将线性代数应用于张量流中参差不齐的张量

Question

我正在使用 tensorflow v2.7.0 并尝试使用参差不齐的张量创建 ML 模型。

问题是 tf.linalg.diag、tf.matmul 和 tf.linalg.det 无法处理参差不齐的张量。我通过在 numpy 中转换参差不齐的张量并将其转换回参差不齐的张量找到了一种解决方法，但是在全局模型中应用该层时它不起作用。

以下代码有效

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)

但是一旦我在更全局的模型中使用了这一层，我就会遇到以下错误

OperatorNotAllowedInGraphError: Exception encountered when calling layer "lr_det_10" (type LRDet).

    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 .numpy() 的列表理解但没有成功。

非常感谢任何帮助。

Answer 1

这里有一个选项运行tf.map_fn；但是，由于最近 bug 关于 tf.map_fn、参差不齐的张量和 GPU，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)

将线性代数应用于张量流中参差不齐的张量

Apply linear algebra to ragged tensor in tensorflow

python

tensorflow

tensorflow2.0

ragged-tensors