我目前无法恢复此模型以进行预测。
代码:
def neural_network(data):
with tf.name_scope("network"):
layer1 = tf.layers.dense(data, 1000, activation=tf.nn.relu, name="hidden_layer1")
layer2 = tf.layers.dense(layer1, 1000, activation=tf.nn.relu, name="hidden_layer2")
output = tf.layers.dense(layer2, 2, name="output_layer")
return output
def evaluate():
with tf.name_scope("loss"):
global x
xentropy = tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=neural_network(x))
loss = tf.reduce_mean(xentropy, name="loss")
with tf.name_scope("train"):
optimizer = tf.train.AdamOptimizer()
training_op = optimizer.minimize(loss)
with tf.name_scope("exec"):
with tf.Session() as sess:
for i in range(1, 10):
sess.run(tf.global_variables_initializer())
sess.run(training_op, feed_dict={x: np.array(train_data).reshape([-1, 1]), y: label})
print "Training " + str(i)
saver = tf.train.Saver()
saver.save(sess, "saved_models/testing")
print "Model Saved."
def predict():
with tf.name_scope("predict"):
output = neural_network(x)
output = tf.nn.softmax(output)
with tf.Session() as sess:
saver = tf.train.import_meta_graph("saved_models/testing.meta")
# saver = tf.train.Saver()
saver.restore(sess, "saved_models/testing")
print sess.run(output, feed_dict={x: np.array([12003]).reshape([-1, 1])})
我已尝试使用tf.train.Saver()
进行恢复,但也会出现同样的错误。
The error given is ValueError: Variable hidden_layer1/kernel already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:
我已尝试为reuse=True
设置tf.layers.dense()
,但这导致我无法训练图表(提供与上述相同的ValueError但要求设置reuse=None
)。
我猜测它与会话中仍存在的图形有关,因此当我尝试恢复它时,它会检测到重复的图形。但是,我认为这不应该发生,因为会议已经结束。
链接到整个代码:gistlink
答案 0 :(得分:1)
我认为你在同一个图表中加载变量。为了测试,尝试创建一个新图并加载它。做这样的事情:
loaded_graph = tf.Graph()
with tf.Session(graph=loaded_graph) as sess:
# Load the graph with the trained states