为什么ImageDataGenerator mdoel.fit_生成器显示错误函数调用堆栈:keras_scratch_图形?
数据发生器安装(X_系列)为什么ImageDataGenerator mdoel.fit_生成器显示错误函数调用堆栈:keras_scratch_图形?,keras,deep-learning,image-recognition,Keras,Deep Learning,Image Recognition,数据发生器安装(X_系列) 内部错误:Blas-GEMM启动失败:a.shape=(863136),b.shape=(3136256),m=86,n=256,k=3136 [[node densite_1/MatMul(定义于c:\users\shahj\appdata\local\programs\python35\lib\site packages\tensorflow\u core\python\framework\ops.py:1751)][Op:[u推理\u keras\u scra
内部错误:Blas-GEMM启动失败:a.shape=(863136),b.shape=(3136256),m=86,n=256,k=3136 [[node densite_1/MatMul(定义于c:\users\shahj\appdata\local\programs\python35\lib\site packages\tensorflow\u core\python\framework\ops.py:1751)][Op:[u推理\u keras\u scratch\u图形\u 1528] 函数调用堆栈:
keras_scratch_图 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”
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
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])