以下代码包含一个带有回调函数的LSTM模型，一旦训练集准确率达到90%，该回调函数就会停止训练。

当我使用tensorflow-gpu=1.14时，它运行良好。

import tensorflow as tffrom tensorflow.keras.layers import Dense, Dropout,Bidirectional,Masking,LSTMfrom keras_self_attention import SeqSelfAttentiondef duo_bi_LSTM_model(X_train, y_train, X_test, y_test, num_classes, loss,batch_size=68, units=128, learning_rate=0.005,epochs=20, dropout=0.2,recurrent_dropout=0.2,optimizer='Adam'):            class myCallback(tf.keras.callbacks.Callback):        def on_epoch_end(self, epoch, logs={}):            if (logs.get('acc') > 0.90):                print("\nReached 90% accuracy so cancelling training!")                self.model.stop_training = True                         callbacks = myCallback()        adamopt = tf.keras.optimizers.Adam(lr=learning_rate, beta_1=0.9, beta_2=0.999, epsilon=1e-8)    RMSopt = tf.keras.optimizers.RMSprop(lr=learning_rate, rho=0.9, epsilon=1e-6)                model = tf.keras.models.Sequential()    model.add(Masking(mask_value=0.0, input_shape=(X_train.shape[1], X_train.shape[2])))    model.add(Bidirectional(        LSTM(units, dropout=dropout, recurrent_dropout=recurrent_dropout, return_sequences=True)))    model.add(Bidirectional(LSTM(units, dropout=dropout, recurrent_dropout=recurrent_dropout)))    model.add(Dense(num_classes, activation='softmax'))    opt = opt_select(optimizer)    model.compile(loss=loss,                  optimizer=opt,                  metrics=['accuracy'])    history = model.fit(X_train, y_train,                        batch_size=batch_size,                        epochs=epochs,                        validation_data=(X_test, y_test),                        verbose=1,                        callbacks=[callbacks])    score, acc = model.evaluate(X_test, y_test,                                batch_size=batch_size)    return history, thatX_train = np.random.rand(700, 50,34)y_train = np.random.choice([0, 1], 700)X_test = np.random.rand(100, 50, 34)y_test = np.random.choice([0, 1], 100)batch_size= 217epochs = 600dropout = 0.6Rdropout = 0.7learning_rate = 0.00001optimizer = 'RMS'loss = 'categorical_crossentropy'num_classes = y_train.shape[1]duo_bi_LSTM_his,yhat = duo_bi_LSTM_model(X_train,y_train,X_test,y_test,loss =loss,num_classes=num_classes,batch_size=batch_size,units=32,learning_rate=learning_rate,epochs=epochs,dropout = 0.5,recurrent_dropout=Rdropout,optimizer=optimizer)

在更新TensorFlow到2.2后，出现了以下错误：

~/Speech/Feature_engineering/LXRmodels.py in on_epoch_end(self, epoch, logs)    103     class myCallback(tf.keras.callbacks.Callback):    104         def on_epoch_end(self, epoch, logs={}):--> 105             if (logs.get('acc') > 0.90):    106                 print("\nReached 90% accuracy so cancelling training!")    107                 self.model.stop_training = TrueTypeError: '>' not supported between instances of 'NoneType' and 'float'

这是因为TensorFlow更新导致的问题吗？我应该如何修改代码？

回答：

你需要替换

logs.get('acc')

为

logs.get('accuracy')