ValueError:max_pooling2d_2层的输入0与该层不兼容:预期ndim = 4，找到的ndim = 5.收到的完整图形:[1，无，64、64、8] [英] ValueError: Input 0 of layer max_pooling2d_2 is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: [1, None, 64, 64, 8]

问题描述

我正在进行CNN在线课程分配，该课程建立了卷积模型.说明如下:

I am doing a CNN online course assignment which builds a convolutional model. The instructions are listed as following:

练习2-卷积模型

实施下面的convolutional_model函数以构建以下模型: CONV2D->RELU->MAXPOOL->CONV2D->RELU->MAXPOOL->FLATTEN->DENSE .使用上面的功能！

Implement the convolutional_model function below to build the following model: CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> DENSE. Use the functions above!

此外，为所有步骤插入以下参数:

Also, plug in the following parameters for all the steps:

• Conv2D:使用8个4×4过滤器，跨度1，填充为"SAME"
• ReLU
• MaxPool2D:使用8 x 8的滤镜大小和8 x 8的跨度，填充为"SAME"
• Conv2D:使用16个2 x 2过滤器，跨度1，填充为"SAME"
• ReLU
• MaxPool2D:使用4乘4的滤镜大小和4乘4的步幅，填充为"SAME"
• 平整先前的输出.
• 完全连接(密集)层:应用具有6个神经元和softmax激活的完全连接层.

代码在这里:

# GRADED FUNCTION: convolutional_model

def convolutional_model(input_shape):
    """
    Implements the forward propagation for the model:
    CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> DENSE
    
    Note that for simplicity and grading purposes, you'll hard-code some values
    such as the stride and kernel (filter) sizes. 
    Normally, functions should take these values as function parameters.
    
    Arguments:
    input_img -- input dataset, of shape (input_shape)

    Returns:
    model -- TF Keras model (object containing the information for the entire training process) 
    """

    input_img = tf.keras.Input(shape=input_shape)
    
    ## CONV2D: 8 filters 4x4, stride of 1, padding 'SAME'
    Z1 = tf.keras.layers.Conv2D(8,(4,4), strides=(1,1),padding='same')(input_img),

    
    ## RELU
    A1 = tf.keras.layers.ReLU()(Z1),

    ## MAXPOOL: window 8x8, stride 8, padding 'SAME'
    print("A1 size: ", str(A1)),
    P1 = tf.keras.layers.MaxPool2D(pool_size=(8,8), strides=(8,8), padding='same')(A1),
    #P1 = tf.nn.max_pool(A1, ksize = [1,8,8,1], strides = [1,8,8,1], padding = 'SAME')
    ## CONV2D: 16 filters 2x2, stride 1, padding 'SAME'
    Z2 = tf.keras.layers.Conv2D(16,(2,2), strides=(1,1),padding='same' )(P1),
    ## RELU
    A2 = tf.keras.layers.ReLU()(Z2),
    ## MAXPOOL: window 4x4, stride 4, padding 'SAME'
    P2 = tf.keras.layers.MaxPool2D((4,4), strides=(4,4), padding='same')(A2),
    ## FLATTEN
    F = tf.keras.layers.Flatten()(P2),
    ## Dense layer
    ## 6 neurons in output layer. Hint: one of the arguments should be "activation='softmax'" 
    outputs = tf.keras.layers.Dense(6, activation='softmax', name='fc')(F),
    # YOUR CODE STARTS HERE
    
    
    # YOUR CODE ENDS HERE
    model = tf.keras.Model(inputs=input_img, outputs=outputs)
    return model

但是，当我运行以下代码进行测试

However, when I run following code for testing

conv_model = convolutional_model((64, 64, 3))
conv_model.compile(optimizer='adam',
                  loss='categorical_crossentropy',
                  metrics=['accuracy'])
conv_model.summary()
    
output = [['InputLayer', [(None, 64, 64, 3)], 0],
        ['Conv2D', (None, 64, 64, 8), 392, 'same', 'linear', 'GlorotUniform'],
        ['ReLU', (None, 64, 64, 8), 0],
        ['MaxPooling2D', (None, 8, 8, 8), 0, (8, 8), (8, 8), 'same'],
        ['Conv2D', (None, 8, 8, 16), 528, 'same', 'linear', 'GlorotUniform'],
        ['ReLU', (None, 8, 8, 16), 0],
        ['MaxPooling2D', (None, 2, 2, 16), 0, (4, 4), (4, 4), 'same'],
        ['Flatten', (None, 64), 0],
        ['Dense', (None, 6), 390, 'softmax']]
    
comparator(summary(conv_model), output)

我收到错误消息:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-24-f1284300b767> in <module>
----> 1 conv_model = convolutional_model((64, 64, 3))
      2 conv_model.compile(optimizer='adam',
      3                   loss='categorical_crossentropy',
      4                   metrics=['accuracy'])
      5 conv_model.summary()

<ipython-input-23-610251af1ba8> in convolutional_model(input_shape)
     28     ## MAXPOOL: window 8x8, stride 8, padding 'SAME'
     29     print("A1 size: ", str(A1)),
---> 30     P1 = tf.keras.layers.MaxPool2D(pool_size=(8,8), strides=(8,8), padding='same')(A1),
     31     #P1 = tf.nn.max_pool(A1, ksize = [1,8,8,1], strides = [1,8,8,1], padding = 'SAME')
     32     ## CONV2D: 16 filters 2x2, stride 1, padding 'SAME'

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
    924     if _in_functional_construction_mode(self, inputs, args, kwargs, input_list):
    925       return self._functional_construction_call(inputs, args, kwargs,
--> 926                                                 input_list)
    927 
    928     # Maintains info about the `Layer.call` stack.

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in _functional_construction_call(self, inputs, args, kwargs, input_list)
   1090       # TODO(reedwm): We should assert input compatibility after the inputs
   1091       # are casted, not before.
-> 1092       input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
   1093       graph = backend.get_graph()
   1094       # Use `self._name_scope()` to avoid auto-incrementing the name.

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    178                          'expected ndim=' + str(spec.ndim) + ', found ndim=' +
    179                          str(ndim) + '. Full shape received: ' +
--> 180                          str(x.shape.as_list()))
    181     if spec.max_ndim is not None:
    182       ndim = x.shape.ndims

ValueError: Input 0 of layer max_pooling2d_2 is incompatible with the layer: expected ndim=4, found ndim=5. Full shape received: [1, None, 64, 64, 8]

看起来像我的 MaxPool2D(pool_size =(8,8)，stride =(8,8)，padding ='same')一样有问题.如指令所述，"MaxPool2D:使用8×8的过滤器尺寸和8×8的跨度，填充为"SAME"，我对我的MaxPool2D无法正常工作感到困惑吗?我该如何纠正?非常感谢.

Looks like the my MaxPool2D(pool_size=(8,8), strides=(8,8), padding='same') has problems. As the instruction says, "MaxPool2D: Use an 8 by 8 filter size and an 8 by 8 stride, padding is "SAME"", I am confused on what my MaxPool2D is not working as it should? How should I correct it? Thanks a lot.

推荐答案

您(偶然)在每个层的末尾使用逗号(，)，这在构建模型时不正确.删除逗号，它应该可以工作.

You (accidentally) use commas (,) at the end of each layer which is not right when you build the model. Remove the commas and it should work.

conv_model = convolutional_model((64, 64, 3))
conv_model.compile(optimizer='adam',
                  loss='categorical_crossentropy',
                  metrics=['accuracy'])
conv_model.summary()

conv_model = convolutional_model((64, 64, 3))
conv_model.compile(optimizer='adam',
                  loss='categorical_crossentropy',
                  metrics=['accuracy'])
conv_model.summary()
A1 size:  KerasTensor(type_spec=TensorSpec(shape=(None, 64, 64, 8), dtype=tf.float32, name=None), name='re_lu_9/Relu:0', description="created by layer 're_lu_9'")
Model: "model_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_9 (InputLayer)         [(None, 64, 64, 3)]       0         
_________________________________________________________________
conv2d_9 (Conv2D)            (None, 64, 64, 8)         392       
_________________________________________________________________
re_lu_9 (ReLU)               (None, 64, 64, 8)         0         
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 8, 8, 8)           0         
_________________________________________________________________
conv2d_10 (Conv2D)           (None, 8, 8, 16)          528       
_________________________________________________________________
re_lu_10 (ReLU)              (None, 8, 8, 16)          0         
_________________________________________________________________
max_pooling2d_7 (MaxPooling2 (None, 2, 2, 16)          0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 64)                0         
_________________________________________________________________
fc (Dense)                   (None, 6)                 390       
=================================================================
Total params: 1,310
Trainable params: 1,310
Non-trainable params: 0
_________________________________________________________________

这篇关于ValueError:max_pooling2d_2层的输入0与该层不兼容:预期ndim = 4，找到的ndim = 5.收到的完整图形:[1，无，64、64、8]的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！