Keras自定义图层ValueError:操作没有"None"用于渐变 [英] Keras Custom Layer ValueError: An operation has `None` for gradient
问题描述
我创建了一个自定义的Keras图层.该模型编译良好,但是在训练时却出现以下错误:
I have created a custom Keras Layer. The model compiles fine, but gives me the following error while training:
ValueError:操作没有
None
进行渐变.请确定您所有的操作都定义了渐变(即可区分的).不带渐变的常见操作:K.argmax,K.round,埃瓦尔.
ValueError: An operation has
None
for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.
我的自定义层中是否存在任何实现错误?
Is there any implementation error in my custom layer?
class SpatialLayer(Layer):
def __init__(self, output_dim, **kwargs):
self.output_dim = output_dim
super(SpatialLayer, self).__init__(**kwargs)
def build(self, input_shape):
self.bias = None
self.built = True
self.kernelA = self.add_weight(name='kernelA', shape=(input_shape[1]-2, self.output_dim), initializer='uniform', trainable=True)
def compute_output_shape(self, input_shape):
return (input_shape[0], input_shape[1]-2, input_shape[1]-2, self.output_dim)
def call(self, inputs):
x_shape = tf.shape(inputs)
top_values, top_indices = tf.nn.top_k(tf.reshape(inputs, (-1,)), 10, sorted=True,)
top_indices = tf.stack(((top_indices // x_shape[1]), (top_indices % x_shape[1])), -1)
top_indices = tf.cast(top_indices, dtype=tf.float32)
t1 = tf.reshape(top_indices, (1,10,2))
t2 = tf.reshape(top_indices, (10,1,2))
result = tf.norm(t1-t2, ord='euclidean', axis=2)
x = tf.placeholder(tf.float32, shape=[None, 10, 10, 1])
tensor_zeros = tf.zeros_like(x)
matrix = tensor_zeros + result
return K.dot(matrix, self.kernelA)
model = applications.VGG16(weights = "imagenet", include_top=False, input_shape = (img_width, img_height, 3))
model.layers.pop()
new_custom_layers = model.layers[-1].output
model.layers[-1].trainable = False
new_custom_layers = Conv2D(filters=1, kernel_size=(3, 3))(new_custom_layers)
new_custom_layers = SpatialLayer(output_dim=1)(new_custom_layers)
new_custom_layers = Flatten()(new_custom_layers)
new_custom_layers = Dense(1024, activation="relu")(new_custom_layers)
new_custom_layers = Dropout(0.5)(new_custom_layers)
new_custom_layers = Dense(1024, activation="relu")(new_custom_layers)
任何帮助将不胜感激.
说明
我的自定义Keras图层的输入是张量(?,12,12,1),它表示给定图像中的特征图.例如:
The input to my custom Keras Layer is a tensor (?, 12,12,1) that represents a feature map from a given image. For example:
[[147.00 20.14 ... 0 34.2 0 ]
[ 12.00 10.14 ... 0 45.2 0 ]
...
[100.00 60.14 ... 0 34.2 99.1]
[ 90.00 65.14 ... 0 12.2 00.1]]
我想从该张量中获取前10个值的坐标,例如:(0,0),(10,0)....,(10,11),即10个坐标.
I want to get the coordinates of the top 10 values from this tensor, for example: (0,0), (10,0) ...., (10,11), i.e., 10 coordinates.
最后,我想计算坐标之间的距离矩阵.我正在使用欧几里得距离.例如:
Finally, I want to calculate a distance matrix between the coordinates. I am using euclidean distance. For example:
coord1 coord2 ... coord9 cood10
coord1 0 12.3 13.1 2.3
coord2 1.3 0 3.2 9.1
.
.
.
coord9 4.2 5.2 0 4.2
coor10 1.1 5.6 9.1 0
此矩阵(?,10,10,1)将作为图层输出.
This matrix (?, 10,10,1) will be the layer output.
推荐答案
您无法通过不可微分的函数向后传播.并且您的功能是不可区分的.
You cannot backpropagate through functions that are not differentiable. And your function is not differentiable.
您舍弃了值 top_values
,而只保留了整数常量 top_indices
.
You discarded the values top_values
and kept only integer constants top_indices
.
在模型中使用此层的唯一方法是,如果之前的所有内容都不可训练.(或者,如果您找到另一种以可微分的方式计算您想要的东西的方法,这意味着:必须涉及输入值的操作)
The only way to use this layer in a model is if everything before it is not trainable. (Or if you find another way of calculating what you want in a differentiable way - this means: operations that must involve the input values)
这篇关于Keras自定义图层ValueError:操作没有"None"用于渐变的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!