当前位置: 首页>>代码示例>>Python>>正文


Python tensorflow.eye函数代码示例

本文整理汇总了Python中tensorflow.eye函数的典型用法代码示例。如果您正苦于以下问题:Python eye函数的具体用法?Python eye怎么用?Python eye使用的例子?那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。


在下文中一共展示了eye函数的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: initialize_mod_binary_MERA

def initialize_mod_binary_MERA(phys_dim,
                               chi,
                               dtype=tf.float64):
                          
    """
    Parameters:
    -------------------
    phys_dim:         int 
                      Hilbert space dimension of the bottom layer
    chi:              int 
                      maximum bond dimension
    dtype:            tensorflow dtype
                      dtype of the MERA tensors
    Returns:
    -------------------
    (wC, vC, uC, rhoAB, rhoBA)
    wC, vC, uC:      list of tf.Tensor
    rhoAB, rhoBA:    tf.Tensor
    """
    
    wC, vC, uC = increase_bond_dimension_by_adding_layers(chi_new=chi,
                                                          wC=[tf.random_uniform(shape=[phys_dim, phys_dim, phys_dim],dtype=dtype)],
                                                          vC=[tf.random_uniform(shape=[phys_dim, phys_dim, phys_dim],dtype=dtype)],
                                                          uC=[tf.random_uniform(shape=[phys_dim, phys_dim, phys_dim, phys_dim],dtype=dtype)])
    chi_top = wC[-1].shape[2]
    rhoAB = tf.reshape(tf.eye(chi_top * chi_top, dtype=dtype),
                       (chi_top, chi_top, chi_top, chi_top))

    rhoBA = tf.reshape(tf.eye(chi_top * chi_top, dtype=dtype),
                       (chi_top, chi_top, chi_top, chi_top))
    
    return wC, vC, uC, rhoAB, rhoBA
开发者ID:zoltanegyed,项目名称:TensorNetwork,代码行数:32,代码来源:modified_binary_mera.py

示例2: test_with_tensors

 def test_with_tensors(self):
   net = tensornetwork.TensorNetwork()
   a = net.add_node(tf.eye(2) * 2, name="T")
   b = net.add_node(tf.eye(2) * 3, name="A")
   e1 = net.connect(a[0], b[0], "edge")
   e2 = net.connect(a[1], b[1], "edge2")
   net.check_correct()
   net.contract(e1)
   net.check_correct()
   val = net.contract(e2)
   net.check_correct()
   self.assertAlmostEqual(val.get_tensor().numpy(), 12.0)
开发者ID:zoltanegyed,项目名称:TensorNetwork,代码行数:12,代码来源:tensornetwork_test.py

示例3: _build_predict

    def _build_predict(self, Xnew, full_cov=False):
        """
        Xnew is a data matrix, point at which we want to predict

        This method computes

            p(F* | Y )

        where F* are points on the GP at Xnew, Y are noisy observations at X.

        """
        Kx = self.kern.K(self.X, Xnew)
        K = self.kern.K(self.X) + tf.eye(tf.shape(self.X)[0], dtype=settings.float_type) * self.likelihood.variance
        L = tf.cholesky(K)
        A = tf.matrix_triangular_solve(L, Kx, lower=True)
        V = tf.matrix_triangular_solve(L, self.Y - self.mean_function(self.X))
        fmean = tf.matmul(A, V, transpose_a=True) + self.mean_function(Xnew)
        if full_cov:
            fvar = self.kern.K(Xnew) - tf.matmul(A, A, transpose_a=True)
            shape = tf.stack([1, 1, tf.shape(self.Y)[1]])
            fvar = tf.tile(tf.expand_dims(fvar, 2), shape)
        else:
            fvar = self.kern.Kdiag(Xnew) - tf.reduce_sum(tf.square(A), 0)
            fvar = tf.tile(tf.reshape(fvar, (-1, 1)), [1, tf.shape(self.Y)[1]])
        return fmean, fvar
开发者ID:vincentadam87,项目名称:GPflow,代码行数:25,代码来源:gpr.py

示例4: initial_state

  def initial_state(self, batch_size, trainable=False):
    """Creates the initial memory.

    We should ensure each row of the memory is initialized to be unique,
    so initialize the matrix to be the identity. We then pad or truncate
    as necessary so that init_state is of size
    (batch_size, self._mem_slots, self._mem_size).

    Args:
      batch_size: The size of the batch.
      trainable: Whether the initial state is trainable. This is always True.

    Returns:
      init_state: A truncated or padded matrix of size
        (batch_size, self._mem_slots, self._mem_size).
    """
    init_state = tf.eye(self._mem_slots, batch_shape=[batch_size])

    # Pad the matrix with zeros.
    if self._mem_size > self._mem_slots:
      difference = self._mem_size - self._mem_slots
      pad = tf.zeros((batch_size, self._mem_slots, difference))
      init_state = tf.concat([init_state, pad], -1)
    # Truncation. Take the first `self._mem_size` components.
    elif self._mem_size < self._mem_slots:
      init_state = init_state[:, :, :self._mem_size]
    return init_state
开发者ID:ccchang0111,项目名称:sonnet,代码行数:27,代码来源:relational_memory.py

示例5: maximum_mean_discrepancy

def maximum_mean_discrepancy(k_xx, k_yy, k_xy):
	samples_x = tf.cast(tf.shape(k_xx)[0], dtype=tf.float32)
	samples_y = tf.cast(tf.shape(k_yy)[0], dtype=tf.float32)

	k_xx_diag = tf.multiply(k_xx, tf.eye(tf.shape(k_xx)[0]))
	k_xx = k_xx - k_xx_diag

	k_yy_diag = tf.multiply(k_yy, tf.eye(tf.shape(k_yy)[0]))
	k_yy = k_yy - k_yy_diag

	E_xx = tf.reduce_sum(k_xx)/(samples_x*(samples_x-1))
	E_yy = tf.reduce_sum(k_yy)/(samples_y*(samples_y-1))
	E_xy = tf.reduce_mean(k_xy)
	mmd_2 = E_xx + E_yy - 2*E_xy
	mmd = tf.sqrt(tf.maximum(mmd_2,0))
	return mmd
开发者ID:AdalbertoCq,项目名称:Pathology-GAN,代码行数:16,代码来源:utils.py

示例6: _build_predict

 def _build_predict(self, Xnew, full_cov=False):
     """
     Compute the mean and variance of the latent function at some new points
     Xnew. For a derivation of the terms in here, see the associated SGPR
     notebook.
     """
     num_inducing = len(self.feature)
     err = self.Y - self.mean_function(self.X)
     Kuf = self.feature.Kuf(self.kern, self.X)
     Kuu = self.feature.Kuu(self.kern, jitter=settings.numerics.jitter_level)
     Kus = self.feature.Kuf(self.kern, Xnew)
     sigma = tf.sqrt(self.likelihood.variance)
     L = tf.cholesky(Kuu)
     A = tf.matrix_triangular_solve(L, Kuf, lower=True) / sigma
     B = tf.matmul(A, A, transpose_b=True) + tf.eye(num_inducing, dtype=settings.float_type)
     LB = tf.cholesky(B)
     Aerr = tf.matmul(A, err)
     c = tf.matrix_triangular_solve(LB, Aerr, lower=True) / sigma
     tmp1 = tf.matrix_triangular_solve(L, Kus, lower=True)
     tmp2 = tf.matrix_triangular_solve(LB, tmp1, lower=True)
     mean = tf.matmul(tmp2, c, transpose_a=True)
     if full_cov:
         var = self.kern.K(Xnew) + tf.matmul(tmp2, tmp2, transpose_a=True) \
               - tf.matmul(tmp1, tmp1, transpose_a=True)
         shape = tf.stack([1, 1, tf.shape(self.Y)[1]])
         var = tf.tile(tf.expand_dims(var, 2), shape)
     else:
         var = self.kern.Kdiag(Xnew) + tf.reduce_sum(tf.square(tmp2), 0) \
               - tf.reduce_sum(tf.square(tmp1), 0)
         shape = tf.stack([1, tf.shape(self.Y)[1]])
         var = tf.tile(tf.expand_dims(var, 1), shape)
     return mean + self.mean_function(Xnew), var
开发者ID:vincentadam87,项目名称:GPflow,代码行数:32,代码来源:sgpr.py

示例7: radial_symmetry

  def radial_symmetry(self, d_cutoff, d, atom_numbers):
    """ Radial Symmetry Function """
    embedding = tf.eye(np.max(self.atom_cases) + 1)
    atom_numbers_embedded = tf.nn.embedding_lookup(embedding, atom_numbers)

    Rs = np.linspace(0., self.radial_cutoff, self.radial_length)
    ita = np.ones_like(Rs) * 3 / (Rs[1] - Rs[0])**2
    Rs = tf.cast(np.reshape(Rs, (1, 1, 1, -1)), tf.float32)
    ita = tf.cast(np.reshape(ita, (1, 1, 1, -1)), tf.float32)
    length = ita.get_shape().as_list()[-1]

    d_cutoff = tf.stack([d_cutoff] * length, axis=3)
    d = tf.stack([d] * length, axis=3)

    out = tf.exp(-ita * tf.square(d - Rs)) * d_cutoff
    if self.atomic_number_differentiated:
      out_tensors = []
      for atom_type in self.atom_cases:
        selected_atoms = tf.expand_dims(
            tf.expand_dims(atom_numbers_embedded[:, :, atom_type], axis=1),
            axis=3)
        out_tensors.append(tf.reduce_sum(out * selected_atoms, axis=2))
      return tf.concat(out_tensors, axis=2)
    else:
      return tf.reduce_sum(out, axis=2)
开发者ID:ktaneishi,项目名称:deepchem,代码行数:25,代码来源:transformers.py

示例8: _build_likelihood

    def _build_likelihood(self):
        """
        q_alpha, q_lambda are variational parameters, size N x R
        This method computes the variational lower bound on the likelihood,
        which is:
            E_{q(F)} [ \log p(Y|F) ] - KL[ q(F) || p(F)]
        with
            q(f) = N(f | K alpha + mean, [K^-1 + diag(square(lambda))]^-1) .
        """
        K = self.kern.K(self.X)
        K_alpha = tf.matmul(K, self.q_alpha)
        f_mean = K_alpha + self.mean_function(self.X)

        # compute the variance for each of the outputs
        I = tf.tile(tf.expand_dims(tf.eye(self.num_data, dtype=settings.float_type), 0),
                    [self.num_latent, 1, 1])
        A = I + tf.expand_dims(tf.transpose(self.q_lambda), 1) * \
            tf.expand_dims(tf.transpose(self.q_lambda), 2) * K
        L = tf.cholesky(A)
        Li = tf.matrix_triangular_solve(L, I)
        tmp = Li / tf.expand_dims(tf.transpose(self.q_lambda), 1)
        f_var = 1. / tf.square(self.q_lambda) - tf.transpose(tf.reduce_sum(tf.square(tmp), 1))

        # some statistics about A are used in the KL
        A_logdet = 2.0 * tf.reduce_sum(tf.log(tf.matrix_diag_part(L)))
        trAi = tf.reduce_sum(tf.square(Li))

        KL = 0.5 * (A_logdet + trAi - self.num_data * self.num_latent +
                    tf.reduce_sum(K_alpha * self.q_alpha))

        v_exp = self.likelihood.variational_expectations(f_mean, f_var, self.Y)
        return tf.reduce_sum(v_exp) - KL
开发者ID:sanket-kamthe,项目名称:GPflow,代码行数:32,代码来源:vgp.py

示例9: body

  def body(self, features):
    with tf.variable_scope('string_embedding'):
      string_embedding = self.encode(features, 'inputs')

    if 'targets' in features:
      with tf.variable_scope('code_embedding'):
        code_embedding = self.encode(features, 'targets')

      string_embedding_norm = tf.nn.l2_normalize(string_embedding, axis=1)
      code_embedding_norm = tf.nn.l2_normalize(code_embedding, axis=1)

      # All-vs-All cosine distance matrix, reshaped as row-major.
      cosine_dist = 1.0 - tf.matmul(string_embedding_norm, code_embedding_norm,
                                    transpose_b=True)
      cosine_dist_flat = tf.reshape(cosine_dist, [-1, 1])

      # Positive samples on the diagonal, reshaped as row-major.
      label_matrix = tf.eye(tf.shape(cosine_dist)[0], dtype=tf.int32)
      label_matrix_flat = tf.reshape(label_matrix, [-1])

      logits = tf.concat([1.0 - cosine_dist_flat, cosine_dist_flat], axis=1)
      labels = tf.one_hot(label_matrix_flat, 2)

      loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=labels,
                                                     logits=logits)

      return string_embedding, {'training': loss}

    return string_embedding
开发者ID:qixiuai,项目名称:tensor2tensor,代码行数:29,代码来源:similarity_transformer.py

示例10: _update_ortho

 def _update_ortho(self,v,i):
   s = self.gan.ops.shape(v)
   if len(s) == 4 and s[0] == s[1]:
     w=v
     newv = []
     #s = self.ops.shape(v_transpose)
     #identity = tf.reshape(identity, [s[0],s[1],1,1])
     #identity = tf.tile(identity, [1,1,s[2],s[3]])
     decay = self.config.decay or 0.01
     w = tf.transpose(w, perm=[2,3,0,1])
     for i in range(self.config.iterations or 3):
         wt = tf.transpose(w, perm=[1,0,2,3])
         w2 = tf.reshape(w,[-1, s[0],s[1]])
         wt2 = tf.reshape(wt,[-1, s[0],s[1]])
         wtw = tf.matmul(wt2,w2)
         eye = tf.eye(s[0],s[1])
         eye = tf.tile(eye, [1,s[2]*s[3]])
         eye = tf.reshape(eye, self.gan.ops.shape(w))
         wtw = tf.reshape(wtw, self.gan.ops.shape(w))
         qk = eye - wtw
         w = w * (eye + 0.5*qk)
     w = tf.transpose(w, perm=[2,3,0,1])
     newv = w
     newv=(1.0+decay)*v - decay*(newv)
     newv = tf.reshape(newv,self.ops.shape(v))
     return tf.assign(v, newv)
   else:
     return None
开发者ID:255BITS,项目名称:hyperchamber-gan,代码行数:28,代码来源:weight_constraint_train_hook.py

示例11: test_sample_mvn

def test_sample_mvn(session_tf, cov_structure, num_samples):
    """
    Draws 10,000 samples from a distribution
    with known mean and covariance. The test checks
    if the mean and covariance of the samples is
    close to the true mean and covariance.
    """

    N, D = 10000, 2
    means = tf.ones((N, D), dtype=float_type)
    if cov_structure == "full":
        covs = tf.eye(D, batch_shape=[N], dtype=float_type)
    elif cov_structure == "diag":
        covs = tf.ones((N, D), dtype=float_type)

    samples = _sample_mvn(means, covs, cov_structure, num_samples=num_samples)
    value = session_tf.run(samples)

    if num_samples is None:
        assert value.shape == (N, D)
    else:
        assert value.shape == (num_samples, N, D)
        value = value.reshape(-1, D)

    samples_mean = np.mean(value, axis=0)
    samples_cov = np.cov(value, rowvar=False)
    np.testing.assert_array_almost_equal(samples_mean, [1., 1.], decimal=1)
    np.testing.assert_array_almost_equal(samples_cov, [[1., 0.], [0., 1.]], decimal=1)
开发者ID:sanket-kamthe,项目名称:GPflow,代码行数:28,代码来源:test_multioutput.py

示例12: testDimensionGuardDynamicShape

 def testDimensionGuardDynamicShape(self):
   testee_lkj = tfd.LKJ(
       dimension=3, concentration=[1., 4.], validate_args=True)
   with self.assertRaisesOpError('dimension mismatch'):
     self.evaluate(
         testee_lkj.log_prob(
             tf.placeholder_with_default(tf.eye(4), shape=None)))
开发者ID:asudomoeva,项目名称:probability,代码行数:7,代码来源:lkj_test.py

示例13: testMultivariateNormalNd

  def testMultivariateNormalNd(self, event_size, num_samples):
    def target_log_prob_fn(event):
      return tfd.MultivariateNormalFullCovariance(
          loc=tf.zeros(event_size),
          covariance_matrix=tf.eye(event_size)).log_prob(event)

    state = tf.zeros(event_size)
    samples = []
    for seed in range(num_samples):
      [state], _, _ = no_u_turn_sampler.kernel(
          target_log_prob_fn=target_log_prob_fn,
          current_state=[state],
          step_size=[0.3],
          seed=seed)
      npstate = state.numpy()
      samples.append([npstate[0], npstate[1]])

    samples = np.array(samples)
    plt.scatter(samples[:, 0], samples[:, 1])
    savefig("projection_chain_{}d_normal_{}_steps.png".format(
        event_size, num_samples))
    plt.close()

    target_samples = tfd.MultivariateNormalFullCovariance(
        loc=tf.zeros(event_size),
        covariance_matrix=tf.eye(event_size)).sample(
            num_samples, seed=4).numpy()
    plt.scatter(target_samples[:, 0], target_samples[:, 1])
    savefig("projection_independent_{}d_normal_{}_samples.png".format(
        event_size, num_samples))
    plt.close()
开发者ID:asudomoeva,项目名称:probability,代码行数:31,代码来源:nuts_test.py

示例14: _get_fldj_numerical

  def _get_fldj_numerical(self, bijector, x, event_ndims,
                          eps=1.e-6,
                          input_to_vector=tfb.Identity,
                          output_to_vector=tfb.Identity):
    """Numerically approximate the forward log det Jacobian of a bijector.

    Args:
      bijector: the bijector whose Jacobian we wish to approximate
      x: the value for which we want to approximate the Jacobian
      event_ndims: number of dimensions in an event
      eps: epsilon to add when forming (f(x+eps)-f(x)) / eps
      input_to_vector: a bijector that maps the input value to a vector
      output_to_vector: a bijector that maps the output value to a vector

    Returns:
      A numerical approximation to the log det Jacobian of bijector.forward
      evaluated at x.
    """
    x_vector = input_to_vector.forward(x)
    n = tf.shape(x_vector)[-1]
    x_plus_eps_vector = x_vector + eps * tf.eye(n, dtype=x_vector.dtype)
    x_plus_eps = input_to_vector.inverse(x_plus_eps_vector)

    f_x = bijector.forward(x)
    f_x_vector = output_to_vector.forward(f_x)
    f_x_plus_eps = bijector.forward(x_plus_eps)
    f_x_plus_eps_vector = output_to_vector.forward(f_x_plus_eps)

    jacobian_numerical = (f_x_plus_eps_vector - f_x_vector) / eps
    return (
        tf.log(tf.abs(tf.matrix_determinant(jacobian_numerical))) +
        input_to_vector.forward_log_det_jacobian(x, event_ndims=event_ndims) -
        output_to_vector.forward_log_det_jacobian(f_x, event_ndims=event_ndims))
开发者ID:asudomoeva,项目名称:probability,代码行数:33,代码来源:cholesky_to_inv_cholesky_test.py

示例15: distance_cutoff

 def distance_cutoff(self, d, cutoff, flags):
   """ Generate distance matrix with trainable cutoff """
   # Cutoff with threshold Rc
   d_flag = flags * tf.sign(cutoff - d)
   d_flag = tf.nn.relu(d_flag)
   d_flag = d_flag * tf.expand_dims((1 - tf.eye(self.max_atoms)), 0)
   d = 0.5 * (tf.cos(np.pi * d / cutoff) + 1)
   return d * d_flag
开发者ID:ktaneishi,项目名称:deepchem,代码行数:8,代码来源:transformers.py


注:本文中的tensorflow.eye函数示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。