Question

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])

内部错误：Blas GEMM启动失败：a.shape =（86，3136），b.shape =（3136，256），m = 86，n = 256，k = 3136 [[node density_1 / MatMul（在c：\ users \ shahj \ appdata \ local \ programs \ python \ python35 \ lib \ site-packages \ tensorflow_core \ python \ framework \ ops.py：1751定义）]] [操作：__ inference_keras_scratch_graph_1528 ]

函数调用堆栈：
keras_scratch_graph

Answer 1

try this worked for me

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'

为什么ImageDataGenerator mdoel.fit_generator显示错误函数调用堆栈：keras_scratch_graph？

1 个答案: