Keras 模型在属于类时不起作用

Question

所以我有一个类

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，我收到类似ValueError: Tensor Tensor("dense_2/Softmax:0", shape=(?, 4), dtype=float32) is not an element of this graph.的错误 当我使用相同的模型和相同的配置但未将 do 函数作为线程

运行时出现问题 一切正常完整的错误消息

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.

我尝试了这个问题链接的解决方案，所以我尝试在self.factorModel()后打电话给self.model._make_predict_function()，但结果我得到了这个错误InvalidArgumentError: Tensor conv2d_1_input:0, specified in either feed_devices or fetch_devices was not found in the Graph

好的，我找到了这个问题链接，所以可能无法在线程中进行预测

所以我根据对代码的建议进行了一些更改，所以现在看起来像这样：

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}}]]

Answer 1

Tensorflow对多线程并不友好，但有一个解决方法。

这样做

class Trainer:
def __init__(self):
self.factorModel()
self.graph = tf.get_default_graph()  # [1]
def do(self, state):
with self.graph.as_default():  # [2]
return self.model.predict(np.array(state))[0]
def factorModel(self):
self.model = Sequential()
self.model.add(Conv2D(50, (3, 3), activation='relu', input_shape=(10, 10, 3), strides=4))
self.model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
t = Trainer()
def fn():
t.do(np.zeros((1, 10, 10, 3)))
if __name__ == '__main__':
thread_one = threading.Thread(target=fn)
thread_two = threading.Thread(target=fn)
thread_one.start()
thread_two.start()

顺便说一句，如果您不需要特别channel first订购，那么我建议您改用 TF 标准channel last。天气你直接用opencv获取图像，或者使用numpy将枕头图像转换为ndarray，默认情况下你会得到channel last。

编辑

您是否尝试过在发送到线程之前确保模型正常工作，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)

也是可调用模型而不是顺序模型，例如

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)