Python keras自定义层中的0个训练参数
最近我从tensorflow切换到keras,我需要创建一个自定义层 我对类的定义如下:Python keras自定义层中的0个训练参数,python,tensorflow,deep-learning,keras,layer,Python,Tensorflow,Deep Learning,Keras,Layer,最近我从tensorflow切换到keras,我需要创建一个自定义层 我对类的定义如下: class Apply_conv2d(Layer): def __init__(self, **kwargs): super(Apply_conv2d, self).__init__(**kwargs) def build(self, input_shape): super(Apply_conv2d, self).build(input_shape) # Be sure to call
class Apply_conv2d(Layer):
def __init__(self, **kwargs):
super(Apply_conv2d, self).__init__(**kwargs)
def build(self, input_shape):
super(Apply_conv2d, self).build(input_shape) # Be sure to call this somewhere!
def call(self, x):
res = Conv2D(32, (1, 1), padding='same')(x)
self.shape = res.shape
res = k.reshape(res, [-1, self.shape[1] * self.shape[2] * self.shape[3]])
return res
def compute_output_shape(self, input_shape):
return (None, input_shape[3])
但是当我打印
model.summary()
时,我在使用该层时得到了0个可训练的参数
这种实现有什么问题?
非常感谢。
编辑
我将类定义更改为:
class Apply_conv2d(Layer):
def __init__(self, **kwargs):
self.trainable = True
super(Apply_conv2d, self).__init__(**kwargs)
def build(self, input_shape):
w = self.add_weight(name='kernel', shape=(1, 1, 2048, 32), initializer='uniform', trainable=True)
b = self.add_weight(name='kernel', shape=(32,), initializer='uniform', trainable=True)
self.kernel = [w, b]
super(Apply_conv2d, self).build(input_shape) # Be sure to call this somewhere!
def call(self, x):
res = Conv2D(32, (1, 1), padding='same', name='feature_conv', weights=self.kernel)(x)
self.shape = res.shape
res = k.reshape(res, [-1, self.shape[1] * self.shape[2] * self.shape[3]])
return res
def compute_output_shape(self, input_shape):
return (None, input_shape[3])
但这仍然不起作用…错误是:
Traceback (most recent call last):
File "C:\Program Files\JetBrains\PyCharm Community Edition
2017.2.3\helpers\pydev\pydevd.py", line 1668, in <module>
main()
File "C:\Program Files\JetBrains\PyCharm Community Edition
2017.2.3\helpers\pydev\pydevd.py", line 1662, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\pydevd.py", line 1072, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "C:/Users/Reza/Dropbox/Reza/VOC2012-D/script.py", line 123, in <module>
model = cl.get_model(inputs)
File "C:/Users/Reza/Dropbox/Reza/VOC2012-D\custom_layers.py", line 77, in get_model
x3 = Apply_conv2d()(x)
File "C:\Program Files\Python35\lib\site-packages\keras\engine\topology.py", line 603, in __call__
output = self.call(inputs, **kwargs)
File "C:/Users/Reza/Dropbox/Reza/VOC2012-D\custom_layers.py", line 104, in call
res = Conv2D(32, (1, 1), padding='same', name='feature_conv', weights=self.kernel)(x)
File "C:\Program Files\Python35\lib\site-packages\keras\engine\topology.py", line 583, in __call__
self.set_weights(self._initial_weights)
File "C:\Program Files\Python35\lib\site-packages\keras\engine\topology.py", line 1203, in set_weights
K.batch_set_value(weight_value_tuples)
File "C:\Program Files\Python35\lib\site-packages\keras\backend\tensorflow_backend.py", line 2239, in batch_set_value
value = np.asarray(value, dtype=dtype(x))
File "C:\Program Files\Python35\lib\site-packages\numpy\core\numeric.py", line 531, in asarray
return array(a, dtype, copy=False, order=order)
ValueError: setting an array element with a sequence.
回溯(最近一次呼叫最后一次):
文件“C:\Program Files\JetBrains\PyCharm社区版
2017.2.3\helpers\pydev\pydevd.py“,第1668行,在
main()
文件“C:\Program Files\JetBrains\PyCharm社区版
2017.2.3\helpers\pydev\pydevd.py“,第1662行,主视图
globals=debugger.run(setup['file'],None,None,is_模块)
文件“C:\Program Files\JetBrains\PyCharm Community Edition 2017.2.3\helpers\pydev\pydevd.py”,第1072行,正在运行
pydev_imports.execfile(文件、全局、局部)#执行脚本
文件“C:\Program Files\JetBrains\PyCharm社区版2017.2.3\helpers\pydev\\u pydev\u imps\\u pydev\u execfile.py”,execfile中第18行
exec(编译(内容+“\n”,文件,'exec'),全局,loc)
文件“C:/Users/Reza/Dropbox/Reza/VOC2012-D/script.py”,第123行,在
模型=cl.get_模型(输入)
get_模型中的文件“C:/Users/Reza/Dropbox/Reza/VOC2012-D\custom_layers.py”,第77行
x3=应用(x)
文件“C:\Program Files\Python35\lib\site packages\keras\engine\topology.py”,第603行,在调用中__
输出=自调用(输入,**kwargs)
文件“C:/Users/Reza/Dropbox/Reza/VOC2012-D\custom_layers.py”,第104行,在调用中
res=Conv2D(32,(1,1),padding='same',name='feature\u conv',weights=self.kernel)(x)
文件“C:\Program Files\Python35\lib\site packages\keras\engine\topology.py”,第583行,在调用中__
自设置权重(自初始权重)
文件“C:\Program Files\Python35\lib\site packages\keras\engine\topology.py”,第1203行,在集合中
K.批量设置值(权重值元组)
文件“C:\Program Files\Python35\lib\site packages\keras\backend\tensorflow\u backend.py”,第2239行,在批处理设置值中
value=np.asarray(value,dtype=dtype(x))
文件“C:\Program Files\Python35\lib\site packages\numpy\core\numeric.py”,第531行,在asarray中
返回数组(a,数据类型,copy=False,order=order)
ValueError:使用序列设置数组元素。
有什么建议吗?经过大量研究和尝试各种方法,我终于找到了解决方案。
我应该使用来自keras的原始conv操作,因此实现应该是这样的:
class Apply_conv2d(Layer):
def __init__(self, **kwargs):
super(Apply_conv2d, self).__init__(**kwargs)
self.trainable = True
def build(self, input_shape):
self.kernel = self.add_weight(name='kernel', shape=(1, 1, 2048, 32), initializer='uniform', trainable=True)
self.bias = self.add_weight(name='bias', shape=(32,), initializer='uniform', trainable=True)
def call(self, inputs, **kwargs):
outputs = k.conv2d(inputs, self.kernel)
outputs = k.bias_add(outputs, self.bias)
self.shape = outputs.shape
outputs = k.reshape(outputs, [-1, self.shape[1] * self.shape[2] * self.shape[3]])
return outputs
def compute_output_shape(self, input_shape):
return (input_shape[0], input_shape[3])
您缺少一个步骤,需要在
build()
期间创建可训练重量数组。但是,由于您的自定义层看起来像一个执行Conv2D->flant()
的层?您可能需要将权重数组设置为res。获取\u weights()
。顺便说一下,每次调用该层时,都会初始化一个新的Conv2D层。不确定这是不是故意的,也许你想把它移到建筑上去?@umutto我已经照你说的做了,但还是不起作用