问题描述
我收到此错误
'ValueError: Tensor Tensor("Placeholder:0", shape=(1, 1), dtype=int32)不是此图的元素.'
代码在没有 和 tf.Graph() 的情况下运行得非常好.as_default():.但是我需要多次调用 M.sample(...) 并且每次在 session.close() 之后内存都不会空闲.可能存在内存泄漏，但不确定它在哪里.
The code is running perfectly fine without with tf.Graph(). as_default():. However I need to call M.sample(...) multiple times and each time the memory won't be free after session.close(). Probably there is a memory leak but not sure where is it.
我想恢复一个预训练的神经网络，将其设置为默认图，并在默认图上多次测试(例如 10000)，而不是每次都放大.
I want to restore a pre-trained neural network, set it as default graph, and testing it multiple times (like 10000) over the default graph without making it larger each time.
代码是:
def SessionOpener(save):
grph = tf.get_default_graph()
sess = tf.Session(graph=grph)
ckpt = tf.train.get_checkpoint_state(save)
saver = tf.train.import_meta_graph('./predictor/save/model.ckpt.meta')
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
tf.global_variables_initializer().run(session=sess)
return sess
def LoadPredictor(save):
with open(os.path.join(save, 'config.pkl'), 'rb') as f:
saved_args = cPickle.load(f)
with open(os.path.join(save, 'words_vocab.pkl'), 'rb') as f:
words, vocab = cPickle.load(f)
model = Model(saved_args, True)
return model, words, vocab
if __name__ == '__main__':
Save = './save'
M, W, V = LoadPredictor(Save)
Sess = SessionOpener(Save)
word = M.sample(Sess, W, V, 1, str(123), 2, 1, 4)
Sess.close()
模型是:
class Model():
def __init__(self, args, infer=False):
with tf.Graph().as_default():
self.args = args
if infer:
args.batch_size = 1
args.seq_length = 1
if args.model == 'rnn':
cell_fn = rnn.BasicRNNCell
elif args.model == 'gru':
cell_fn = rnn.GRUCell
elif args.model == 'lstm':
cell_fn = rnn.BasicLSTMCell
else:
raise Exception("model type not supported: {}".format(args.model))
cells = []
for _ in range(args.num_layers):
cell = cell_fn(args.rnn_size)
cells.append(cell)
self.cell = cell = rnn.MultiRNNCell(cells)
self.input_data = tf.placeholder(tf.int32, [args.batch_size, args.seq_length])
self.targets = tf.placeholder(tf.int32, [args.batch_size, args.seq_length])
self.initial_state = cell.zero_state(args.batch_size, tf.float32)
self.batch_pointer = tf.Variable(0, name="batch_pointer", trainable=False, dtype=tf.int32)
self.inc_batch_pointer_op = tf.assign(self.batch_pointer, self.batch_pointer + 1)
self.epoch_pointer = tf.Variable(0, name="epoch_pointer", trainable=False)
self.batch_time = tf.Variable(0.0, name="batch_time", trainable=False)
tf.summary.scalar("time_batch", self.batch_time)
def variable_summaries(var):
"""Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.summary.scalar('mean', mean)
tf.summary.scalar('max', tf.reduce_max(var))
tf.summary.scalar('min', tf.reduce_min(var))
with tf.variable_scope('rnnlm'):
softmax_w = tf.get_variable("softmax_w", [args.rnn_size, args.vocab_size])
variable_summaries(softmax_w)
softmax_b = tf.get_variable("softmax_b", [args.vocab_size])
variable_summaries(softmax_b)
with tf.device("/cpu:0"):
embedding = tf.get_variable("embedding", [args.vocab_size, args.rnn_size])
inputs = tf.split(tf.nn.embedding_lookup(embedding, self.input_data), args.seq_length, 1)
inputs = [tf.squeeze(input_, [1]) for input_ in inputs]
def loop(prev, _):
prev = tf.matmul(prev, softmax_w) + softmax_b
prev_symbol = tf.stop_gradient(tf.argmax(prev, 1))
return tf.nn.embedding_lookup(embedding, prev_symbol)
outputs, last_state = legacy_seq2seq.rnn_decoder(inputs, self.initial_state, cell, loop_function=loop if infer else None, scope='rnnlm')
output = tf.reshape(tf.concat(outputs, 1), [-1, args.rnn_size])
self.logits = tf.matmul(output, softmax_w) + softmax_b
self.probs = tf.nn.softmax(self.logits)
loss = legacy_seq2seq.sequence_loss_by_example([self.logits],
[tf.reshape(self.targets, [-1])],
[tf.ones([args.batch_size * args.seq_length])],
args.vocab_size)
self.cost = tf.reduce_sum(loss) / args.batch_size / args.seq_length
tf.summary.scalar("cost", self.cost)
self.final_state = last_state
self.lr = tf.Variable(0.0, trainable=False)
tvars = tf.trainable_variables()
grads, _ = tf.clip_by_global_norm(tf.gradients(self.cost, tvars),
args.grad_clip)
optimizer = tf.train.AdamOptimizer(self.lr)
self.train_op = optimizer.apply_gradients(zip(grads, tvars))
def sample(self, sess, words, vocab, num=200, prime='first all', sampling_type=1, pick=0, width=4):
def weighted_pick(weights):
t = np.cumsum(weights)
s = np.sum(weights)
return(int(np.searchsorted(t, np.random.rand(1)*s)))
ret = ''
if pick == 1:
state = sess.run(self.cell.zero_state(1, tf.float32))
if not len(prime) or prime == ' ':
prime = random.choice(list(vocab.keys()))
for word in prime.split()[:-1]:
x = np.zeros((1, 1))
x[0, 0] = vocab.get(word,0)
feed = {self.input_data: x, self.initial_state:state}
[state] = sess.run([self.final_state], feed)
ret = prime
word = prime.split()[-1]
for n in range(num):
x = np.zeros((1, 1))
x[0, 0] = vocab.get(word, 0)
feed = {self.input_data: x, self.initial_state:state}
[probs, state] = sess.run([self.probs, self.final_state], feed)
p = probs[0]
if sampling_type == 0:
sample = np.argmax(p)
elif sampling_type == 2:
if word == '
':
sample = weighted_pick(p)
else:
sample = np.argmax(p)
else: # sampling_type == 1 default:
sample = weighted_pick(p)
ret = words[sample]
return ret
输出为:
Traceback (most recent call last):
File "/rcg/software/Linux/Ubuntu/16.04/amd64/TOOLS/TENSORFLOW/1.2.1-GPU-PY352/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 942, in _run
allow_operation=False)
File "/rcg/software/Linux/Ubuntu/16.04/amd64/TOOLS/TENSORFLOW/1.2.1-GPU-PY352/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2584, in as_graph_element
return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
File "/rcg/software/Linux/Ubuntu/16.04/amd64/TOOLS/TENSORFLOW/1.2.1-GPU-PY352/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2663, in _as_graph_element_locked
raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("Placeholder:0", shape=(1, 1), dtype=int32) is not an element of this graph.
推荐答案
当您创建 Model 时，会话尚未恢复.Model.__init__ 中定义的所有占位符、变量和操作都被放置在一个 新图 中，这使自己成为 with 块内的默认图.这是关键行:
When you create a Model, the session hasn't been restored yet. All placeholders, variables and ops that are defined in Model.__init__ are placed in a new graph, which makes itself a default graph inside with block. This is the key line:
with tf.Graph().as_default():
...
这意味着tf.Graph()的这个实例等于with块内的tf.get_default_graph()实例，但不是之前或之后.从这一刻开始，存在两个不同的图表.
This means that this instance of tf.Graph() equals to tf.get_default_graph() instance inside with block, but not before or after it. From this moment on, there exist two different graphs.
当您稍后创建会话并将图形恢复到其中时，您无法访问该会话中 tf.Graph() 的前一个实例.这是一个简短的例子:
When you later create a session and restore a graph into it, you can't access the previous instance of tf.Graph() in that session. Here's a short example:
with tf.Graph().as_default() as graph:
var = tf.get_variable("var", shape=[3], initializer=tf.zeros_initializer)
# This works
with tf.Session(graph=graph) as sess:
sess.run(tf.global_variables_initializer())
print(sess.run(var)) # ok because `sess.graph == graph`
# This fails
saver = tf.train.import_meta_graph('/tmp/model.ckpt.meta')
with tf.Session() as sess:
saver.restore(sess, "/tmp/model.ckpt")
print(sess.run(var)) # var is from `graph`, not `sess.graph`!
解决这个问题的最好方法是为所有节点命名，例如'input'、'target'等，保存模型，然后按名称查找恢复图中的节点，类似这样:
The best way to deal with this is give names to all nodes, e.g. 'input', 'target', etc, save the model and then look up the nodes in the restored graph by name, something like this:
saver = tf.train.import_meta_graph('/tmp/model.ckpt.meta')
with tf.Session() as sess:
saver.restore(sess, "/tmp/model.ckpt")
input_data = sess.graph.get_tensor_by_name('input')
target = sess.graph.get_tensor_by_name('target')
此方法保证所有节点都来自会话中的图中.
This method guarantees that all nodes will be from the graph in session.
这篇关于张量不是此图的元素的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！