我想执行我的图模型,但我遇到了困难。代码是:
epoch_x, epoch_y = features, labels
sess.run(optimizer, feed_dict = {"x:0": epoch_x, "y:0": epoch_y})
,错误是:
----------------------------------------------- ---------------------------- KeyError Traceback(最近一次调用 持续) d:\ AnacondaIDE \ LIB \站点包\ tensorflow \ python的\客户端\ session.py 在_run中(self,handle,fetches,feed_dict,options,run_metadata)
1067 subfeed_t = self.graph.as_graph_element(subfeed, allow_tensor =真, - > 1068 allow_operation = False)1069除了例外e:D:\ AnacondaIDE \ lib \ site-packages \ tensorflow \ python \ framework \ ops.py in as_graph_element(self,obj,allow_tensor,allow_operation)2707
与self._lock: - > 2708返回self._as_graph_element_locked(obj,allow_tensor,allow_operation)2709D:\ AnacondaIDE \ lib \ site-packages \ tensorflow \ python \ framework \ ops.py in _as_graph_element_locked(self,obj,allow_tensor,allow_operation)2749“存在。操作,%s,不 存在于“ - > 2750“图。” %(repr(name),repr(op_name)))2751尝试:
KeyError:“名称'x:0'指的是不存在的Tensor 操作'x',图中不存在。“
在处理上述异常期间,发生了另一个异常:
TypeError Traceback(最近一次调用 最后)in() 22#feed_dict = {x:epoch_x,y:epoch_y} 23 ---> 24 sess.run(optimizer,feed_dict = {“x:0”:epoch_x,“y:0”:epoch_y}) 25 train_loss.append(sess.run(cost,feed_dict = {x:epoch_x,y:epoch_y})) 26 train_accuracy.append(sess.run(accr,feed_dict = {x:epoch_x,y:epoch_y}))
d:\ AnacondaIDE \ lib中\站点包\ tensorflow \蟒\客户\ session.py 在运行中(self,fetches,feed_dict,options,run_metadata) 893尝试: 894 result = self._run(None,fetches,feed_dict,options_ptr, - > 895 run_metadata_ptr) 896如果run_metadata: 897 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
d:\ AnacondaIDE \ lib中\站点包\ tensorflow \蟒\客户\ session.py 在_run中(self,handle,fetches,feed_dict,options,run_metadata)
1069除了例外e:1070加注 TypeError('无法将feed_dict键解释为Tensor:' - > 1071 + e.args [0])1072 1073 if isinstance(subfeed_val,ops.Tensor):TypeError:无法将feed_dict键解释为Tensor:名称'x:0' 是指不存在的张量。操作“x”没有 存在于图中。
我也尝试过以下声明:
sess.run(optimizer, feed_dict = {"x": epoch_x, "y": epoch_y})
然后错误是:
----------------------------------------------- ---------------------------- NameError Traceback(最近一次调用 最后)in() 22#feed_dict = {x:epoch_x,y:epoch_y} 23 ---> 24 sess.run(optimizer,feed_dict = {x:epoch_x,y:epoch_y}) 25 train_loss.append(sess.run(cost,feed_dict = {x:epoch_x,y:epoch_y})) 26 train_accuracy.append(sess.run(accr,feed_dict = {x:epoch_x,y:epoch_y}))
NameError:名称'x'未定义
请注意print(features.shape)
会产生:
(4000,6000,3)
我正在使用Tensorflow-gpu(1.3.0)。
答案 0 :(得分:3)
在feed dict中应该没有引号,但键应该是指向你想要提供的占位符的python变量。
例如,如果在声明占位符时有类似
的内容pl_ = tf.placeholder(...., name='placeholder_1')
然后你应该跑这个
sess.run(...., feed_dict={pl_: value})
而不是这个
sess.run(..., feed_dict={'placeholder_1': value})