ValueError: tf.function-decorated function tried to create variables on non-first call while using Custom Loss Function

Question

我正在尝试创建一个三元组损失函数来计算两个句子之间的相似度，如下所示：

def TripletLoss(y_true,y_pred, margin=0.25,batch_size = 64):
    v1, v2 = y_pred[:,:128],y_pred[:,-128:]
    scores = K.dot(v1, K.transpose(v2))
    positive = tf.linalg.diag_part(scores)
    negative_without_positive = scores - 2 * K.eye(batch_size)

    closest_negative = tf.reduce_max(negative_without_positive, axis=1)

    negative_zero_on_duplicate = scores * (1.0 - K.eye(batch_size))
    
    mean_negative = K.sum(negative_zero_on_duplicate, axis=1) / (batch_size-1)
    
    triplet_loss1 = K.maximum(0.0, margin - positive + closest_negative)
    
    triplet_loss2 = K.maximum(0.0, margin - positive + mean_negative)
    
    triplet_loss = K.mean(triplet_loss1 + triplet_loss2)

    return triplet_loss

我的模型如下：

input1 = keras.Input(shape=(train_data1.shape[1],))
input2 = keras.Input(shape=(train_data1.shape[1],))

encoding1 = base_model(input1)
encoding2 = base_model(input2)

merged = layers.Concatenate()([encoding1, encoding2])

model = models.Model(inputs = [input1, input2], outputs = merged)

基础模型是：

def calculate_mean(x, axis=1):
    return K.mean(x, axis=axis)

def normalize(x):
        return x / K.sqrt(K.sum(x * x, axis=-1, keepdims=True))

base_model = models.Sequential()
base_model.add(layers.Embedding(input_dim=len(vocab)+2, output_dim=128))
base_model.add(layers.LSTM(128, return_sequences=True))
base_model.add(layers.Lambda(calculate_mean, name='mean'))
base_model.add(layers.Lambda(normalize, name='normalize'))

现在，当我使用那个损失函数编译模型时

model.compile(
    optimizer = Adam(0.001),
    loss = TripletLoss
)

它没有给出任何错误。但是当我使用 fit 方法训练它时，它给我的错误是：

ValueError: tf.function-decorated function tried to create variables on non-first call.

如果我使用其他损失函数，效果会很好。不知道这里的损失函数有什么问题

Answer 1

也许可以用 tf.eye 尝试以下操作：

import tensorflow as tf

from tensorflow.keras import backend as K

def TripletLoss(margin=0.25):
    def triplet(y_true,y_pred):
      batch_size = tf.cast(tf.shape(y_true)[0], dtype=tf.float32)
      v1, v2 = y_pred[:,:128],y_pred[:,-128:]
      scores = K.dot(v1, K.transpose(v2))
      positive = tf.linalg.diag_part(scores)
      negative_without_positive = scores - 2 * tf.eye(batch_size)

      closest_negative = tf.reduce_max(negative_without_positive, axis=1)

      negative_zero_on_duplicate = scores * (1.0 - tf.eye(batch_size))
      
      mean_negative = K.sum(negative_zero_on_duplicate, axis=1) / (batch_size-1)
      
      triplet_loss1 = K.maximum(0.0, margin - positive + closest_negative)
      
      triplet_loss2 = K.maximum(0.0, margin - positive + mean_negative)
      
      triplet_loss = K.mean(triplet_loss1 + triplet_loss2)

      return triplet_loss
    return triplet

triplet_loss = TripletLoss()

def calculate_mean(x, axis=1):
    return K.mean(x, axis=axis)

def normalize(x):
        return x / K.sqrt(K.sum(x * x, axis=-1, keepdims=True))

base_model = tf.keras.Sequential()
base_model.add(tf.keras.layers.Embedding(input_dim=50, output_dim=128))
base_model.add(tf.keras.layers.LSTM(128, return_sequences=True))
base_model.add(tf.keras.layers.Lambda(calculate_mean, name='mean'))
base_model.add(tf.keras.layers.Lambda(normalize, name='normalize'))

input1 = tf.keras.layers.Input(shape=(50,))
input2 = tf.keras.layers.Input(shape=(50,))

encoding1 = base_model(input1)
encoding2 = base_model(input2)

merged = tf.keras.layers.Concatenate()([encoding1, encoding2])

model = tf.keras.Model(inputs = [input1, input2], outputs = merged)
model.compile(
    optimizer = tf.keras.optimizers.Adam(0.001),
    loss = triplet_loss
)

x = tf.random.uniform((500, 50), maxval=50, dtype=tf.int32)
y = tf.random.uniform((500, 256))
model.fit([x, x], y, epochs=2, batch_size=64)

Epoch 1/2
8/8 [==============================] - 6s 237ms/step - loss: 0.0037
Epoch 2/2
8/8 [==============================] - 2s 233ms/step - loss: 5.4691e-04
<keras.callbacks.History at 0x7fd249072d50>

ValueError: tf.function-decorated function tried to create variables on non-first call while using Custom Loss Function

ValueError: tf.function-decorated function tried to create variables on non-first call while using Custom Loss Function

python

nlp

deep-learning

keras

tensorflow