Keras mobilenet实施

我想使用具有depth_multiplier（或分辨率乘数）的不同值的mobilenet . 这两行代码给出了以下错误 . 知道这里出了什么问题吗？

from keras.applications.mobilenet import MobileNet
basic_model = MobileNet(alpha=0.25, depth_multiplier=0.25, weights=None)

错误：

回溯（最近一次调用最后一次）：文件“C：/Users/Pedro/Desktop/Work/Smile/files/CVPR_2016_SMILES_DATA/test.py”，第2行，在basic_model = MobileNet（alpha = 0.25，depth_multiplier = 0.25，权重） =无）文件“C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ keras \ applications \ mobilenet.py”，第456行，在MobileNet中x = depthwise_conv_block（x，64，alpha，depth_multiplier，block_id = 1）文件“C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ keras \ applications \ mobilenet.py”，第654行，在_depthwise_conv_block name ='conv_dw％d'％block_id）（输入）文件“C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ keras \ engine \ topology.py“，第576行，调用self.build（input_shapes [0]）文件”C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ keras \ applications \ mobilenet.py“，第228行，在build constraint = self.depthwise_constraint中）文件”C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ keras \ _ legacy \ interfaces.py“，第87行，在包装器返回func（* args，** kwargs）文件“C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ keras \ engine \ topology.py”中，行397，在add_weight weight = K.variable（initializer（shape），File“C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ keras \ initializers.py”，第212行，调用dtype = dtype，seed = self.seed）文件“C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ keras \ backend \ tensorflow_backend.py”，第3627行，in random_uniform dtype = dtype，seed = seed）文件“C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ tensorflow \ python \ ops \ random_ops.py“，第240行，in random_uniform形状，dtype，seed = seed1，seed2 = seed2）文件”C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ tensorflow \ python \ ops \ gen_random_ops.py“，第247行，_random_uniform seed = seed，seed2 = seed2，name = name）文件”C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ tensorflow \ python \ framework \ op_def_library.py“，第589行，在apply_op param_name = input_name中）文件”C：\ Users \ Pedro \ Anaconda3 \ lib \ site-packages \ tensorflow \ python \ framework \ op_def_library.py“，第60行，在_SatisfiesTypeConstraint“，” . join（dtypes.as_dtype（x）.name for x in allowed_list）））TypeError：传递给参数的值'shape'的DataType float32不在允许值列表中：int32，int64

来自mobilent paper："The second hyper-parameter to reduce the computational cost of a neural network is a resolution multiplier ρ. We apply this to the input image and the internal representation of every layer is subsequently reduced by the same multiplier. In practice, we implicitly set ρ by setting the input resolution. We can now express the computational cost for the core layers of our network as depthwise separable convolutions with width multiplier α and resolution multiplier ρ: DK · DK · αM · ρDF · ρDF + αM · αN · ρDF · ρDF (7) where ρ ∈ (0, 1] which is typically set implicitly so that the input resolution of the network is 224, 192, 160 or 128. ρ = 1 is the baseline MobileNet and ρ < 1 are reduced computation MobileNets. Resolution multiplier has the effect of reducing computational cost by ρ^2."

并且Keras声称depth_multiplier与here和here中的分辨率乘数相同："depth_multiplier: depth multiplier for depthwise convolution (also called the resolution multiplier)"