Python keras模型作为类的一部分时不起作用

所以我有一节课

class Trainer:
    def __init__(self,episodes):
        self.factorModel()

    def factorModel(self):
        self.model = Sequential()
        self.model.add(Conv2D(50, (3, 3), activation='relu', input_shape=(3,200,200),dim_ordering="th",strides=4))
        self.model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2) ))
        self.model.add(Conv2D(64, (5, 5), activation='relu') )
        self.model.add(MaxPooling2D(pool_size=(2, 2) ))
        self.model.add(Dense(1000, activation='relu'))
        self.model.add(Flatten())
        self.model.add(Dense(4, activation='softmax'))
        self.model.compile(loss='categorical_crossentropy',optimizer=Adam(lr=0.01), metrics=['accuracy'])


    def do(self,state):
        self.model.predict(np.array(state))[0]

当我尝试调用

do

时，我得到了类似

ValueError:Tensor Tensor（“稠密_2/Softmax:0”，shape=（？，4），dtype=float32）的错误，它不是这个图的一个元素。

当我使用相同的模型和相同的配置时，当我尝试将do函数作为线程运行时，问题就出现了，但我没有将do函数作为线程运行，一切都正常

完整错误消息

  File "/usr/lib/python2.7/threading.py", line 801, in __bootstrap_inner
    self.run()
  File "/usr/lib/python2.7/threading.py", line 754, in run
    self.__target(*self.__args, **self.__kwargs)
  File "path", line 141, in do
     self.model.predict_classes(state)[0]
  File "path/.local/lib/python2.7/site-packages/keras/engine/sequential.py", line 268, in predict_classes
    proba = self.predict(x, batch_size=batch_size, verbose=verbose)
  File "path/.local/lib/python2.7/site-packages/keras/engine/training.py", line 1456, in predict
    self._make_predict_function()
  File "path/.local/lib/python2.7/site-packages/keras/engine/training.py", line 378, in _make_predict_function
    **kwargs)
  File "path/.local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 3009, in function
    **kwargs)
  File "path/.local/lib/python2.7/site-packages/tensorflow/python/keras/backend.py", line 3479, in function
    return GraphExecutionFunction(inputs, outputs, updates=updates, **kwargs)
  File "path/.local/lib/python2.7/site-packages/tensorflow/python/keras/backend.py", line 3142, in __init__
    with ops.control_dependencies([self.outputs[0]]):
  File "path/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 5426, in control_dependencies
    return get_default_graph().control_dependencies(control_inputs)
  File "path/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 4867, in control_dependencies
    c = self.as_graph_element(c)
  File "path/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3796, in as_graph_element
    return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
  File "path/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3875, in _as_graph_element_locked
    raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("dense_2/Softmax:0", shape=(?, 4), dtype=float32) is not an element of this graph.

我尝试了这个问题的解决方案，所以我尝试在

self.factorModel（）

之后调用

self.model.\u make\u predict\u function（）
InvalidArgumentError:Tensor conv2d_1_输入：0，在图形中找不到feed_设备或fetch_设备中指定的输入

好的，我发现了这个问题，所以可能没有办法在线程中进行预测

因此，我根据对代码的建议进行了一些更改，现在看起来如下所示：

class Trainer:
    def __init__(self,episodes):
        self.factorModel()
        self.graph = tf.get_default_graph() 


    def factorModel(self):
        self.model = Sequential()
        self.model.add(Conv2D(50, (3, 3), activation='relu', input_shape=(3,200,200),dim_ordering="th",strides=4))
        self.model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2) ))
        self.model.add(Conv2D(64, (5, 5), activation='relu') )
        self.model.add(MaxPooling2D(pool_size=(2, 2) ))
        self.model.add(Dense(1000, activation='relu'))
        self.model.add(Flatten())
        self.model.add(Dense(4, activation='softmax'))
        self.model.compile(loss='categorical_crossentropy',optimizer=Adam(lr=0.01), metrics=['accuracy'])


    def do(self,state):
        with self.graph.as_default():
            self.model.predict(np.array(state))[0]

结果我得到了以下错误

Exception in thread Thread-1:
Traceback (most recent call last):
  File "/usr/lib/python2.7/threading.py", line 801, in __bootstrap_inner
    self.run()
  File "/usr/lib/python2.7/threading.py", line 754, in run
    self.__target(*self.__args, **self.__kwargs)
  File "path/Desktop/marioQProject/new_class_trainer.py", line 151, in do
    self.model.predict_classes(state)[0]
  File "path/.local/lib/python2.7/site-packages/keras/engine/sequential.py", line 268, in predict_classes
    proba = self.predict(x, batch_size=batch_size, verbose=verbose)
  File "path/.local/lib/python2.7/site-packages/keras/engine/training.py", line 1462, in predict
    callbacks=callbacks)
  File "path/.local/lib/python2.7/site-packages/keras/engine/training_arrays.py", line 324, in predict_loop
    batch_outs = f(ins_batch)
  File "patha/.local/lib/python2.7/site-packages/tensorflow/python/keras/backend.py", line 3292, in __call__
    run_metadata=self.run_metadata)
  File "path/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1458, in __call__
    run_metadata_ptr)
FailedPreconditionError: Error while reading resource variable conv2d_1/bias from Container: localhost. This could mean that the variable was uninitialized. Not found: Resource localhost/conv2d_1/bias/N10tensorflow3VarE does not exist.
         [[{{node conv2d_1/Reshape/ReadVariableOp}}]]

Tensorflow对多线程不是很友好，但有一个解决方法

这样做

课堂培训师：
定义初始化（自）：
self.factorModel（）
self.graph=tf.get_default_graph（）#[1]
def do（自身、状态）：
使用self.graph.as_default（）：#[2]
返回self.model.predict（np.array（state））[0]
def factorModel（自）：
self.model=Sequential（）
self.model.add（Conv2D（50，（3,3），activation='relu'，input_shape=（10,10,3），strips=4））
self.model.compile（loss='classifical_crossentropy'，optimizer='adam'，metrics=['accurity']）
t=培训师（）
def fn（）：
t、 do（np.zero（（1,10,10,3）））
如果uuuu name uuuuuu='\uuuuuuu main\uuuuuuu'：
thread\u one=threading.thread（目标=fn）
thread_two=线程。线程（目标=fn）
线程1.start（）
线程2.start（）

顺便说一句，如果您不特别需要先订购
频道
，那么我建议您使用TF standard
频道后订购
。无论您是使用opencv直接获取图像，还是使用numpy将枕头图像转换为ndarray，默认情况下，您将获得
频道最后一个

编辑
在发送到线程之前，您是否尝试过确保模型正常工作，例如

class Trainer:
    def __init__(self, episodes, model, graph):
        self.graph = graph
        self.model = model


model = Sequential()
model.add(Conv2D(...))
.
.
.
# make sure it runs here
model.predict(np.zeros((1, 3, 200, 200)))
# if you don't need to train then try not compile first
graph = tf.get_default_graph()
trainer = Trainer(episodes, model, graph)

还有可调用模型，而不是顺序模型，如

from keras import models, layers
inp = layers.Input((200, 200, 3))
x = layers.Conv2D(50, (3, 3), activation='relu',strides=4)(inp)
x = layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2) )(x)
x = layers.Conv2D(64, (5, 5), activation='relu')(x)
.
.
.
x = layers.Dense(4, activation='softmax')(x)
model = models.Model(inp, x)

请发布您的完整错误跟踪。@VivekMehta如果这很重要，请在threadInside
\uuuu init\uuuuu
中调用do函数，尝试初始化
self.model=None
，然后调用
self.factorModel（）
@YOLO我尝试了这一点，但不幸的是仍然存在同样的问题如果您正常调用它，您还会遇到问题吗，不在线程中？所以我尝试了您的解决方案，并得到以下错误
failedPremissionError:error，在从容器：localhost读取资源变量conv2d_1/bias时出错。这可能意味着变量未初始化。找不到：资源localhost/conv2d\u 1/bias/N10tensorflow3VarE不存在。
我想这可能是我的环境有问题，但idk是否可以将新的回溯和代码添加到主要问题中，尤其是前面的所有内容都是最新的，我假设正常的
模型.predict
也不起作用，因为您的回溯是
self.model.predict\u类
。我加了一些我能想到的东西。