TypeError: (‘Keyword argument not understood:‘, ‘dim_ordering‘)

TypeError: (‘Keyword argument not understood:’, ‘dim_ordering’)

问题描述

from tensorflow.python.keras.layers import Conv2D

Conv2D(24, 5, 5, padding='same',init='he_normal', input_shape = (target_Width,target_Height, 3),dim_ordering="tf")

报错：

TypeError: ('Keyword argument not understood:', 'dim_ordering')

原因

dim_ordering=“tf” 只用在 stand-alone Keras，而from tensorflow.python.keras.layers 没有

解决方法

from tensorflow.python.keras.layers import Conv2D
model.add(Conv2D(24, 5, 5, padding='same', kernel_initializer='he_normal', input_shape = (target_Width,target_Height, 3)))

或用stand-alone Keras

from keras.models import Sequential
model = Sequential()
model.add(keras.layers.convolutional.Convolution2D(24, 5, 5, padding='same',init='he_normal', input_shape = (target_Width,target_Height, 3),dim_ordering="tf"))

参考链接：

https://stackoverflow.com/questions/66517434/keras-throwing-error-keyword-argument-not-understood-init-and-keyword