Tensorflow 我怎样才能解决这个问题呢;运行时错误:试图使用关闭的会话;
当我运行下面的Tensorflow代码时,我收到一个运行时错误,上面写着“试图使用一个关闭的会话”。有人能告诉我如何避免这个错误吗?代码如下:Tensorflow 我怎样才能解决这个问题呢;运行时错误:试图使用关闭的会话;,tensorflow,tensorboard,Tensorflow,Tensorboard,当我运行下面的Tensorflow代码时,我收到一个运行时错误,上面写着“试图使用一个关闭的会话”。有人能告诉我如何避免这个错误吗?代码如下: # coding=utf-8 # (...imports omitted...) # (...some constant declarations and helper functions omitted: # max_steps, batch_size, log_dir, variable_with_weight_loss, variable_su
# coding=utf-8
# (...imports omitted...)
# (...some constant declarations and helper functions omitted:
# max_steps, batch_size, log_dir, variable_with_weight_loss, variable_summaries,
# layer1, full_layer1, full_layer2, full_layer3, loss
# ...)
def run():
image, label = read_and_decode('train.tfrecords')
batch_image, batch_label = get_batch(image, label, batch_size=128, crop_size=56)
test_image, test_label = read_and_decode('val.tfrecords')
test_images, test_labels = get_test_batch(test_image, test_label, batch_size=128, crop_size=56) # batch 生成测试
def feed_dict(train):
if train:
x=image_batch
y=label_batch
else:
x=img_batch
y=lab_batch
return {image_holder:x,label_holder:y}
saver=tf.train.Saver()
num_examples = 10000
num_iter = int(math.ceil(num_examples / batch_size))
true_count = 0
total_sample_count = num_iter * batch_size
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(log_dir + '/train', sess.graph)
test_writer = tf.summary.FileWriter(log_dir + '/test')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
for step in range(max_steps):
start_time = time.time()
image_batch, label_batch = sess.run([batch_image, batch_label])
# (...rest of function omitted...)
if __name__=='__main__':
run()
以下是运行代码时发生的异常:
File "/home/vrview/tensorflow/example/char/tfrecords/color2_board.py", line 238, in <module>
run()
File "/home/vrview/tensorflow/example/char/tfrecords/color2_board.py", line 207, in run
image_batch, label_batch = sess.run([batch_image, batch_label])
File "/home/vrview/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 767, in run
run_metadata_ptr)
File "/home/vrview/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 903, in _run
raise RuntimeError('Attempted to use a closed Session.')
RuntimeError: Attempted to use a closed Session.
文件“/home/vrview/tensorflow/example/char/tfrecords/color2_board.py”,第238行,在
运行()
文件“/home/vrview/tensorflow/example/char/tfrecords/color2_board.py”,第207行,运行中
image\u batch,label\u batch=sess.run([batch\u image,batch\u label])
文件“/home/vrview/tensorflow/local/lib/python2.7/site packages/tensorflow/python/client/session.py”,第767行,正在运行
运行_元数据_ptr)
文件“/home/vrview/tensorflow/local/lib/python2.7/site packages/tensorflow/python/client/session.py”,第903行,正在运行
raise RUNTIMERROR('试图使用关闭的会话')
RuntimeError:试图使用已关闭的会话。
谢谢你的帮助 任何使用
sess
的内容都应该在您的中,并将tf.Session()作为sess
。基本上,您只需缩进所有内容,从到步长范围(最大步长):
到test\u writer.close()
发生的情况是,您试图调用sess.run([batch\u image,batch\u label])
在之外,将tf.Session()作为sess
作用域,一旦sess对象超出作用域就会自动关闭。在我的例子中:
try:
model.load("model.tflearn")
except:
model.fit(training, output, n_epoch=1000, batch_size=8, show_metric=True)
model.save("model.tflearn")
我删除了
尝试:
和例外:
并且只使用最后两行就可以解决问题。非常感谢。我刚刚重新体验了。还有一个问题。当我运行它时,我发现了另一个错误:“TypeError:ParametertoMergeFrom()必须是同一个类的实例:expected tensorflow.Summary get list。”在“test\u writer.add\u Summary(predictions)”中,你知道如何解决它吗?Hi@Frank.Fan-尝试在不同的问题帖子中分别提问。这不仅是一个好的形式,它还做了两件事。它使您的问题更容易为其他人搜索,您+回答者将获得更多分数。干杯