Question

我在运行此代码时遇到了让keras工作的问题：

from keras.layers import Conv2D,UpSampling2D,MaxPooling2D
import keras 


(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_test = x_test.reshape(-1,28,28,1)
x_train = x_train.reshape(-1,28,28,1)

def caev1():
    input_shape = (28,28,1)
    model = Sequential()
    model.add(Conv2D(32, kernel_size=(3, 3), activation='relu',padding = ' 
    same',input_shape=input_shape))
    model.add(MaxPooling2D(pool_size = (2,2),padding = 'valid'))
    #(14,14,32)

    model.add(Conv2D(16, kernel_size=(3, 3), activation='relu',padding = 
   'same'))
    model.add(MaxPooling2D(pool_size = (2,2),padding = 'valid'))
    #(7,7,16)

    model.add(Conv2D(16, kernel_size=(3, 3), activation='relu',padding = 
    'same'))
    model.add(UpSampling2D())
    #(14,4,16)

    model.add(Conv2D(32, kernel_size=(3, 3), activation='relu',padding = 
    'same'))
    model.add(UpSampling2D())
    #(28,28,16)

    model.add(Conv2D(1,3,activation = 'sigmoid',padding = 'same'))

    model.compile(optimizer='adam', loss='binary_crossentropy')

    return model


m = caev1()

m.fit(x_train, x_train,epochs = 1, batch_size = 128, validation_data = 
(x_test,x_test))

我收到此错误

2018-03-24 14:00:56.136200: E C:\tf_jenkins\workspace\rel-win\M\windows- 
gpu\PY\36\tensorflow\stream_executor\cuda\cuda_dnn.cc:378] Loaded runtime 
CuDNN library: 7101 (compatibility version 7100) but source was compiled 
with 7003 (compatibility version 7000).  If using a binary install, upgrade 
your CuDNN library to match.  If building from sources, make sure the 
library loaded at runtime matches a compatible version specified during 
compile configuration.
2018-03-24 14:00:56.138654: F C:\tf_jenkins\workspace\rel-win\M\windows- 
gpu\PY\36\tensorflow\core\kernels\conv_ops.cc:717] Check failed: stream- 
>parent()->GetConvolveAlgorithms( 
conv_parameters.ShouldIncludeWinogradNonfusedAlgo<T>(), &algorithms)

所以从理论上讲我遇到了cudnn版本的问题，但是当运行另一个非常相似的代码（完全连接的层而不是conv）时，错误不会发生并且它完美地运行

cudnn版本不一致时出错

0 个答案: