我試圖讓一段代碼在google coolab上運行，這是一段舊的代碼，所以可能在匯入和版本上有一些問題：
# IMPORT
import tensorflow as tf
from keras.models import Model
from keras.layer.core import Dense, Dropout, Activation
from keras.layer.convolutional import Conv2D, Conv2DTranspose
from keras.layer.pooling import AveragePooling2D
from keras.layer.pooling import globalAveragePooling2D
from keras.layer import Input, Concatenate
#from keras.layer.normalization import BatchNormalization。
from tensorflow.keras.layer import BatchNormalization
from keras.regularizers import l2
import keras.backend as K
from keras_layer_normalization import LayerNormalization
import numpy as np
import matplotlib.pyplot as plt
from keras.models import *
from keras.layer import *
from keras.optimizers import *
from keras.callbacks import ModelCheckpoint, LearningRateScheduler, ModelCheckpoint
from keras import backend as keras
#from keras.utils import plot_model[/span]。
from keras.utils.vis_utils import plot_model
from keras.callbacks import EarlyStopping, TensorBoard
from keras.callbacks import ModelCheckpoint
import zipfile
from google.colab import drive
from keras.callbacks import CSVLogger
drive.mount('/content/gdrive')
model = model_standard
opt = keras.optimizers.Adam(learning_rate=0.01, amsgrad=True)
model.compile(opt, loss = custom_loss, metrics=['mean_absolute_error', SSIM] )
這就是我運行時出現的問題：
AttributeError Traceback (most recent call last)
<ipython-input-91-4cf6655c0fc5> in <module> ()
32 model = model_standard
33
---gt; 34 opt = keras.optimizers.Adam(learning_rate=0.01, amsgrad=True)
35 model.compile(opt, loss = custom_loss, metrics=['mean_absolute_error', SSIM] )
AttributeError: 模塊'keras.backend'沒有屬性'優化器'。
我正在使用這些版本的tensorflow和keras：
print(tf.__version__)
print(tf.keras.__version__)
2.6.0。
2.6.0。
uj5u.com熱心網友回復：
你遇到的問題是因為匯入了f keras import backend as keras。
簡單地將keras匯入為import keras并洗掉from keras import backend as keras
轉載請註明出處，本文鏈接：https://www.uj5u.com/houduan/310706.html
標籤：
上一篇：這是我的c 鏈接表的代碼。我在deleteAtEnd方法中遇到了問題，在洗掉最后一個節點后，它顯示了一些垃圾值。