Keras中的ResNet50v2

我想在Keras中加载预先训练过的ResNet50v2模型。我试过了

keras.applications.resnet_v2.ResNet50V2()

这是一个错误

Traceback (most recent call last):
  File "<input>", line 1, in <module>
AttributeError: module 'keras.applications' has no attribute 'resnet_v2'

这就产生了错误

Traceback (most recent call last):
  File "<input>", line 1, in <module>
  File "/home/nagabhushan/.local/lib/python3.6/site-packages/keras_applications/resnet_common.py", line 495, in ResNet50V2
    **kwargs)
  File "/home/nagabhushan/.local/lib/python3.6/site-packages/keras_applications/resnet_common.py", line 348, in ResNet
    data_format=backend.image_data_format(),
AttributeError: 'NoneType' object has no attribute 'image_data_format'

导入keras
keras.applications.resnet_v2.ResNet50V2（）

工作正常！我使用的是

tensorflow gpu

和

keras gpu

。仅使用

tensorflow

和

keras

进行了尝试。成功了。

Traceback (most recent call last):
  File "<input>", line 1, in <module>
  File "/home/nagabhushan/.local/lib/python3.6/site-packages/keras_applications/resnet_common.py", line 495, in ResNet50V2
    **kwargs)
  File "/home/nagabhushan/.local/lib/python3.6/site-packages/keras_applications/resnet_common.py", line 348, in ResNet
    data_format=backend.image_data_format(),
AttributeError: 'NoneType' object has no attribute 'image_data_format'

from keras.applications.resnet50 import ResNet50