Python tensorflow.sparse_placeholder函数代码示例

        def __init__(self, sess, n_nodes, args):

            self.sess = sess
            self.result_dir = args.result_dir
            self.dataset_name = args.dataset_name
            self.n_nodes = n_nodes
            self.n_hidden = args.n_hidden
            self.n_embedding = args.n_embedding
            self.dropout = args.dropout
            self.learning_rate = args.learning_rate
            self.max_iteration = args.max_iteration                   
            self.shape = np.array([self.n_nodes, self.n_nodes])

            self.adjacency = tf.sparse_placeholder(tf.float32, shape=self.shape, name='adjacency')
            self.norm_adj_mat = tf.sparse_placeholder(tf.float32, shape=self.shape, name='norm_adj_mat')
            self.keep_prob = tf.placeholder(tf.float32)
            
            self.W_0_mu = None
            self.W_1_mu = None            
            self.W_0_sigma = None
            self.W_1_sigma = None
            
            self.mu_np = []
            self.sigma_np = []        
            
            self._build_VGAE()

    def __init__(self, **hparam ):
        '''
        vocab_size, emb_size, enc_func, dec_func, is_tied_params, lambda_w, learning_rate, type_of_opt
        (adadelta)rho, (adam)beta1, beta2, epsilon
        '''
        self.vocab_size = hparam['vocab_size'] if 'vocab_size' in hparam else 100000 
        self.emb_size = hparam['emb_size'] if 'emb_size' in hparam else 64
        self.is_tied_params = hparam['is_tied_params'] if 'is_tied_params' in hparam else False
        self.init_value = hparam['init_value'] if 'init_value' in hparam else 0.01
        self.lambda_w = hparam['lambda_w'] if 'lambda_w' in hparam else 0.001 
        self.lr = hparam['learning_rate'] if 'learning_rate' in hparam else 0.001 
        self.opt = hparam['type_of_opt'] if 'type_of_opt' in hparam else 'adam'
        self.rho = hparam['rho'] if 'rho' in hparam else 0.95
        self.epsilon = hparam['epsilon'] if 'epsilon' in hparam else 1e-8
        self.beta1 = hparam['beta1'] if 'beta1' in hparam else 0.9
        self.beta2 = hparam['beta2'] if 'beta2' in hparam else 0.999
        
        self.enc_func =  self.get_activation_func(hparam['enc_func'] if 'enc_func' in hparam else 'tanh')
        self.dec_func =  self.get_activation_func(hparam['dec_func'] if 'dec_func' in hparam else 'tanh')
        
        self.summary_path = hparam['tf_summary_file'] if 'tf_summary_file' in hparam else 'log_tmp_path'

        self.saver = None 
        
        self.X = tf.sparse_placeholder(tf.float32) 
        self.Y = tf.sparse_placeholder(tf.float32) 
        self.mask = tf.sparse_placeholder(tf.float32) 
        
        self.params = {}
        
        self.W = tf.Variable(
                            tf.truncated_normal([self.vocab_size, self.emb_size], stddev=self.init_value / math.sqrt(float(self.emb_size)), mean=0), 
                            name='encoder_W' , dtype=tf.float32
                            )
        self.b = tf.Variable(tf.truncated_normal([self.emb_size], stddev=self.init_value * 0.001, mean=0), name='encoder_bias', dtype=tf.float32 )
        
        self.params['W'] = self.W 
        self.params['b'] = self.b 
            
        if not self.is_tied_params:
            self.W_prime = tf.Variable(
                            tf.truncated_normal([self.emb_size, self.vocab_size], stddev=self.init_value / math.sqrt(float(self.emb_size)), mean=0),  
                            name='decoder_W' , dtype=tf.float32
                            ) 
            self.params['W_prime'] = self.W_prime 
        else:
            self.W_prime = tf.transpose(self.W) 
        
        self.b_prime = tf.Variable(tf.truncated_normal([self.vocab_size], stddev=self.init_value * 0.001, mean=0), name='decoder_W', dtype=tf.float32 )
        self.params['b_prime'] = self.b_prime 
        
        self.encoded_values, self.decoded_values, self.masked_decoded_values, self.error, self.loss, self.train_step, self.summary = self.build_model()
        
        self.sess = tf.Session() 
        self.sess.run(tf.global_variables_initializer())
        self.log_writer = tf.summary.FileWriter(self.summary_path, graph = self.sess.graph)
        self._glo_ite_counter = 0

def test_edit_distance():
		graph = tf.Graph()
		with graph.as_default():
				truth = tf.sparse_placeholder(tf.int32)
				hyp = tf.sparse_placeholder(tf.int32)
				editDist = tf.edit_distance(hyp, truth, normalize=False)

		with tf.Session(graph=graph) as session:
				truthTest = sparse_tensor_feed([[0,1,2], [0,1,2,3,4]])
				hypTest = sparse_tensor_feed([[3,4,5], [0,1,2,2]])
				feedDict = {truth: truthTest, hyp: hypTest}
				dist = session.run([editDist], feed_dict=feedDict)
				print(dist)

  def __init__(self,args):
    super(seqMLP, self).__init__()
    self.args = args
    self.batch_size=args.batch_size
    self.input_data = tf.placeholder(tf.float32,[self.args.batch_size,self.args.sentence_length,self.args.word_dim],name='inputdata')
    
    self.output_data = tf.sparse_placeholder(tf.float32, name='outputdata')  #[None, 114]
    self.dense_outputdata= tf.sparse_tensor_to_dense(self.output_data)   
    self.keep_prob = tf.placeholder(tf.float32,name='keep_prob_NER')
    
    self.entMentIndex = tf.placeholder(tf.int32,[None,5],name='ent_mention_index')
    
    self.entCtxLeftIndex = tf.placeholder(tf.int32,[None,10],name='ent_ctxleft_index')
    self.entCtxRightIndex = tf.placeholder(tf.int32,[None,10],name='ent_ctxright_index')
    self.pos_f1 = tf.placeholder(tf.float32,[None,5,1])
    self.pos_f2 = tf.placeholder(tf.float32,[None,10,1])
    self.pos_f3 = tf.placeholder(tf.float32,[None,10,1])
    self.figerHier = np.asarray(cPickle.load(open('data/figer/figerhierarchical.p','rb')),np.float32)  #add the hierarchy features
    
    self.layers={}
    self.layers['fullyConnect'] = layers_lib.FullyConnection(self.args.class_size)
   
    
    used = tf.sign(tf.reduce_max(tf.abs(self.input_data),reduction_indices=2))
    self.length = tf.cast(tf.reduce_sum(used,reduction_indices=1),tf.int32)
      
    with tf.device('/gpu:0'):
      self.prediction,self.loss_lm = self.cl_loss_from_embedding(self.input_data)
      print 'self.loss_lm:',self.loss_lm
      
      _,self.adv_loss = self.adversarial_loss()
      print 'self.adv_loss:',self.adv_loss

      self.loss = tf.add(self.loss_lm,self.adv_loss)

    def __init__(self, field_sizes=None, embed_size=10, filter_sizes=None, layer_acts=None, drop_out=None,
                 init_path=None, opt_algo='gd', learning_rate=1e-2, random_seed=None):
        Model.__init__(self)
        init_vars = []
        num_inputs = len(field_sizes)
        for i in range(num_inputs):
            init_vars.append(('embed_%d' % i, [field_sizes[i], embed_size], 'xavier', dtype))
        init_vars.append(('f1', [embed_size, filter_sizes[0], 1, 2], 'xavier', dtype))
        init_vars.append(('f2', [embed_size, filter_sizes[1], 2, 2], 'xavier', dtype))
        init_vars.append(('w1', [2 * 3 * embed_size, 1], 'xavier', dtype))
        init_vars.append(('b1', [1], 'zero', dtype))

        self.graph = tf.Graph()
        with self.graph.as_default():
            if random_seed is not None:
                tf.set_random_seed(random_seed)
            self.X = [tf.sparse_placeholder(dtype) for i in range(num_inputs)]
            self.y = tf.placeholder(dtype)
            self.keep_prob_train = 1 - np.array(drop_out)
            self.keep_prob_test = np.ones_like(drop_out)
            self.layer_keeps = tf.placeholder(dtype)
            self.vars = utils.init_var_map(init_vars, init_path)
            w0 = [self.vars['embed_%d' % i] for i in range(num_inputs)]
            xw = tf.concat([tf.sparse_tensor_dense_matmul(self.X[i], w0[i]) for i in range(num_inputs)], 1)
            l = xw

            l = tf.transpose(tf.reshape(l, [-1, num_inputs, embed_size, 1]), [0, 2, 1, 3])
            f1 = self.vars['f1']
            l = tf.nn.conv2d(l, f1, [1, 1, 1, 1], 'SAME')
            l = tf.transpose(
                utils.max_pool_4d(
                    tf.transpose(l, [0, 1, 3, 2]),
                    int(num_inputs / 2)),
                [0, 1, 3, 2])
            f2 = self.vars['f2']
            l = tf.nn.conv2d(l, f2, [1, 1, 1, 1], 'SAME')
            l = tf.transpose(
                utils.max_pool_4d(
                    tf.transpose(l, [0, 1, 3, 2]), 3),
                [0, 1, 3, 2])
            l = tf.nn.dropout(
                utils.activate(
                    tf.reshape(l, [-1, embed_size * 3 * 2]),
                    layer_acts[0]),
                self.layer_keeps[0])
            w1 = self.vars['w1']
            b1 = self.vars['b1']
            l = tf.matmul(l, w1) + b1

            l = tf.squeeze(l)
            self.y_prob = tf.sigmoid(l)

            self.loss = tf.reduce_mean(
                tf.nn.sigmoid_cross_entropy_with_logits(logits=l, labels=self.y))
            self.optimizer = utils.get_optimizer(opt_algo, learning_rate, self.loss)

            config = tf.ConfigProto()
            config.gpu_options.allow_growth = True
            self.sess = tf.Session(config=config)
            tf.global_variables_initializer().run(session=self.sess)

    def __init__(self, input_dim=None, output_dim=1, init_path=None, opt_algo='gd', learning_rate=1e-2, l2_weight=0,
                 random_seed=None):
        Model.__init__(self)
        init_vars = [('w', [input_dim, output_dim], 'xavier', dtype),
                     ('b', [output_dim], 'zero', dtype)]
        self.graph = tf.Graph()
        with self.graph.as_default():
            if random_seed is not None:
                tf.set_random_seed(random_seed)
            self.X = tf.sparse_placeholder(dtype)
            self.y = tf.placeholder(dtype)
            self.vars = utils.init_var_map(init_vars, init_path)  # 初始化变量w, b

            w = self.vars['w']
            b = self.vars['b']
            xw = tf.sparse_tensor_dense_matmul(self.X, w)
            logits = tf.reshape(xw + b, [-1])
            self.y_prob = tf.sigmoid(logits)

            self.loss = tf.reduce_mean(
                tf.nn.sigmoid_cross_entropy_with_logits(labels=self.y, logits=logits)) + \
                        l2_weight * tf.nn.l2_loss(xw)
            self.optimizer = utils.get_optimizer(opt_algo, learning_rate, self.loss)

            config = tf.ConfigProto()
            config.gpu_options.allow_growth = True
            self.sess = tf.Session(config=config)
            tf.global_variables_initializer().run(session=self.sess)

  def testMatchingTensorInfoProtoMaps(self):
    sig1 = _make_signature({
        "x": tf.placeholder(tf.int32, [2]),
    }, {
        "x": tf.placeholder(tf.int32, [2]),
    })

    sig2 = _make_signature({
        "x": tf.placeholder(tf.int32, [2]),
    }, {
        "x": tf.sparse_placeholder(tf.int64, [2]),
    })
    self.assertTrue(
        tensor_info.tensor_info_proto_maps_match(sig1.inputs, sig2.inputs))
    self.assertFalse(
        tensor_info.tensor_info_proto_maps_match(sig1.outputs, sig2.outputs))

    sig3 = _make_signature({
        "x": tf.placeholder(tf.int32, [None]),
    }, {
        "x": tf.placeholder(tf.int32, [2]),
    })
    self.assertFalse(
        tensor_info.tensor_info_proto_maps_match(sig1.inputs, sig3.inputs))
    self.assertTrue(
        tensor_info.tensor_info_proto_maps_match(sig1.outputs, sig3.outputs))

    def add_placeholders(self):
        # the batch_size and max_stepsize每步都是变长的。
        self.input_tensor = tf.placeholder(tf.float32, [None, None, n_input + (2 * n_input * n_context)],
                                           name='input')  # 语音log filter bank or MFCC features

        self.text = tf.sparse_placeholder(tf.int32, name='text')  # 文本
        self.seq_length = tf.placeholder(tf.int32, [None], name='seq_length')  # 序列长
        self.keep_dropout = tf.placeholder(tf.float32)

  def _run_test_als(self, use_factors_weights_cache):
    with self.test_session():
      col_init = np.random.rand(7, 3)
      als_model = factorization_ops.WALSModel(
          5, 7, 3,
          col_init=col_init,
          row_weights=None,
          col_weights=None,
          use_factors_weights_cache=use_factors_weights_cache)

      als_model.initialize_op.run()
      als_model.worker_init.run()
      als_model.row_update_prep_gramian_op.run()
      als_model.initialize_row_update_op.run()
      process_input_op = als_model.update_row_factors(self._wals_inputs)[1]
      process_input_op.run()
      row_factors1 = [x.eval() for x in als_model.row_factors]

      wals_model = factorization_ops.WALSModel(
          5, 7, 3,
          col_init=col_init,
          row_weights=0,
          col_weights=0,
          use_factors_weights_cache=use_factors_weights_cache)
      wals_model.initialize_op.run()
      wals_model.worker_init.run()
      wals_model.row_update_prep_gramian_op.run()
      wals_model.initialize_row_update_op.run()
      process_input_op = wals_model.update_row_factors(self._wals_inputs)[1]
      process_input_op.run()
      row_factors2 = [x.eval() for x in wals_model.row_factors]

      for r1, r2 in zip(row_factors1, row_factors2):
        self.assertAllClose(r1, r2, atol=1e-3)

      # Here we test partial column updates.
      sp_c = np_matrix_to_tf_sparse(INPUT_MATRIX, col_slices=[2, 0],
                                    shuffle=True).eval()

      sp_feeder = tf.sparse_placeholder(tf.float32)
      feed_dict = {sp_feeder: sp_c}
      als_model.col_update_prep_gramian_op.run()
      als_model.initialize_col_update_op.run()
      process_input_op = als_model.update_col_factors(sp_input=sp_feeder)[1]
      process_input_op.run(feed_dict=feed_dict)
      col_factors1 = [x.eval() for x in als_model.col_factors]

      feed_dict = {sp_feeder: sp_c}
      wals_model.col_update_prep_gramian_op.run()
      wals_model.initialize_col_update_op.run()
      process_input_op = wals_model.update_col_factors(sp_input=sp_feeder)[1]
      process_input_op.run(feed_dict=feed_dict)
      col_factors2 = [x.eval() for x in wals_model.col_factors]

      for c1, c2 in zip(col_factors1, col_factors2):
        self.assertAllClose(c1, c2, rtol=5e-3, atol=1e-2)

 def __init__(self, mode):
     self.mode = mode
     # image
     self.inputs = tf.placeholder(tf.float32, [None, FLAGS.image_height, FLAGS.image_width, FLAGS.image_channel])
     # SparseTensor required by ctc_loss op
     self.labels = tf.sparse_placeholder(tf.int32)
     # 1d array of size [batch_size]
     # self.seq_len = tf.placeholder(tf.int32, [None])
     # l2
     self._extra_train_ops = []

def get_train_model():
    # Has size [batch_size, max_stepsize, num_features], but the
    # batch_size and max_stepsize can vary along each step
    inputs, features = convolutional_layers()
    # print features.get_shape()

    # inputs = tf.placeholder(tf.float32, [None, None, common.OUTPUT_SHAPE[0]])

    # Here we use sparse_placeholder that will generate a
    # SparseTensor required by ctc_loss op.
    targets = tf.sparse_placeholder(tf.int32)

    # 1d array of size [batch_size]
    seq_len = tf.placeholder(tf.int32, [None])

    # Defining the cell
    # Can be:
    #   tf.nn.rnn_cell.RNNCell
    #   tf.nn.rnn_cell.GRUCell
    # cell = tf.contrib.rnn.LSTMCell(common.num_hidden, state_is_tuple=True)

    # Stacking rnn cells
    stack = tf.contrib.rnn.MultiRNNCell([lstm_cell() for _ in range(0, common.num_layers)],
                                        state_is_tuple=True)

    # The second output is the last state and we will no use that
    outputs, _ = tf.nn.dynamic_rnn(stack, features, seq_len, dtype=tf.float32)

    shape = tf.shape(features)
    batch_s, max_timesteps = shape[0], shape[1]

    # Reshaping to apply the same weights over the timesteps
    outputs = tf.reshape(outputs, [-1, common.num_hidden])

    # Truncated normal with mean 0 and stdev=0.1
    # Tip: Try another initialization
    # see https://www.tensorflow.org/versions/r0.9/api_docs/python/contrib.layers.html#initializers
    W = tf.Variable(tf.truncated_normal([common.num_hidden,
                                         common.num_classes],
                                        stddev=0.1), name="W")
    # Zero initialization
    # Tip: Is tf.zeros_initializer the same?
    b = tf.Variable(tf.constant(0., shape=[common.num_classes]), name="b")

    # Doing the affine projection
    logits = tf.matmul(outputs, W) + b

    # Reshaping back to the original shape
    logits = tf.reshape(logits, [batch_s, -1, common.num_classes])

    # Time major
    logits = tf.transpose(logits, (1, 0, 2))

    return logits, inputs, targets, seq_len, W, b

  def testBuildInputMap(self):
    x = tf.placeholder(tf.int32, [2])
    y = tf.sparse_placeholder(tf.string, [None])
    sig = _make_signature({"x": x, "y": y}, {})

    input_map = tensor_info.build_input_map(sig.inputs, {"x": x, "y": y})
    self.assertEquals(len(input_map), 4)
    self.assertEquals(input_map[x.name], x)
    self.assertEquals(input_map[y.indices.name], y.indices)
    self.assertEquals(input_map[y.values.name], y.values)
    self.assertEquals(input_map[y.dense_shape.name], y.dense_shape)

  def testBuildOutputMap(self):
    x = tf.placeholder(tf.int32, [2])
    y = tf.sparse_placeholder(tf.string, [None])
    sig = _make_signature({}, {"x": x, "y": y})

    def _get_tensor(name):
      return tf.get_default_graph().get_tensor_by_name(name)

    output_map = tensor_info.build_output_map(sig.outputs, _get_tensor)
    self.assertEquals(len(output_map), 2)
    self.assertEquals(output_map["x"], x)
    self.assertEquals(output_map["y"].indices, y.indices)
    self.assertEquals(output_map["y"].values, y.values)
    self.assertEquals(output_map["y"].dense_shape, y.dense_shape)

  def _run_test_als_transposed(self, use_factors_weights_cache):
    with self.test_session():
      col_init = np.random.rand(7, 3)
      als_model = factorization_ops.WALSModel(
          5, 7, 3,
          col_init=col_init,
          row_weights=None,
          col_weights=None,
          use_factors_weights_cache=use_factors_weights_cache)

      als_model.initialize_op.run()
      als_model.worker_init.run()

      wals_model = factorization_ops.WALSModel(
          5, 7, 3,
          col_init=col_init,
          row_weights=[0] * 5,
          col_weights=[0] * 7,
          use_factors_weights_cache=use_factors_weights_cache)
      wals_model.initialize_op.run()
      wals_model.worker_init.run()
      sp_feeder = tf.sparse_placeholder(tf.float32)
      # Here test partial row update with identical inputs but with transposed
      # input for als.
      sp_r_t = np_matrix_to_tf_sparse(INPUT_MATRIX, [3, 1],
                                      transpose=True).eval()
      sp_r = np_matrix_to_tf_sparse(INPUT_MATRIX, [3, 1]).eval()

      feed_dict = {sp_feeder: sp_r_t}
      als_model.row_update_prep_gramian_op.run()
      als_model.initialize_row_update_op.run()
      process_input_op = als_model.update_row_factors(sp_input=sp_feeder,
                                                      transpose_input=True)[1]
      process_input_op.run(feed_dict=feed_dict)
      # Only updated row 1 and row 3, so only compare these rows since others
      # have randomly initialized values.
      row_factors1 = [als_model.row_factors[0].eval()[1],
                      als_model.row_factors[0].eval()[3]]

      feed_dict = {sp_feeder: sp_r}
      wals_model.row_update_prep_gramian_op.run()
      wals_model.initialize_row_update_op.run()
      process_input_op = wals_model.update_row_factors(sp_input=sp_feeder)[1]
      process_input_op.run(feed_dict=feed_dict)
      # Only updated row 1 and row 3, so only compare these rows since others
      # have randomly initialized values.
      row_factors2 = [wals_model.row_factors[0].eval()[1],
                      wals_model.row_factors[0].eval()[3]]
      for r1, r2 in zip(row_factors1, row_factors2):
        self.assertAllClose(r1, r2, atol=1e-3)

  def __init__(self,args):
    '''
    @time: 2016/12/20
    @editor: wujs
    @function: also need to return the candidates entity mentions lstm representation
    '''
    super(seqCNN, self).__init__()
    self.args = args
    self.batch_size=args.batch_size

    self.input_data = tf.placeholder(tf.float32,[self.args.batch_size,self.args.sentence_length,self.args.word_dim],name='inputdata')
    print 'self.input_data:',self.input_data
    
    self.output_data = tf.sparse_placeholder(tf.float32, name='outputdata')
    self.keep_prob = tf.placeholder(tf.float32,name='keep_prob_NER')
    
    self.pos_f1 = tf.placeholder(tf.float32,[None,5,1])
    self.pos_f2 = tf.placeholder(tf.float32,[None,10,1])
    self.pos_f3 = tf.placeholder(tf.float32,[None,10,1])
    
    self.entMentIndex = tf.placeholder(tf.int32,[None,5],name='ent_mention_index')
    
    self.entCtxLeftIndex = tf.placeholder(tf.int32,[None,10],name='ent_ctxleft_index')
    self.entCtxRightIndex = tf.placeholder(tf.int32,[None,10],name='ent_ctxright_index')
    
    if args.datasets == 'figer':
      self.hier = np.asarray(cPickle.load(open('data/figer/figerhierarchical.p','rb')),np.float32)  #add the hierarchy features
    else:
      self.hier = np.asarray(cPickle.load(open('data/OntoNotes/OntoNoteshierarchical.p','rb')),np.float32)
    
    self.pred_bias = tf.Variable(tf.zeros([self.args.class_size]), name="pred_bias")
    
    self.layers={}
    self.layers['CNN'] = layers_lib.CNN(filters=[1,2,3,4,5],word_embedding_size=self.args.word_dim+1,num_filters=5)
    self.layers['fullyConnect_ment'] = layers_lib.FullyConnection(self.args.class_size,name='FullyConnection_ment') # 90 is the row of type hierical 
    self.layers['fullyConnect_ctx'] = layers_lib.FullyConnection(self.args.class_size,name='FullyConnection_ctx')
    #self.layers['fullyConnect_ctx'] = layers_lib.FullyConnection(np.shape(self.hier)[0],name='FullyConnection_ctx')
        
    self.dense_outputdata= tf.sparse_tensor_to_dense(self.output_data)
    
    print 'self.dense_outputdata:', self.dense_outputdata
    
    self.prediction,self.loss_lm = self.cl_loss_from_embedding(self.input_data)
    print 'self.loss_lm:',self.loss_lm
      
    _,self.adv_loss = self.adversarial_loss()
    print 'self.adv_loss:',self.adv_loss

    self.loss = tf.add(self.loss_lm,self.adv_loss)