训练时，我将权重存储在张量流变量字典中。我将该权重字典与一些数据一起传递给“模型”功能，以获得所需的输出。
经过培训后，我想将该字典存储在文件中，以便可以重新创建它。这样，我可以通过简单地将权重字典与新数据一起传递到同一模型函数来应用学习的权重。
根据the documentation，只需将权重字典传递给保护程序，就可以将这些权重保存为正确的名称。然后，我应该能够在应用程序函数中创建相同的词典，然后恢复保存的值。但是，如果执行此操作，则会出现“值未初始化”错误。谁能帮助我找到我做错了什么？
最少的独立代码示例和相应的错误：
import tensorflow as tf
import numpy as np
# first train a linear model on random vectors of length 5 and store the trained parameters.
# Then load those parameters and try to apply them to a new vector.
def run():
train_model()
apply_model()
def train_model():
# create random training data: 100 vectors of length 5 for both input and output.
train_data = np.random.random((100,5))
train_labels = np.random.random((100,5))
train_data_node = tf.placeholder(tf.float32, shape=(5), name="train_data_node")
train_labels_node = tf.placeholder(tf.float32, shape=(5), name="train_labels_node")
weights = defineWeights()
prediction = model(train_data_node, weights)
loss = tf.norm(prediction - train_labels_node)
train_op = tf.train.AdagradOptimizer(learning_rate=1).minimize(loss)
saver = tf.train.Saver(weights)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# train for 50 epochs on all 100 training examples, with a batchsize of 1.
for _ in range(50):
for i in range(100):
batch_data = train_data[i,:]
batch_labels = train_labels[i,:]
feed_dict = {train_data_node: batch_data, train_labels_node: batch_labels}
sess.run([train_op, loss, weights], feed_dict=feed_dict)
saver.save(sess, '/results/weights')
def apply_model():
sess = tf.Session()
weights = defineWeights()
new_saver = tf.train.import_meta_graph('/results/weights.meta')
new_saver.restore(sess, tf.train.latest_checkpoint('/results'))
print(model(np.random.random(5).astype(np.float32), weights).eval(session=sess))
def model(data, weights):
# multiply the matrix weights['a'] with the vector data
l1 = tf.matmul(tf.expand_dims(data,0), weights['a'])
l1 = l1 + weights['b']
return l1
def defineWeights():
weights = {
'a': tf.Variable(tf.random_normal([5, 5],
stddev=0.01,
dtype = tf.float32),
name = 'a'),
'b': tf.Variable(tf.random_normal([5]), name = 'b'),
}
return weights
在上面的代码中调用'run（）'函数会产生以下错误：
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "/usr/local/lib/python2.7/dist-packages/myFolder/example.py", line 8, in run
apply_model()
File "/usr/local/lib/python2.7/dist-packages/myFolder/example.py", line 50, in apply_model
print(model(np.random.random(5).astype(np.float32), weights).eval(session=sess))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 569, in eval
return _eval_using_default_session(self, feed_dict, self.graph, session)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3741, in _eval_using_default_session
return session.run(tensors, feed_dict)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 786, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 994, in _run
feed_dict_string, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1044, in _do_run
target_list, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1064, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.FailedPreconditionError: Attempting to use uninitialized value a_1
[[Node: a_1/read = Identity[T=DT_FLOAT, _class=["loc:@a_1"], _device="/job:localhost/replica:0/task:0/gpu:0"](a_1)]]
[[Node: add_2/_5 = _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_add_2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op u'a_1/read', defined at:
File "<string>", line 1, in <module>
File "/usr/local/lib/python2.7/dist-packages/myFolder/example.py", line 8, in run
apply_model()
File "/usr/local/lib/python2.7/dist-packages/myFolder/example.py", line 45, in apply_model
weights = defineWeights()
File "/usr/local/lib/python2.7/dist-packages/myFolder/example.py", line 63, in defineWeights
name = 'a'),
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 a_1
[[Node: a_1/read = Identity[T=DT_FLOAT, _class=["loc:@a_1"], _device="/job:localhost/replica:0/task:0/gpu:0"](a_1)]]
[[Node: add_2/_5 = _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_add_2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
最佳答案
我编辑了您的代码以使其正常工作-一种可能的方式！核实。
import tensorflow as tf
import numpy as np
# first train a linear model on random vectors of length 5 and store the trained parameters.
# Then load those parameters and try to apply them to a new vector.
def run():
train_model()
apply_model()
def train_model():
# create random training data: 100 vectors of length 5 for both input and output.
train_data = np.random.random((100,5))
train_labels = np.random.random((100,5))
train_data_node = tf.placeholder(tf.float32, shape=(5), name="train_data_node")
train_labels_node = tf.placeholder(tf.float32, shape=(5), name="train_labels_node")
weights = defineWeights()
prediction = model(train_data_node, weights)
prediction = tf.identity(prediction, name="prediction")
loss = tf.norm(prediction - train_labels_node)
train_op = tf.train.AdagradOptimizer(learning_rate=1).minimize(loss)
saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# train for 50 epochs on all 100 training examples, with a batchsize of 1.
for _ in range(50):
for i in range(100):
batch_data = train_data[i,:]
batch_labels = train_labels[i,:]
feed_dict = {train_data_node: batch_data, train_labels_node: batch_labels}
sess.run([train_op, loss, weights], feed_dict=feed_dict)
saver.save(sess, 'results/model')
print("Trained Weights")
print(sess.run(weights))
def apply_model():
sess = tf.Session()
new_saver = tf.train.import_meta_graph('results/model.meta')
new_saver.restore(sess, tf.train.latest_checkpoint('results'))
print("Loaded Weights")
print(sess.run(['a:0','b:0']))
prediction = tf.get_default_graph().get_tensor_by_name("prediction:0")
train_data_node = tf.get_default_graph().get_tensor_by_name("train_data_node:0")
test_data = np.random.random(5).astype(np.float32)
pred = sess.run([prediction],feed_dict={train_data_node:test_data})
print("Prediction")
print(pred)
def model(data, weights):
# multiply the matrix weights['a'] with the vector data
l1 = tf.matmul(tf.expand_dims(data,0), weights['a'])
l1 = l1 + weights['b']
return l1
def defineWeights():
weights = {
'a': tf.Variable(tf.random_normal([5, 5],
stddev=0.01,
dtype = tf.float32),
name = 'a'),
'b': tf.Variable(tf.random_normal([5]), name = 'b'),
}
return weights
def main(_):
run()
if __name__ == '__main__':
tf.app.run(main=main)
输出：
Trained Weights
{'a': array([[ 0.01243415, -0.42879951, 0.0174435 , -0.24622701, 0.35309449],
[ 0.03154161, -0.08194152, 0.09223857, -0.15719411, -0.06323836],
[-0.03263358, 0.05096304, 0.1769278 , -0.17564282, 0.04325204],
[-0.17412457, -0.00338688, 0.08468977, -0.06877152, -0.02180972],
[ 0.25160244, -0.19224152, 0.14535131, -0.20594895, -0.03813718]], dtype=float32), 'b': array([ 0.33825615, 0.79861975, 0.30609566, 0.91897982, 0.20577262], dtype=float32)}
I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:01:00.0)
Loaded Weights
[array([[ 0.01243415, -0.42879951, 0.0174435 , -0.24622701, 0.35309449],
[ 0.03154161, -0.08194152, 0.09223857, -0.15719411, -0.06323836],
[-0.03263358, 0.05096304, 0.1769278 , -0.17564282, 0.04325204],
[-0.17412457, -0.00338688, 0.08468977, -0.06877152, -0.02180972],
[ 0.25160244, -0.19224152, 0.14535131, -0.20594895, -0.03813718]], dtype=float32), array([ 0.33825615, 0.79861975, 0.30609566, 0.91897982, 0.20577262], dtype=float32)]
Prediction
[array([[ 0.3465074 , 0.42139536, 0.71310139, 0.30854774, 0.32671657]], dtype=float32)]
说明：
命名恢复后要访问的张量。
还原图形并还原您命名的变量-在apply_model（）中显示
使用feed_dict将新的test_data馈入占位符
问题：
我尝试使用sess.run（tf.global_variables_initializer（）），但它正在将变量重新初始化为新的随机值。 （使用TF 1.0）
我希望这有帮助 ！
关于python - 如何在TensorFlow中存储和重建权重字典，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/43983528/