Keras Maxpooling2d层给出ValueError

Question

我正在尝试在keras中复制VGG16模型，以下是我的代码：

model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2))) ###This line gives error
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))

maxpooling2d层在注释的行处给出了一个错误

错误显示：

ValueError: Negative dimension size caused by subtracting 2 from 1 for 'MaxPool_7' (op: 'MaxPool') with input shapes: [?,1,112,128].

/usr/local/lib/python2.7/dist-packages/keras/engine/topology.pyc in create_node（cls,outbound_layer,inbound_layers,node_indexes,tensor_index)147 148 if len(input_tensors）==1:-->149 output_tensors=to_list(outbound_layer.call(input_tensors[0],mask=input_masks[0]))150output_masks=

/usr/local/lib/python2.7/dist-packages/keras/layers/pooling.pyc in call（self,x,mask)160strides=self.strides，161border_mode=self.border_mode，-->162 dim_ordering=self.dim_ordering)163返回输出164

/usr/local/lib/python2.7/dist-packages/keras/layers/pooling.pyc in_pooling_function（self,inputs,pool_size,strides,border_mode,dim_ordering)210 border_mode,dim_ordering):211 output=k.pool2d（inputs,pool_size,strides,-->212 border_mode,dim_ordering)213返回输出214

/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.pyc在pool2d(x,pool_size,strides,border_mode,dim_ordering,pool_mode)1699 1700如果pool_mode=='max':->1701 x=tf.nn.max_pool(x,pool_size,strides,padding=padding)1702 elif pool_mode=='avg':1703
x=tf.nn.avg_pool(x

/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/nn_ops.pyc in max_pool（value,ksize,strides,padding,data_format,name）1391 padding=padding,1392
data_format=data_format,->1393 name=name）1394 1395

/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_nn_ops.pyc in_max_pool（input,ksize,strides,padding,data_format,name)
1593 result=_op_def_lib.apply_op（“maxpool”,input=input,ksize=ksize,1594 strides=strides,padding=padding,->1595 data_format=data_format,name=name)1596

/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.pyc in apply_op（self,op_type_name,name,**关键字）747 op=g.create_op(op_type_name,inputs,output_types,name=scope,748 input_types=input_types,attrs=attr_protos,-->749 op_def=op_def)750 outputs=op.outputs 751 return_restructure

/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.pyc in create_op(self,op_type,input,dtypes,input_types,name,attrs,op_def,compute_shapes,compute_device)2388
original_op=self._default_original_op,op_def=op_def)2389 if compute_shapes：->2390 set_shapes_for_outputs(ret)2391

/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.pyc in set_shapes_for_outputs(op)1783 raise RuntimeError（“没有为标准操作%s注册的形状函数”1784
%op.type)->1785 shapes=shape_func(op)1786如果shapes为none：1787 raise RuntimeError（

/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/common_shape.pyc in call_cpp_shape_fn（op，input_tensors_need，debug_python_shape_fn)594 status）595 except errors.invalidargumenterror as err:-->596提高值错误（err.message）597 598#转换output_shapes中的TensorShapeProto值。

ValueError：输入形状为[？,1,112,128]的“MaxPool_7”（操作：“MaxPool')从1减去2导致的负尺寸大小。

Answer 1

引用github中提到的一个答案，您需要指定维度排序：

Keras是Theano或Tensorflow库的包装器。Keras使用设置变量image_dim_ordering来决定输入层是Theano还是Tensorflow格式。此设置可通过2种方式指定-

1. 在~/.keras/keras.json中指定'tf'或'th'，类似于so-image_dim_orderming:'th'。注意：这是一个json文件。
2. 或在模型中指定image_dim_ordering，如下所示:model.add(MaxPooling2D(pool_size=(2,2）,dim_ordering=“th”））

更新：2020年4月Keras 2.2.5链接似乎有一个更新的API，其中dim_ordering更改为data_format，因此：

keras.layers.maxpooling2d(pool_size=(2,2）,strides=none,padding='valid',data_format='channels_first')获取NCHW或使用channels_last获取NHWC

附录:image_dim_ordering在'th'模式中，通道尺寸（深度）位于索引1（例如3、256、256)。在'tf'模式中，它是否位于索引3（例如256、256、3)。从评论中引用@Naoko。