ValueError：输入具有不兼容的形状

Question

我有以下代码：

def fcn8_decoder(convs, n_classes):
  # features from the encoder stage
  f3, f4, f5 = convs

  # number of filters
  n = 512

  # add convolutional layers on top of the CNN extractor.
  o = tf.keras.layers.Conv2D(n , (7 , 7) , activation='relu' , padding='same', name="conv6", data_format=IMAGE_ORDERING)(f5)
  o = tf.keras.layers.Dropout(0.5)(o)

  o = tf.keras.layers.Conv2D(n , (1 , 1) , activation='relu' , padding='same', name="conv7", data_format=IMAGE_ORDERING)(o)
  o = tf.keras.layers.Dropout(0.5)(o)

  o = tf.keras.layers.Conv2D(n_classes,  (1, 1), activation='relu' , padding='same', data_format=IMAGE_ORDERING)(o)

    
  ### START CODE HERE ###

  # Upsample `o` above and crop any extra pixels introduced
  o = tf.keras.layers.Conv2DTranspose(n_classes , kernel_size=(4,4) ,  strides=(2,2) , use_bias=False)(o)
  o = tf.keras.layers.Cropping2D(cropping=(1,1))(o)

  # load the pool 4 prediction and do a 1x1 convolution to reshape it to the same shape of `o` above
  o2 = f4
  o2 = ( tf.keras.layers.Conv2D(n_classes , ( 1 , 1 ) , activation='relu' , padding='same', data_format=IMAGE_ORDERING))(o2)

  # add the results of the upsampling and pool 4 prediction
  o = tf.keras.layers.Add()([o, o2])

  # upsample the resulting tensor of the operation you just did
  o = (tf.keras.layers.Conv2DTranspose( n_classes , kernel_size=(4,4) ,  strides=(2,2) , use_bias=False))(o)
  o = tf.keras.layers.Cropping2D(cropping=(1, 1))(o)

  # load the pool 3 prediction and do a 1x1 convolution to reshape it to the same shape of `o` above
  o2 = f3
  o2 = tf.keras.layers.Conv2D(n_classes , ( 1 , 1 ) , activation='relu' , padding='same', data_format=IMAGE_ORDERING)(o2)

  # add the results of the upsampling and pool 3 prediction
  o = tf.keras.layers.Add()([o, o2])

  # upsample up to the size of the original image
  o = tf.keras.layers.Conv2DTranspose(n_classes , kernel_size=(8,8) ,  strides=(8,8) , use_bias=False )(o)
  o = tf.keras.layers.Cropping2D(((0, 0), (0, 96-84)))(o)

  # append a sigmoid activation
  o = (tf.keras.layers.Activation('sigmoid'))(o)
  ### END CODE HERE ###

  return o

# TEST CODE

test_convs, test_img_input = FCN8()
test_fcn8_decoder = fcn8_decoder(test_convs, 11)

print(test_fcn8_decoder.shape)

del test_convs, test_img_input, test_fcn8_decoder

可以查看完整代码here。

我收到以下错误：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-14-cff468b82c6a> in <module>
      2 
      3 test_convs, test_img_input = FCN8()
----> 4 test_fcn8_decoder = fcn8_decoder(test_convs, 11)
      5 
      6 print(test_fcn8_decoder.shape)

2 frames
/usr/local/lib/python3.8/dist-packages/keras/layers/merging/base_merge.py in _compute_elemwise_op_output_shape(self, shape1, shape2)
     71       else:
     72         if i != j:
---> 73           raise ValueError(
     74               'Inputs have incompatible shapes. '
     75               f'Received shapes {shape1} and {shape2}')

ValueError: Inputs have incompatible shapes. Received shapes (4, 4, 11) and (4, 5, 11)

我在这里做错了什么？

Answer 1

您的模型实现看起来是正确的。问题在于输入形状。输入形状必须能被 32 整除，例如 (224, 224, 3) 或 (64, 64, 3)。

在出错的代码中，您使用的是形状(64, 84, 3)，但 84 不能被 32 整除。

解释：

FCN8 的下采样路径使用 5 个卷积块对输入进行下采样。因为模型使用 5 个这样的块，所以输入必须能被 2**5 = 32 整除。 （相关https://stackoverflow.com/a/74847194/5666087.）

工作示例：

test_convs, test_img_input = FCN8(input_height=64, input_width=64)
test_fcn8_decoder = fcn8_decoder(convs=test_convs, n_classes=11)

test_convs, test_img_input = FCN8(input_height=224, input_width=224)
test_fcn8_decoder = fcn8_decoder(convs=test_convs, n_classes=11)

test_convs, test_img_input = FCN8(input_height=128, input_width=128)
test_fcn8_decoder = fcn8_decoder(convs=test_convs, n_classes=11)

Answer 2

可能导致问题的原因是您的输入不是正方形格式（相同的高度和宽度），并且在总和层中，您试图对经过一些卷积后具有不同形状的张量求和，然后成为更多的张量之一长方形。

我设法找到了一些随意的导致具有兼容形状的张量的内核大小。还删除了填充。

这是我改变的：

这个：

o2 = f4
o2 = ( tf.keras.layers.Conv2D(n_classes , ( 1 , 1 ) , activation='relu' , padding= 'same', data_format=IMAGE_ORDERING))(o2)

转向这个：

o2 = f4
o2 = ( tf.keras.layers.Conv2D(n_classes , ( 1 , 2 ) ,activation='relu', data_format=IMAGE_ORDERING))(o2)

和这个：

o2 = f3
o2 = tf.keras.layers.Conv2D(n_classes , ( 1 , 1 ) , activation='relu' , padding ='same', data_format=IMAGE_ORDERING)(o2)

转向这个：

o2 = f3
o2 = tf.keras.layers.Conv2D(n_classes , ( 1 , 3 ) , activation='relu' , data_format=IMAGE_ORDERING)(o2)

这是完整的代码：

def fcn8_decoder(convs, n_classes):
    #features from the encoder stage
    f3, f4, f5 = convs

    # number of filters
    n = 512

    # add convolutional layers on top of the CNN extractor.
    o = tf.keras.layers.Conv2D(n , (7 , 7) , activation='relu' , padding='same', name="conv6", data_format=IMAGE_ORDERING)(f5)
    o = tf.keras.layers.Dropout(0.5)(o)

    o = tf.keras.layers.Conv2D(n , (1 , 1) , activation='relu' , padding='same', name="conv7", data_format=IMAGE_ORDERING)(o)
    o = tf.keras.layers.Dropout(0.5)(o)

    o = tf.keras.layers.Conv2D(n_classes,  (1, 1), activation='relu' , padding='same', data_format=IMAGE_ORDERING)(o)


    ### START CODE HERE ###

    # Upsample `o` above and crop any extra pixels introduced
    o = tf.keras.layers.Conv2DTranspose(n_classes , kernel_size=(4,4) ,  strides=(2,2) , use_bias=False)(o)
    o = tf.keras.layers.Cropping2D(cropping=(1,1))(o)

    # load the pool 4 prediction and do a 1x1 convolution to reshape it to the same shape of `o` above
    o2 = f4
    o2 = ( tf.keras.layers.Conv2D(n_classes , ( 1 , 2 ) , activation='relu' , data_format=IMAGE_ORDERING))(o2)



    # add the results of the upsampling and pool 4 prediction
    o = tf.keras.layers.Add()([o, o2])

    # upsample the resulting tensor of the operation you just did
    o = (tf.keras.layers.Conv2DTranspose( n_classes , kernel_size=(4,4) ,  strides=(2,2) , use_bias=False))(o)
    o = tf.keras.layers.Cropping2D(cropping=(1, 1))(o)

    # load the pool 3 prediction and do a 1x1 convolution to reshape it to the same shape of `o` above
    o2 = f3
    o2 = tf.keras.layers.Conv2D(n_classes , ( 1 , 3 ) , activation='relu' , data_format=IMAGE_ORDERING)(o2)

    print("###################################################")
    print(o2.shape,o.shape)

    # add the results of the upsampling and pool 3 prediction
    o = tf.keras.layers.Add()([o, o2])

    # upsample up to the size of the original image
    o = tf.keras.layers.Conv2DTranspose(n_classes , kernel_size=(8,8) ,  strides=(8,8) , use_bias=False )(o)
    o = tf.keras.layers.Cropping2D(((0, 0), (0, 96-84)))(o)

    # append a sigmoid activation
    o = (tf.keras.layers.Activation('sigmoid'))(o)
    ### END CODE HERE ###

    return o