如何解决conv2d错误？

我是python和tensorflow的初学者。我在尺寸问题上有错误。有没有人可以解决这个问题？我的代码如下，错误来自'aux = Convolution2D'line。错误消息是“ValueError：由'conv2d_15 /卷积'（op：'Conv2D'）从10减去512所导致的负尺寸大小，输入形状为：[？，10,10,512]，[10,512,512,1]如何解决conv2d错误？

。

这是tensorflow后端

def _conv_bn_relu(nb_filter, nb_row, nb_col, subsample=(1, 1)): 
     def f(input): 
      conv = Convolution2D(nb_filter=nb_filter, nb_row=nb_row, nb_col=nb_col, 
           subsample=subsample, init="he_normal", 
           border_mode="same")(input) 
      norm = BatchNormalization()(conv) 
      return ELU()(norm) 
     return f 

def get_unet(): 
    inputs = Input((img_rows, img_cols, 1), name='main_input') 
    conv1 = _conv_bn_relu(32, 7, 7)(inputs) 
    conv1 = _conv_bn_relu(32, 3, 3)(conv1) 
    pool1 = _conv_bn_relu(32, 2, 2, subsample=(2, 2))(conv1) 
    drop1 = Dropout(0.5)(pool1) 

    conv2 = _conv_bn_relu(64, 3, 3)(drop1) 
    conv2 = _conv_bn_relu(64, 3, 3)(conv2) 
    pool2 = _conv_bn_relu(64, 2, 2, subsample=(2, 2))(conv2) 
    drop2 = Dropout(0.5)(pool2) 

    conv3 = _conv_bn_relu(128, 3, 3)(drop2) 
    conv3 = _conv_bn_relu(128, 3, 3)(conv3) 
    pool3 = _conv_bn_relu(128, 2, 2, subsample=(2, 2))(conv3) 
    drop3 = Dropout(0.5)(pool3) 

    conv4 = _conv_bn_relu(256, 3, 3)(drop3) 
    conv4 = _conv_bn_relu(256, 3, 3)(conv4) 
    pool4 = _conv_bn_relu(256, 2, 2, subsample=(2, 2))(conv4) 
    drop4 = Dropout(0.5)(pool4) 

    conv5 = _conv_bn_relu(512, 3, 3)(drop4) 
    conv5 = _conv_bn_relu(512, 3, 3)(conv5) 
    drop5 = Dropout(0.5)(conv5) 
    print(drop5.shape) 

    # Using conv to mimic fully connected layer. 
    aux = Convolution2D(nb_filter=1, nb_row=drop5._keras_shape[2], nb_col=drop5._keras_shape[3], 
         subsample=(1, 1), init="he_normal", activation='sigmoid')(drop5) 
    aux = Flatten(name='aux_output')(aux) 

    # up6 = concatenate([Conv2DTranspose(256, (2, 2), strides=(2, 2), padding='same')(drop5), conv4], axis=3) 
    up6 = merge([UpSampling2D()(drop5), conv4], mode='concat', concat_axis=1) 
    conv6 = _conv_bn_relu(256, 3, 3)(up6) 
    conv6 = _conv_bn_relu(256, 3, 3)(conv6) 
    drop6 = Dropout(0.5)(conv6) 

    # up7 = concatenate([Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(drop6), conv3], axis=3) 
    up7 = merge([UpSampling2D()(drop6), conv3], mode='concat', concat_axis=1) 
    conv7 = _conv_bn_relu(128, 3, 3)(up7) 
    conv7 = _conv_bn_relu(128, 3, 3)(conv7) 
    drop7 = Dropout(0.5)(conv7) 

    # up8 = concatenate([Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(drop7), conv2], axis=3) 
    up8 = merge([UpSampling2D()(drop7), conv2], mode='concat', concat_axis=1) 
    conv8 = _conv_bn_relu(64, 3, 3)(up8) 
    conv8 = _conv_bn_relu(64, 3, 3)(conv8) 
    drop8 = Dropout(0.5)(conv8) 

    # up9 = concatenate([Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same')(drop8), conv1], axis=3) 
    up9 = merge([UpSampling2D()(drop8), conv1], mode='concat', concat_axis=1) 
    conv9 = _conv_bn_relu(32, 3, 3)(up9) 
    conv9 = _conv_bn_relu(32, 3, 3)(conv9) 
    drop9 = Dropout(0.5)(conv9) 

    conv10 = Convolution2D(1, 1, 1, activation='sigmoid', init="he_normal", name='main_output')(drop9) 

    # model = Model(inputs=[inputs], outputs=[conv10]) 
    model = Model(inputs=[inputs], outputs=[conv10, aux]) 

    # model.compile(optimizer=Adam(lr=1e-5), loss={'main_output': dice_loss}, 
    #    metrics={'main_output': dice}, 
    #    loss_weights={'main_output': 1}) 
    model.compile(optimizer=Adam(lr=1e-5), loss={'main_output': dice_loss, 'aux_output': 'binary_crossentropy'}, 
        metrics={'main_output': dice, 'aux_output': 'acc'}, 
        loss_weights={'main_output': 1, 'aux_output': 0.5}) 

    return model

来源

2017-10-16 Tom

我想你应该改变这一行：

aux = Convolution2D(nb_filter=1, nb_row=drop5._keras_shape[2], nb_col=drop5._keras_shape[3], 
        subsample=(1, 1), init="he_normal", activation='sigmoid')(drop5)

到：

aux = Convolution2D(nb_filter=1, nb_row=drop5._keras_shape[1], nb_col=drop5._keras_shape[2], 
        subsample=(1, 1), init="he_normal", activation='sigmoid')(drop5)

来源

2017-10-16 17:21:47

我不使用Keras，但我相信在你的代码的问题在于你投入

aux = Convolution2D(nb_filter=1, nb_row=drop5._keras_shape[2], nb_col=drop5._keras_shape[3], subsample=(1, 1), init="he_normal", activation='sigmoid')(drop5)

这是非常难演绎的张量的尺寸滤波器的尺寸范围内，但有后通过Keras documentation of Convolution2D阅读，以及分析了张量的尺寸，我假设drop5输出一个形状张量(samples, new_rows, new_cols, nb_filter)（[?,10,10,512] in your error message)。换句话说，您的drop5输出的图像尺寸为10 x 10 x 512，或等效为512 10 x 10图像（this is a great read if you want to learn more about CNNs）。

当您现在设置nb_row=drop5._keras_shape[2]和nb_col=drop5._keras_shape[3]时，您将过滤器的尺寸设置为nb_row=10和nb_col=512。这意味着您将尝试使用10 x 512形状滤镜对512 10 x 10图像执行卷积。为了查看滤镜是否适合图像，我会假设TensorFlow减去图像和滤镜尺寸。 [10, 10] - [10, 512] = [0, -502]显示过滤器比图像大得多，因此无法执行卷积，因此您的错误消息。

解决此问题的方法是更改您的nb_row和nb_col尺寸。如果您想要的滤镜尺寸大于10 x 10，则可以从drop5调整输出图像的大小。

来源

2017-10-17 03:33:55

如何解决conv2d错误？

回答

相关问题