将线性代数应用于张量流中的粗糙张量

Question

我使用tensorflow v2.7.0，并尝试使用粗糙张量创建ML模型。

问题是tf.linal.diag、tf.matmul和tf.linalg.det不能使用粗糙张量。我找到了一个变通方法，将numpy中的粗糙张量转换回粗糙张量，但在全局模型中应用层时，它不起作用。

以下代码正在中工作

import tensorflow as tf
class LRDet(tf.keras.layers.Layer):

def __init__(self,numItems,rank=10):
super(LRDet,self).__init__()
self.numItems = numItems
self.rank = rank

def build(self,input_shape):
V_init = tf.random_normal_initializer(mean=0.0,stddev=0.01)
D_init = tf.random_normal_initializer(mean=1.0,stddev=0.01)
self.V = tf.Variable(name='V',initial_value=V_init(shape=(self.numItems, self.rank)),trainable=True)
self.D = tf.Variable(name='D',initial_value=D_init(shape=(self.numItems,)),trainable=True)

def call(self,inputs):
batch_size = inputs.nrows()
subV = tf.gather(self.V,inputs)
subD = tf.square(tf.gather(self.D,inputs,batch_dims=0))#tf.linalg.diag(tf.square(tf.gather(D,Xrag,batch_dims=0)))
subD = tf.ragged.constant([tf.linalg.diag(subD[i]).numpy() for i in tf.range(batch_size)])
K = tf.ragged.constant([tf.matmul(subV[i],subV[i],transpose_b=True).numpy() for i in tf.range(batch_size)])
K = tf.add(K,subD)
res = tf.ragged.constant([tf.linalg.det(K[i].to_tensor()).numpy() for i in tf.range(batch_size)])
return res

numItems = 10
rank = 3
detX = LRDet(numItems,rank)
X = [[1,2],[3],[4,5,6]]
Xrag = tf.ragged.constant(X)
_ = detX(Xrag)

但一旦我在一个更全局的模型中使用了这一层，我就会出现以下错误

OperatorNotAllowedInGraphError:调用时遇到异常层"；lr_det_ 10"；(LRDet型(。

in user code:

File "<ipython-input-57-6b073a14386e>", line 18, in call  *
subD = tf.ragged.constant([tf.linalg.diag(subD[i]).numpy() for i in tf.range(batch_size)])

OperatorNotAllowedInGraphError: iterating over `tf.Tensor` is not allowed: AutoGraph did convert this function. This might indicate you are trying to use an unsupported feature.

我尝试使用tf.map_fn而不是使用.numbery((进行列表理解，但没有成功。

如有任何帮助，我们将不胜感激。

Answer 1

这里有一个使用tf.map_fn运行的选项；然而，由于最近出现了一个关于tf.map_fn、粗糙张量和GPU:的错误，它目前仅在CPU上运行

import os
os.environ["CUDA_VISIBLE_DEVICES"] = "-1" # do not access GPU
import tensorflow as tf
class LRDet(tf.keras.layers.Layer):

def __init__(self,numItems,rank=10):
super(LRDet,self).__init__()
self.numItems = numItems
self.rank = rank

def build(self,input_shape):
V_init = tf.random_normal_initializer(mean=0.0,stddev=0.01)
D_init = tf.random_normal_initializer(mean=1.0,stddev=0.01)
self.V = tf.Variable(name='V',initial_value=V_init(shape=(self.numItems, self.rank)),trainable=True)
self.D = tf.Variable(name='D',initial_value=D_init(shape=(self.numItems,)),trainable=True)
def call(self,inputs):
batch_size = inputs.nrows()
subV = tf.gather(self.V,inputs)

subD = tf.square(tf.gather(self.D, inputs, batch_dims=0))
subD = tf.map_fn(self.diag, subD, fn_output_signature=tf.RaggedTensorSpec(shape=[1, None, None],
dtype=tf.type_spec_from_value(subD).dtype,
ragged_rank=2,
row_splits_dtype=tf.type_spec_from_value(subD).row_splits_dtype))
subD = tf.squeeze(subD, 1)

K = tf.map_fn(self.matmul, subV, fn_output_signature=tf.RaggedTensorSpec(shape=[1, None, None],
dtype=tf.type_spec_from_value(subV).dtype,
ragged_rank=2,
row_splits_dtype=tf.type_spec_from_value(subV).row_splits_dtype))
K = tf.squeeze(K, 1)
K = tf.add(K,subD)
res = tf.map_fn(self.det, K, tf.TensorSpec(shape=(), dtype=tf.float32, name=None))
return res

def diag(self, x):
return tf.ragged.stack(tf.linalg.diag(x))
def matmul(self, x):
return tf.ragged.stack(tf.matmul(x, x,transpose_b=True))
def det(self, x):
return tf.linalg.det(x.to_tensor())

numItems = 10
rank = 3
input = tf.keras.layers.Input(shape=(None,), ragged=True, dtype=tf.int32)
detX = LRDet(numItems,rank)
output = detX(input)
model = tf.keras.Model(input, output)
X = [[1,2],[3],[4,5,6]]
Xrag = tf.ragged.constant(X)
y = tf.random.normal((3, 1))
model.compile(loss='mse', optimizer='adam')
model.fit(Xrag, y, batch_size=1, epochs=1)