, logp:%8.5f", i, j, p0, p, logp0, logp)
			}
		}
	}

	t.Log("")
	t.Logf("hmm0 g1:%+v", net0.B[1])
	t.Logf("hmm  g1: %+v", net.B[1])

	t.Log("")
	t.Logf("direct g1:%+v", g)

	// Print time stats.
	t.Log("")
	t.Logf("Total time: %v", dur)
	t.Logf("Time per iteration: %v", dur/time.Duration(iter))
	t.Logf("Time per frame: %v", dur/time.Duration(iter*numFrames*m))

	gjoa.CompareSliceFloat(t, tp0.Data, tp.Data,
		"error in Trans Probs [0]", .03)

	CompareGaussians(t, net0.B[1].(*gm.Model), net.B[1].(*gm.Model), 0.03)

	if t.Failed() {
		t.FailNow()
	}

	// Recognize.
	sg := ms.SearchGraph()

	dec, e := graph.NewDecoder(sg)
	if e != nil {
		t.Fatal(e)
	}

	r := rand.New(rand.NewSource(5151))
	gen := newGenerator(r, true, net0)
	//	testDecoder(t, gen, dec, 1000)
	testDecoder(t, gen, dec, 10)
}
Esempio n. 3
0
func TestHMMGauss(t *testing.T) {

	// Create reference HMM to generate observations.

	g01 := gm.NewModel(1, gm.Name("g01"), gm.Mean([]float64{0}), gm.StdDev([]float64{1}))
	g02 := gm.NewModel(1, gm.Name("g02"), gm.Mean([]float64{16}), gm.StdDev([]float64{2}))

	h0 := narray.New(4, 4)
	h0.Set(.6, 0, 1)
	h0.Set(.4, 0, 2)
	h0.Set(.9, 1, 1)
	h0.Set(.1, 1, 2)
	h0.Set(.7, 2, 2)
	h0.Set(.3, 2, 3)
	h0 = narray.Log(nil, h0.Copy())

	ms0, _ := NewSet()
	net0, e0 := ms0.NewNet("hmm", h0,
		[]model.Modeler{nil, g01, g02, nil})
	fatalIf(t, e0)
	hmm0 := NewModel(OSet(ms0), UpdateTP(true), UpdateOP(true))
	_ = hmm0

	// Create random HMM and estimate params from obs.

	g1 := gm.NewModel(1, gm.Name("g1"), gm.Mean([]float64{-1}), gm.StdDev([]float64{2}))
	g2 := gm.NewModel(1, gm.Name("g2"), gm.Mean([]float64{18}), gm.StdDev([]float64{4}))

	h := narray.New(4, 4)
	h.Set(.5, 0, 1)
	h.Set(.5, 0, 2)
	h.Set(.5, 1, 1)
	h.Set(.5, 1, 2)
	h.Set(.5, 2, 2)
	h.Set(.5, 2, 3)
	h = narray.Log(nil, h.Copy())

	ms, _ = NewSet()
	net, e := ms.NewNet("hmm", h,
		[]model.Modeler{nil, g1, g2, nil})
	fatalIf(t, e)
	hmm := NewModel(OSet(ms), UpdateTP(true), UpdateOP(true))

	iter := 10
	// number of sequences
	m := 500
	numFrames := 0
	t0 := time.Now() // Start timer.
	for i := 0; i < iter; i++ {
		t.Logf("iter [%d]", i)

		// Make sure we generate the same data in each iteration.
		r := rand.New(rand.NewSource(33))
		gen := newGenerator(r, false, net0)

		// Reset all counters.
		hmm.Clear()

		// fix the seed to get the same sequence
		for j := 0; j < m; j++ {
			obs, states := gen.next("oid-" + fi(j))
			numFrames += len(states) - 2
			hmm.UpdateOne(obs, 1.0)
		}
		hmm.Estimate()
	}
	dur := time.Now().Sub(t0)
	tp0 := narray.Exp(nil, h0.Copy())
	tp := narray.Exp(nil, net.A.Copy())
	ns := tp.Shape[0]
	for i := 0; i < ns; i++ {
		for j := 0; j < ns; j++ {
			p0 := tp0.At(i, j)
			logp0 := h0.At(i, j)
			p := tp.At(i, j)
			logp := h.At(i, j)
			if p > smallNumber || p0 > smallNumber {
				t.Logf("TP: %d=>%d, p0:%5.2f, p:%5.2f, logp0:%8.5f, logp:%8.5f", i, j, p0, p, logp0, logp)
			}
		}
	}

	t.Log("")
	t.Logf("hmm0 g1:%+v, g2:%+v", net0.B[1], net0.B[2])
	t.Logf("hmm  g1: %+v, g2:%+v", net.B[1], net.B[2])

	// Print time stats.
	t.Log("")
	t.Logf("Total time: %v", dur)
	t.Logf("Time per iteration: %v", dur/time.Duration(iter))
	t.Logf("Time per frame: %v", dur/time.Duration(iter*numFrames*m))

	gjoa.CompareSliceFloat(t, tp0.Data, tp.Data,
		"error in Trans Probs [0]", .03)

	CompareGaussians(t, net0.B[1].(*gm.Model), net.B[1].(*gm.Model), 0.03)
	CompareGaussians(t, net0.B[2].(*gm.Model), net.B[2].(*gm.Model), 0.03)

	if t.Failed() {
		t.FailNow()
	}

	// Recognize.
	g := ms.SearchGraph()

	dec, e := graph.NewDecoder(g)
	if e != nil {
		t.Fatal(e)
	}

	r := rand.New(rand.NewSource(5151))
	gen := newGenerator(r, true, net0)
	testDecoder(t, gen, dec, 1000)
}