我已经训练了我的模型并使用
保存了它 saver = tf.train.Saver()
saver.save(sess, '/final_model', global_step = i)
然后我重建完全相同的图并尝试恢复模型以重现我的结果,恢复正在工作,但只要尝试访问网络参数或操作的任何值,它给我一个错误说试图使用未初始化的变量。
重建图表后,我用来恢复的代码是:
sess=tf.Session()
new_saver = tf.train.import_meta_graph('final_model-699.meta')
new_saver.restore(sess, tf.train.latest_checkpoint('./'))
但是,以下任何一个都会给我一个尝试使用未初始化变量的错误
print(sess.run(weights['hidden1']))
print(sess.run(loss_f, feed_dict={x: train_x, y_: train_y}))
有什么想法吗?
作为一个简单的例子,这里是训练和保存模型:
train_x = np.random.rand(200,2)
w= np.array([2,3])
train_y = np.dot(train_x, w)
train_y = np.reshape(train_y, [200,1])
feature_dim = 2
output_dim = 1
x = tf.placeholder(tf.float32, [None, feature_dim])
y_ = tf.placeholder(tf.float32, [None, output_dim])
weights = {
'hidden1': tf.Variable(tf.random_normal([feature_dim, output_dim], stddev=1 / np.sqrt(feature_dim)))
}
def network1(data):
output = tf.matmul(x, weights['hidden1'])
return output
y = network1(x)
loss_f = output_dim * tf.reduce_mean(tf.squared_difference(y, y_))
optimizer_f = tf.train.AdamOptimizer(1e-4).minimize(loss_f)
saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(10000):
batch_x = train_x
batch_y = train_y
sess.run(optimizer_f, feed_dict={x: batch_x, y_: batch_y})
print(sess.run(loss_f, feed_dict={x: batch_x, y_: batch_y}))
saver.save(sess,'./savedmodel/', global_step = i)
恢复和复制结果
import scipy.io
import numpy as np
import tensorflow as tf
import random
train_x = np.random.rand(200,2)
w= np.array([2,3])
train_y = np.dot(train_x, w)
train_y = np.reshape(train_y, [200,1])
feature_dim = 2
output_dim = 1
x = tf.placeholder(tf.float32, [None, feature_dim])
y_ = tf.placeholder(tf.float32, [None, output_dim])
weights = {
'hidden1': tf.Variable(tf.random_normal([feature_dim, output_dim], stddev=1 / np.sqrt(feature_dim)))
}
def network1(data):
output = tf.matmul(x, weights['hidden1'])
return output
y = network1(x)
loss_f = tf.reduce_mean(tf.squared_difference(y, y_))
optimizer_f = tf.train.AdamOptimizer(1e-4).minimize(loss_f)
sess = tf.Session()
saver = tf.train.import_meta_graph('./savedmodel/-9999.meta')
saver.restore(sess, tf.train.latest_checkpoint('./savedmodel/'))
print(sess.run(loss_f, feed_dict={x: train_x, y_: train_y}))
错误:
FailedPreconditionErrorTraceback (most recent call last)
<ipython-input-5-17910473afab> in <module>()
----> 1 print(sess.run(loss_f, feed_dict={x: train_x, y_: train_y}))
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
776 try:
777 result = self._run(None, fetches, feed_dict, options_ptr,
--> 778 run_metadata_ptr)
779 if run_metadata:
780 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
980 if final_fetches or final_targets:
981 results = self._do_run(handle, final_targets, final_fetches,
--> 982 feed_dict_string, options, run_metadata)
983 else:
984 results = []
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1030 if handle is None:
1031 return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1032 target_list, options, run_metadata)
1033 else:
1034 return self._do_call(_prun_fn, self._session, handle, feed_dict,
/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
1050 except KeyError:
1051 pass
-> 1052 raise type(e)(node_def, op, message)
1053
1054 def _extend_graph(self):
FailedPreconditionError: Attempting to use uninitialized value Variable
[[Node: Variable/read = Identity[T=DT_FLOAT, _class=["loc:@Variable"], _device="/job:localhost/replica:0/task:0/gpu:0"](Variable)]]
[[Node: Mean/_15 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_7_Mean", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op u'Variable/read', defined at:
File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"__main__", fname, loader, pkg_name)
File "/usr/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/usr/local/lib/python2.7/dist-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/usr/local/lib/python2.7/dist-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelapp.py", line 477, in start
ioloop.IOLoop.instance().start()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/usr/local/lib/python2.7/dist-packages/tornado/ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python2.7/dist-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python2.7/dist-packages/ipykernel/zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python2.7/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-3-7d229041d9bb>", line 6, in <module>
'hidden1': tf.Variable(tf.random_normal([feature_dim, output_dim], stddev=1 / np.sqrt(feature_dim)))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 197, in __init__
expected_shape=expected_shape)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 316, in _init_from_args
self._snapshot = array_ops.identity(self._variable, name="read")
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 1338, in identity
result = _op_def_lib.apply_op("Identity", input=input, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
self._traceback = _extract_stack()
FailedPreconditionError (see above for traceback): Attempting to use uninitialized value Variable
[[Node: Variable/read = Identity[T=DT_FLOAT, _class=["loc:@Variable"], _device="/job:localhost/replica:0/task:0/gpu:0"](Variable)]]
[[Node: Mean/_15 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_7_Mean", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
In [ ]:
print(sess.run(weights['hidden1']))
In [ ]:
同样的错误:
print(sess.run(weights['hidden1']))
答案 0 :(得分:2)
最后我发现,似乎我们想要稍后获取的每个变量或操作都需要给出一个名称,占位符也是如此,那么我们就不需要重新定义图形了。以下是最后的工作,如果有更简单的方法,请给我更多提示。
import scipy.io
import numpy as np
import tensorflow as tf
import random
train_x = np.random.rand(200,2)
w= np.array([2,3])
train_y = np.dot(train_x, w)
train_y = np.reshape(train_y, [200,1])
feature_dim = 2
output_dim = 1
x = tf.placeholder(tf.float32, [None, feature_dim], name="input")
y_ = tf.placeholder(tf.float32, [None, output_dim], name="output")
weights = {
'hidden1': tf.Variable(tf.random_normal([feature_dim, output_dim], stddev=1 / np.sqrt(feature_dim)), name="weights")
}
def network1(data):
output = tf.matmul(data, weights['hidden1'])
return output
y = network1(x)
loss_f = tf.reduce_mean(tf.squared_difference(y, y_), name="op_to_restore")
optimizer_f = tf.train.AdamOptimizer(1e-4).minimize(loss_f)
saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(100):
batch_x = train_x
batch_y = train_y
sess.run(optimizer_f, feed_dict={x: batch_x, y_: batch_y})
print(sess.run(loss_f, feed_dict={x: batch_x, y_: batch_y}))
saver.save(sess,'./savedmodel/', global_step = i)
with tf.Session() as sess:
saver = tf.train.import_meta_graph('./savedmodel/-99.meta')
saver.restore(sess,tf.train.latest_checkpoint('./savedmodel/'))
graph = tf.get_default_graph()
x = graph.get_tensor_by_name("input:0")
y_ = graph.get_tensor_by_name("output:0")
feed_dict={x: train_x, y_: train_y}
op_to_restore = graph.get_tensor_by_name("op_to_restore:0")
print(sess.run(op_to_restore, feed_dict))
答案 1 :(得分:2)
最近与TF v1.5进行了类似的讨论。看来,应该将变量和操作添加到全局集合中,以便正确恢复它们。以下是MNIST数据集的两个片段,用于训练,保存和恢复模型。
训练并坚持
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import os
train_dir = 'train'
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x = tf.placeholder(tf.float32, [None, 784], name='x')
W = tf.Variable(tf.zeros([784, 10]), name='W')
b = tf.Variable(tf.zeros([10]), name='b')
y = tf.nn.softmax(tf.matmul(x, W) + b, name='y')
saver = tf.train.Saver(tf.trainable_variables())
sess = tf.InteractiveSession()
tf.add_to_collection('x', x)
tf.add_to_collection('yt', yt)
tf.add_to_collection('accuracy', accuracy)
with tf.Session() as sess:
latest_checkpoint = tf.train.latest_checkpoint(train_dir)
meta_path = '%s.meta' % latest_checkpoint
saver = tf.train.import_meta_graph(meta_path)
saver.restore(sess, latest_checkpoint)
x = tf.get_collection('x')[0]
yt = tf.get_collection('yt')[0]
accuracy = tf.get_collection('accuracy')[0]
feed_dict={x: mnist.test.images, yt: mnist.test.labels}
print(sess.run(accuracy, feed_dict))
恢复和评估
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import os
train_dir = 'train'
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
with tf.Session() as sess:
latest_checkpoint = tf.train.latest_checkpoint(train_dir)
meta_path = '%s.meta' % latest_checkpoint
saver = tf.train.import_meta_graph(meta_path)
saver.restore(sess, latest_checkpoint)
x = tf.get_collection('x')[0]
yt = tf.get_collection('yt')[0]
accuracy = tf.get_collection('accuracy')[0]
feed_dict={x: mnist.test.images, yt: mnist.test.labels}
print(sess.run(accuracy, feed_dict))
以下是相关TF documentation
的链接