コード例 #1
0
    def test_probs(self):
        rbm = RBM(9, 11)
        rbm.W = np.matrix(np.random.randn(rbm.X.shape[0], rbm.Y.shape[0]))
        rbm.b = np.matrix(np.random.rand(rbm.X.shape[0], 1))
        rbm.c = np.matrix(np.random.randn(rbm.Y.shape[0], 1))

        examples_vis = np.matrix(np.random.rand(rbm.X.shape[0], 100) < 0.5)
        examples_hid = np.matrix(np.random.rand(rbm.Y.shape[0], 100) < 0.5)

        states_vis = utils.binary_numbers(rbm.X.shape[0])
        states_hid = utils.binary_numbers(rbm.Y.shape[0])

        # check that conditional probabilities are normalized
        logprobs = rbm._clogprob_vis_hid(states_vis,
                                         examples_hid,
                                         all_pairs=True)
        self.assertTrue(np.all(utils.logsumexp(logprobs, 0) < 1E-10))

        logprobs = rbm._clogprob_hid_vis(examples_vis,
                                         states_hid,
                                         all_pairs=True)
        self.assertTrue(np.all(utils.logsumexp(logprobs, 1) < 1E-10))

        # test for consistency
        logprobs1 = rbm._ulogprob(examples_vis, examples_hid, all_pairs=True)
        logprobs2 = rbm._clogprob_vis_hid(examples_vis, examples_hid, all_pairs=True) \
                  + rbm._ulogprob_hid(examples_hid)
        logprobs3 = rbm._clogprob_hid_vis(examples_vis, examples_hid, all_pairs=True) \
                  + rbm._ulogprob_vis(examples_vis).T
        self.assertTrue(np.all(np.abs(logprobs1 - logprobs2) < 1E-10))
        self.assertTrue(np.all(np.abs(logprobs1 - logprobs3) < 1E-10))
コード例 #2
0
	def test_probs(self):
		rbm = RBM(9, 11)
		rbm.W = np.matrix(np.random.randn(rbm.X.shape[0], rbm.Y.shape[0]))
		rbm.b = np.matrix(np.random.rand(rbm.X.shape[0], 1))
		rbm.c = np.matrix(np.random.randn(rbm.Y.shape[0], 1))

		examples_vis = np.matrix(np.random.rand(rbm.X.shape[0], 100) < 0.5)
		examples_hid = np.matrix(np.random.rand(rbm.Y.shape[0], 100) < 0.5)

		states_vis = utils.binary_numbers(rbm.X.shape[0])
		states_hid = utils.binary_numbers(rbm.Y.shape[0])

		# check that conditional probabilities are normalized
		logprobs = rbm._clogprob_vis_hid(states_vis, examples_hid, all_pairs=True)
		self.assertTrue(np.all(utils.logsumexp(logprobs, 0) < 1E-10))

		logprobs = rbm._clogprob_hid_vis(examples_vis, states_hid, all_pairs=True)
		self.assertTrue(np.all(utils.logsumexp(logprobs, 1) < 1E-10))

		# test for consistency
		logprobs1 = rbm._ulogprob(examples_vis, examples_hid, all_pairs=True)
		logprobs2 = rbm._clogprob_vis_hid(examples_vis, examples_hid, all_pairs=True) \
		          + rbm._ulogprob_hid(examples_hid)
		logprobs3 = rbm._clogprob_hid_vis(examples_vis, examples_hid, all_pairs=True) \
		          + rbm._ulogprob_vis(examples_vis).T
		self.assertTrue(np.all(np.abs(logprobs1 - logprobs2) < 1E-10))
		self.assertTrue(np.all(np.abs(logprobs1 - logprobs3) < 1E-10))
コード例 #3
0
    def test_ais_with_semirbm_dbn(self):
        dbn = DBN(RBM(5, 5))
        dbn.add_layer(SemiRBM(5, 5))

        ais = Estimator(dbn)
        ais.estimate_log_partition_function(100,
                                            np.arange(0, 1, 1E-3),
                                            layer=0)
        ais.estimate_log_partition_function(10, np.arange(0, 1, 1E-3), layer=1)

        dbn[0]._brf_logz = utils.logsumexp(dbn[0]._ulogprob_vis(
            utils.binary_numbers(dbn[0].X.shape[0])))
        dbn[1]._brf_logz = utils.logsumexp(dbn[1]._ulogprob_vis(
            utils.binary_numbers(dbn[1].X.shape[0])))

        samples = np.concatenate(
            [dbn.sample(25, 100, 20),
             np.matrix(np.random.rand(5, 25) > 0.5)], 1)

        Y = utils.binary_numbers(dbn[0].Y.shape[0])
        X = utils.binary_numbers(dbn[0].X.shape[0])

        logRy = dbn[1]._ulogprob_vis(Y)
        logQy = utils.logsumexp(dbn[0]._ulogprob(X, Y, all_pairs=True), 0)
        log_sum = utils.logsumexp(
            dbn[0]._clogprob_hid_vis(samples, Y, all_pairs=True) - logQy +
            logRy, 1)

        logPx = log_sum + dbn[0]._ulogprob_vis(samples) - dbn[1]._brf_logz
        logPx_ = ais.estimate_log_probability(samples)[0]

        self.assertTrue(np.abs(logPx_.mean() - logPx.mean()) < 0.1)
コード例 #4
0
	def test_probabilities(self):
		grbm = GaussianRBM(7, 13)
		grbm.W = np.asmatrix(np.random.randn(grbm.X.shape[0], grbm.Y.shape[0]))
		grbm.b = np.asmatrix(np.random.rand(grbm.X.shape[0], 1))
		grbm.c = np.asmatrix(np.random.randn(grbm.Y.shape[0], 1))
		grbm.sigma = np.random.rand() * 0.5 + 0.5
		grbm.sigma = 1.

		examples_vis = np.asmatrix(np.random.randn(grbm.X.shape[0], 1000) * 2.)
		examples_hid = np.matrix(np.random.rand(grbm.Y.shape[0], 100) < 0.5)

		states_hid = utils.binary_numbers(grbm.Y.shape[0])

		# check that conditional probabilities are normalized
		logprobs = grbm._clogprob_hid_vis(examples_vis, states_hid, all_pairs=True)
		self.assertTrue(np.all(utils.logsumexp(logprobs, 1) < 1E-8))

		# test for consistency
		logprobs1 = grbm._ulogprob(examples_vis, examples_hid, all_pairs=True)
		logprobs2 = grbm._clogprob_vis_hid(examples_vis, examples_hid, all_pairs=True) \
		          + grbm._ulogprob_hid(examples_hid)
		logprobs3 = grbm._clogprob_hid_vis(examples_vis, examples_hid, all_pairs=True) \
		          + grbm._ulogprob_vis(examples_vis).T

		self.assertTrue(np.all(np.abs(logprobs1 - logprobs2) < 1E-10))
		self.assertTrue(np.all(np.abs(logprobs1 - logprobs3) < 1E-3))
コード例 #5
0
	def test_ais_with_dbn(self):
		dbn = DBN(RBM(10, 10))
		dbn.add_layer(RBM(10, 20))

		hidden_states = utils.binary_numbers(dbn[0].Y.shape[0])

		ais = Estimator(dbn)
		ais_logz = ais.estimate_log_partition_function(100, np.sqrt(np.arange(0, 1, 0.001)))
		brf_logz = utils.logsumexp(dbn[1]._ulogprob_vis(hidden_states))

		brf_probs = []
		dbn_probs = []
		dbn_bound = []

		for i in range(50):
			sample = np.matrix(np.random.rand(10, 1)) > 0.5
			
			prob, bound = ais.estimate_log_probability(sample, 200)

			brf_probs.append(utils.logsumexp(dbn[1]._ulogprob_vis(hidden_states) + dbn[0]._clogprob_vis_hid(sample, hidden_states), 1) - brf_logz)
			dbn_probs.append(prob)
			dbn_bound.append(bound)

		self.assertTrue(np.mean(dbn_bound) < np.mean(dbn_probs))
		self.assertTrue(np.abs(np.mean(dbn_probs) - np.mean(brf_probs)) < 0.1)
コード例 #6
0
    def test_probabilities(self):
        grbm = GaussianRBM(7, 13)
        grbm.W = np.asmatrix(np.random.randn(grbm.X.shape[0], grbm.Y.shape[0]))
        grbm.b = np.asmatrix(np.random.rand(grbm.X.shape[0], 1))
        grbm.c = np.asmatrix(np.random.randn(grbm.Y.shape[0], 1))
        grbm.sigma = np.random.rand() * 0.5 + 0.5
        grbm.sigma = 1.

        examples_vis = np.asmatrix(np.random.randn(grbm.X.shape[0], 1000) * 2.)
        examples_hid = np.matrix(np.random.rand(grbm.Y.shape[0], 100) < 0.5)

        states_hid = utils.binary_numbers(grbm.Y.shape[0])

        # check that conditional probabilities are normalized
        logprobs = grbm._clogprob_hid_vis(examples_vis,
                                          states_hid,
                                          all_pairs=True)
        self.assertTrue(np.all(utils.logsumexp(logprobs, 1) < 1E-8))

        # test for consistency
        logprobs1 = grbm._ulogprob(examples_vis, examples_hid, all_pairs=True)
        logprobs2 = grbm._clogprob_vis_hid(examples_vis, examples_hid, all_pairs=True) \
                  + grbm._ulogprob_hid(examples_hid)
        logprobs3 = grbm._clogprob_hid_vis(examples_vis, examples_hid, all_pairs=True) \
                  + grbm._ulogprob_vis(examples_vis).T

        self.assertTrue(np.all(np.abs(logprobs1 - logprobs2) < 1E-10))
        self.assertTrue(np.all(np.abs(logprobs1 - logprobs3) < 1E-3))
コード例 #7
0
    def test_ais_with_dbn(self):
        dbn = DBN(RBM(10, 10))
        dbn.add_layer(RBM(10, 20))

        hidden_states = utils.binary_numbers(dbn[0].Y.shape[0])

        ais = Estimator(dbn)
        ais_logz = ais.estimate_log_partition_function(
            100, np.sqrt(np.arange(0, 1, 0.001)))
        brf_logz = utils.logsumexp(dbn[1]._ulogprob_vis(hidden_states))

        brf_probs = []
        dbn_probs = []
        dbn_bound = []

        for i in range(50):
            sample = np.matrix(np.random.rand(10, 1)) > 0.5

            prob, bound = ais.estimate_log_probability(sample, 200)

            brf_probs.append(
                utils.logsumexp(
                    dbn[1]._ulogprob_vis(hidden_states) +
                    dbn[0]._clogprob_vis_hid(sample, hidden_states), 1) -
                brf_logz)
            dbn_probs.append(prob)
            dbn_bound.append(bound)

        self.assertTrue(np.mean(dbn_bound) < np.mean(dbn_probs))
        self.assertTrue(np.abs(np.mean(dbn_probs) - np.mean(brf_probs)) < 0.1)
コード例 #8
0
ファイル: testsemirbm.py プロジェクト: zm786955593/deepbelief
    def test_probabilities(self):
        srbm = SemiRBM(9, 12)
        srbm.W = np.matrix(np.random.randn(srbm.X.shape[0], srbm.Y.shape[0]))
        srbm.b = np.matrix(np.random.rand(srbm.X.shape[0], 1))
        srbm.c = np.matrix(np.random.randn(srbm.Y.shape[0], 1))
        srbm.L = np.matrix(np.random.randn(srbm.X.shape[0],
                                           srbm.X.shape[0])) / 2.
        srbm.L = np.triu(srbm.L) + np.triu(
            srbm.L).T - 2. * np.diag(np.diag(srbm.L))

        examples_vis = np.matrix(np.random.rand(srbm.X.shape[0], 100) < 0.5)
        examples_hid = np.matrix(np.random.rand(srbm.Y.shape[0], 100) < 0.5)

        states_vis = utils.binary_numbers(srbm.X.shape[0])
        states_hid = utils.binary_numbers(srbm.Y.shape[0])

        # check that conditional probabilities are normalized
        logprobs = srbm._clogprob_hid_vis(examples_vis,
                                          states_hid,
                                          all_pairs=True)
        self.assertTrue(np.all(utils.logsumexp(logprobs, 1) < 1E-10))

        # test for consistency
        logprobs1 = srbm._ulogprob(examples_vis, examples_hid, all_pairs=True)
        logprobs3 = srbm._clogprob_hid_vis(examples_vis, examples_hid, all_pairs=True) \
                  + srbm._ulogprob_vis(examples_vis).T
        self.assertTrue(np.all(np.abs(logprobs1 - logprobs3) < 1E-10))

        rbm = RBM(srbm.X.shape[0], srbm.Y.shape[0])
        rbm.W = srbm.W
        rbm.b = srbm.b
        rbm.c = srbm.c
        srbm.L *= 0

        logprobs1 = rbm._ulogprob_vis(examples_vis)
        logprobs2 = srbm._ulogprob_vis(examples_vis)
        self.assertTrue(np.all(np.abs(logprobs1 - logprobs2) < 1E-10))

        logprobs1 = rbm._clogprob_hid_vis(examples_vis, examples_hid)
        logprobs2 = srbm._clogprob_hid_vis(examples_vis, examples_hid)
        self.assertTrue(np.all(np.abs(logprobs1 - logprobs2) < 1E-10))
コード例 #9
0
	def test_probabilities(self):
		srbm = SemiRBM(9, 12)
		srbm.W = np.matrix(np.random.randn(srbm.X.shape[0], srbm.Y.shape[0]))
		srbm.b = np.matrix(np.random.rand(srbm.X.shape[0], 1))
		srbm.c = np.matrix(np.random.randn(srbm.Y.shape[0], 1))
		srbm.L = np.matrix(np.random.randn(srbm.X.shape[0], srbm.X.shape[0])) / 2.
		srbm.L = np.triu(srbm.L) + np.triu(srbm.L).T - 2. * np.diag(np.diag(srbm.L))

		examples_vis = np.matrix(np.random.rand(srbm.X.shape[0], 100) < 0.5)
		examples_hid = np.matrix(np.random.rand(srbm.Y.shape[0], 100) < 0.5)

		states_vis = utils.binary_numbers(srbm.X.shape[0])
		states_hid = utils.binary_numbers(srbm.Y.shape[0])

		# check that conditional probabilities are normalized
		logprobs = srbm._clogprob_hid_vis(examples_vis, states_hid, all_pairs=True)
		self.assertTrue(np.all(utils.logsumexp(logprobs, 1) < 1E-10))

		# test for consistency
		logprobs1 = srbm._ulogprob(examples_vis, examples_hid, all_pairs=True)
		logprobs3 = srbm._clogprob_hid_vis(examples_vis, examples_hid, all_pairs=True) \
		          + srbm._ulogprob_vis(examples_vis).T
		self.assertTrue(np.all(np.abs(logprobs1 - logprobs3) < 1E-10))

		rbm = RBM(srbm.X.shape[0], srbm.Y.shape[0])
		rbm.W = srbm.W
		rbm.b = srbm.b
		rbm.c = srbm.c
		srbm.L *= 0

		logprobs1 = rbm._ulogprob_vis(examples_vis)
		logprobs2 = srbm._ulogprob_vis(examples_vis)
		self.assertTrue(np.all(np.abs(logprobs1 - logprobs2) < 1E-10))

		logprobs1 = rbm._clogprob_hid_vis(examples_vis, examples_hid)
		logprobs2 = srbm._clogprob_hid_vis(examples_vis, examples_hid)
		self.assertTrue(np.all(np.abs(logprobs1 - logprobs2) < 1E-10))
コード例 #10
0
	def test_ais_with_semirbm_dbn(self):
		dbn = DBN(RBM(5, 5))
		dbn.add_layer(SemiRBM(5, 5))
		
		ais = Estimator(dbn)
		ais.estimate_log_partition_function(100, np.arange(0, 1, 1E-3), layer=0)
		ais.estimate_log_partition_function(10, np.arange(0, 1, 1E-3), layer=1)

		dbn[0]._brf_logz = utils.logsumexp(dbn[0]._ulogprob_vis(utils.binary_numbers(dbn[0].X.shape[0])))
		dbn[1]._brf_logz = utils.logsumexp(dbn[1]._ulogprob_vis(utils.binary_numbers(dbn[1].X.shape[0])))

		samples = np.concatenate([dbn.sample(25, 100, 20), np.matrix(np.random.rand(5, 25) > 0.5)], 1)

		Y = utils.binary_numbers(dbn[0].Y.shape[0])
		X = utils.binary_numbers(dbn[0].X.shape[0])

		logRy = dbn[1]._ulogprob_vis(Y)
		logQy = utils.logsumexp(dbn[0]._ulogprob(X, Y, all_pairs=True), 0)
		log_sum = utils.logsumexp(dbn[0]._clogprob_hid_vis(samples, Y, all_pairs=True) - logQy + logRy, 1)

		logPx = log_sum + dbn[0]._ulogprob_vis(samples) - dbn[1]._brf_logz
		logPx_ = ais.estimate_log_probability(samples)[0]

		self.assertTrue(np.abs(logPx_.mean() - logPx.mean()) < 0.1)
コード例 #11
0
	def test_ais_with_rbm(self):
		rbm = RBM(5, 20)
		rbm.W = np.matrix(np.random.randn(5, 20))
		rbm.b = np.matrix(np.random.randn(5, 1))
		rbm.c = np.matrix(np.random.randn(20, 1))

		ais = Estimator(rbm)

		ais_logz = ais.estimate_log_partition_function(100, np.arange(0, 1, 0.001))
		brf_logz = utils.logsumexp(rbm._ulogprob_vis(utils.binary_numbers(rbm.X.shape[0])))

		lower = np.log(np.exp(ais_logz) - 4. * np.sqrt(rbm._ais_var))
		upper = np.log(np.exp(ais_logz) + 4. * np.sqrt(rbm._ais_var))

		self.assertTrue(upper - lower < 1.)
		self.assertTrue(lower < brf_logz and brf_logz < upper)
コード例 #12
0
	def test_ais_with_gaussianrbm(self):
		rbm = GaussianRBM(30, 10)
		rbm.c = np.matrix(np.random.randn(10, 1))
		rbm.W = np.matrix(np.random.randn(30, 10))
		rbm.b = np.matrix(np.random.rand(30, 1))

		ais = Estimator(rbm)

		ais_logz = ais.estimate_log_partition_function(100, np.arange(0., 1., 1E-4))
		brf_logz = utils.logsumexp(rbm._ulogprob_hid(utils.binary_numbers(rbm.Y.shape[0])))

		lower = np.log(np.exp(ais_logz) - 4 * np.sqrt(rbm._ais_var))
		upper = np.log(np.exp(ais_logz) + 4 * np.sqrt(rbm._ais_var))

		self.assertTrue(upper - lower < 1.5)
		self.assertTrue(lower < brf_logz and brf_logz < upper)
コード例 #13
0
	def test_ais_with_semirbm(self):
		rbm = SemiRBM(5, 20)
		rbm.L = np.matrix(np.random.randn(5, 5))
		rbm.L = np.triu(rbm.L) + np.triu(rbm.L).T - 2 * np.diag(np.diag(rbm.L))
		rbm.num_lateral_updates = 5
		rbm.sampling_method = SemiRBM.GIBBS

		ais = Estimator(rbm)

		ais_logz = ais.estimate_log_partition_function(100, np.arange(0, 1, 0.001))
		brf_logz = np.log(np.sum(np.exp(rbm._ulogprob_vis(utils.binary_numbers(rbm.X.shape[0])))))

		lower = np.log(np.exp(ais_logz) - 4 * np.sqrt(rbm._ais_var))
		upper = np.log(np.exp(ais_logz) + 4 * np.sqrt(rbm._ais_var))

		self.assertTrue(upper - lower < 1.)
		self.assertTrue(lower < brf_logz and brf_logz < upper)
コード例 #14
0
    def test_ais_with_gaussianrbm(self):
        rbm = GaussianRBM(30, 10)
        rbm.c = np.matrix(np.random.randn(10, 1))
        rbm.W = np.matrix(np.random.randn(30, 10))
        rbm.b = np.matrix(np.random.rand(30, 1))

        ais = Estimator(rbm)

        ais_logz = ais.estimate_log_partition_function(100,
                                                       np.arange(0., 1., 1E-4))
        brf_logz = utils.logsumexp(
            rbm._ulogprob_hid(utils.binary_numbers(rbm.Y.shape[0])))

        lower = np.log(np.exp(ais_logz) - 4 * np.sqrt(rbm._ais_var))
        upper = np.log(np.exp(ais_logz) + 4 * np.sqrt(rbm._ais_var))

        self.assertTrue(upper - lower < 1.5)
        self.assertTrue(lower < brf_logz and brf_logz < upper)
コード例 #15
0
    def test_ais_with_rbm(self):
        rbm = RBM(5, 20)
        rbm.W = np.matrix(np.random.randn(5, 20))
        rbm.b = np.matrix(np.random.randn(5, 1))
        rbm.c = np.matrix(np.random.randn(20, 1))

        ais = Estimator(rbm)

        ais_logz = ais.estimate_log_partition_function(100,
                                                       np.arange(0, 1, 0.001))
        brf_logz = utils.logsumexp(
            rbm._ulogprob_vis(utils.binary_numbers(rbm.X.shape[0])))

        lower = np.log(np.exp(ais_logz) - 4. * np.sqrt(rbm._ais_var))
        upper = np.log(np.exp(ais_logz) + 4. * np.sqrt(rbm._ais_var))

        self.assertTrue(upper - lower < 1.)
        self.assertTrue(lower < brf_logz and brf_logz < upper)
コード例 #16
0
    def test_ais_with_semirbm(self):
        rbm = SemiRBM(5, 20)
        rbm.L = np.matrix(np.random.randn(5, 5))
        rbm.L = np.triu(rbm.L) + np.triu(rbm.L).T - 2 * np.diag(np.diag(rbm.L))
        rbm.num_lateral_updates = 5
        rbm.sampling_method = SemiRBM.GIBBS

        ais = Estimator(rbm)

        ais_logz = ais.estimate_log_partition_function(100,
                                                       np.arange(0, 1, 0.001))
        brf_logz = np.log(
            np.sum(
                np.exp(rbm._ulogprob_vis(utils.binary_numbers(
                    rbm.X.shape[0])))))

        lower = np.log(np.exp(ais_logz) - 4 * np.sqrt(rbm._ais_var))
        upper = np.log(np.exp(ais_logz) + 4 * np.sqrt(rbm._ais_var))

        self.assertTrue(upper - lower < 1.)
        self.assertTrue(lower < brf_logz and brf_logz < upper)