如何修复“ValueError:操作数无法与形状(2592，)(4，)"一起广播在 TensorFlow 中? [英] How to fix "ValueError: Operands could not be broadcast together with shapes (2592,) (4,)" in Tensorflow?
问题描述
我目前正在设计一个 NoisyNet 层，正如这里的建议:"Noisy Networks for Exploration"，在 Tensorflow 中并获得标题中所示的维数误差，而两个张量的维数将在 filtered_output = keras.layers.merge.Multiply()([output, actions_input]) 应该(原则上)在打印所涉及的两个张量的维度时(原则上)彼此兼容，filtered_output 和 actions_input，其中两个张量似乎尺寸为 shape=(1, 4).
I am currently designing a NoisyNet layer, as proposed here: "Noisy Networks for Exploration", in Tensorflow and get the dimensionality error as indicated in the title, while the dimensions of the two tensors to be multiplied element-wise in line filtered_output = keras.layers.merge.Multiply()([output, actions_input]) should (in principle) be compatible with each other according to the printed output when printing the dimensions of both tensors involved, filtered_output and actions_input, where both tensors seem to be of dimension shape=(1, 4).
我在 Python3 中使用 Tensorflow 1.12.0.
I am using Tensorflow 1.12.0 in Python3.
相关代码如下:
import numpy as np
import tensorflow as tf
import keras
class NoisyLayer(keras.layers.Layer):
def __init__(self, in_shape=(1,2592), out_units=256, activation=tf.identity):
super(NoisyLayer, self).__init__()
self.in_shape = in_shape
self.out_units = out_units
self.mu_interval = 1.0/np.sqrt(float(self.out_units))
self.sig_0 = 0.5
self.activation = activation
self.assign_resampling()
def build(self, input_shape):
# Initializer
self.mu_initializer = tf.initializers.random_uniform(minval=-self.mu_interval, maxval=self.mu_interval) # Mu-initializer
self.si_initializer = tf.initializers.constant(self.sig_0/np.sqrt(float(self.out_units))) # Sigma-initializer
# Weights
self.w_mu = tf.Variable(initial_value=self.mu_initializer(shape=(self.in_shape[-1], self.out_units), dtype='float32'), trainable=True) # (1,2592)x(2592,4) = (1,4)
self.w_si = tf.Variable(initial_value=self.si_initializer(shape=(self.in_shape[-1], self.out_units), dtype='float32'), trainable=True)
# Biases
self.b_mu = tf.Variable(initial_value=self.mu_initializer(shape=(self.in_shape[0], self.out_units), dtype='float32'), trainable=True)
self.b_si = tf.Variable(initial_value=self.si_initializer(shape=(self.in_shape[0], self.out_units), dtype='float32'), trainable=True)
def call(self, inputs, resample_noise_flag):
if resample_noise_flag:
self.assign_resampling()
# Putting it all together
self.w = tf.math.add(self.w_mu, tf.math.multiply(self.w_si, self.w_eps))
self.b = tf.math.add(self.b_mu, tf.math.multiply(self.b_si, self.q_eps))
return self.activation(tf.linalg.matmul(inputs, self.w) + self.b)
def assign_resampling(self):
self.p_eps = self.f(self.resample_noise([self.in_shape[-1], 1]))
self.q_eps = self.f(self.resample_noise([1, self.out_units]))
self.w_eps = self.p_eps * self.q_eps # Cartesian product of input_noise x output_noise
def resample_noise(self, shape):
return tf.random.normal(shape, mean=0.0, stddev=1.0, seed=None, name=None)
def f(self, x):
return tf.math.multiply(tf.math.sign(x), tf.math.sqrt(tf.math.abs(x)))
frames_input = tf.ones((1, 84, 84, 4)) # Toy input
conv1 = keras.layers.Conv2D(16, (8, 8), strides=(4, 4), activation="relu")(frames_input)
conv2 = keras.layers.Conv2D(32, (4, 4), strides=(2, 2), activation="relu")(conv1)
flattened = keras.layers.Flatten()(conv2)
actionspace_size = 4
# NoisyNet
hidden = NoisyLayer(activation=tf.nn.relu)(inputs=flattened, resample_noise_flag=True)
output = NoisyLayer(in_shape=(1,256), out_units=actionspace_size)(inputs=hidden, resample_noise_flag=True)
actions_input = tf.ones((1,actionspace_size))
print('hidden:\n', hidden)
print('output:\n', output)
print('actions_input:\n', actions_input)
filtered_output = keras.layers.merge.Multiply()([output, actions_input])
当我运行代码时，输出如下所示:
The output, when I run the code, looks as follows:
hidden:
Tensor("noisy_layer_5/Relu:0", shape=(1, 256), dtype=float32)
output:
Tensor("noisy_layer_6/Identity:0", shape=(1, 4), dtype=float32)
actions_input:
Tensor("ones_5:0", shape=(1, 4), dtype=float32)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-4-f6df621eacab> in <module>()
68 print('actions_input:\n', actions_input)
69
---> 70 filtered_output = keras.layers.merge.Multiply()([output, actions_input])
2 frames
/usr/local/lib/python3.6/dist-packages/keras/layers/merge.py in _compute_elemwise_op_output_shape(self, shape1, shape2)
59 raise ValueError('Operands could not be broadcast '
60 'together with shapes ' +
---> 61 str(shape1) + ' ' + str(shape2))
62 output_shape.append(i)
63 return tuple(output_shape)
ValueError: Operands could not be broadcast together with shapes (2592,) (4,)
特别是，我想知道Operands中的数字一起广播是从哪里来的，因为数字重合将扁平化输入张量的长度 2592不能与形状(2592,)(4,)flattened 放到第一个噪声层，但是 - 在我看来 - 不是第二个噪声层 output 的输出维度的一部分再作为输入到上面指出的错误行.
Particularly, I am wondering where the number 2592 in Operands could not be broadcast together with shapes (2592,) (4,) comes from, since the number coincides with the length of the flattened input tensor flattened to the first noisy layer, but is -as it seems to me- not part of the output dimension of the second noisy layer output anymore, which in turn serves as the input to the erroneous line indicated above.
有人知道出了什么问题吗?
Does anyone know what's going wrong?
提前致谢，丹尼尔
推荐答案
如自定义图层文档，需要实现compute_output_shape(input_shape)方法:
compute_output_shape(input_shape):如果你的层修改了其输入的形状，您应该在此处指定形状转换逻辑.这允许 Keras 进行自动形状推断.
compute_output_shape(input_shape): in case your layer modifies the shape of its input, you should specify here the shape transformation logic. This allows Keras to do automatic shape inference.
如果不应用此方法，Keras 无法在不实际执行计算的情况下进行形状推断.
Keras can't do shape inference without actually executing the computation when you don't apply this method.
print(keras.backend.int_shape(hidden))
print(keras.backend.int_shape(output))
(1, 2592)
(1, 2592)
所以需要添加如下:
def compute_output_shape(self, input_shape):
return (input_shape[0], self.out_units)
另外，build()方法最后必须设置self.built = True，可以通过调用super(NoisyLayer, self).build(input_shape) 根据文档.
In addition, build() method must set self.built = True at the end, which can be done by calling super(NoisyLayer, self).build(input_shape) according to the document.
这篇关于如何修复“ValueError:操作数无法与形状(2592，)(4，)"一起广播在 TensorFlow 中?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！
