Python 为什么keras model.fit_generator()显示错误,如无法获取卷积算法?

Python 为什么keras model.fit_generator()显示错误,如无法获取卷积算法?,python,tensorflow,keras,deep-learning,Python,Tensorflow,Keras,Deep Learning,tensorflow版本->2.0.0 keras版本-->2.2.4 datagen = ImageDataGenerator( featurewise_center=False, # set input mean to 0 over the dataset samplewise_center=False, # set each sample mean to 0 featurewise_std_normalization=False, # divide input

tensorflow版本
->2.0.0

keras版本
-->2.2.4

datagen = ImageDataGenerator(
    featurewise_center=False,  # set input mean to 0 over the dataset
    samplewise_center=False,  # set each sample mean to 0
    featurewise_std_normalization=False,  # divide inputs by std of the dataset
    samplewise_std_normalization=False,  # divide each input by its std
    zca_whitening=False,  # apply ZCA whitening
    rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)
    zoom_range = 0.1, # Randomly zoom image 
    width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
    height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
    horizontal_flip=False,  # randomly flip images
    vertical_flip=False)  # randomly flip images

datagen.fit(X_train)


history = model.fit_generator(datagen.flow(X_train,Y_train,batch_size=batch_size,),
                         epochs=epochs,validation_data=(X_val,Y_val),
                         verbose=2,steps_per_epoch=X_train.shape[0] // batch_size,
                         callbacks=[learning_rate_reduction])
错误:

未知错误:获取卷积算法失败。这可能是 因为cuDNN无法初始化,所以请尝试查看是否出现警告 上面打印了日志消息。[作品:第二辑]

cuda版本-->10.0 cudnn版本-->7.6.4

tensorflow gpu版本-->2.0.0
keras gpu版本-->'2.2.4'

您是否在gpu上运行?如果是,你有什么版本的CUDA,CUDNN?是的,我正在运行GPU。但是我不知道要安装哪种CUDA和CUDNN版本?你需要CUDA版本10和CUDNN版本7.4.1,以及英伟达GPU驱动程序。你可以看到说明。谢谢你已经安装了它并为我工作了!