Keras中的ResNet50v2

Question

我想在Keras中加载经过预先训练的ResNet50v2模型。我试过了

keras.applications.resnet_v2.ResNet50V2()

这引起了一个错误

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

在搜索该错误时，this answer建议使用keras_applications包。所以我试着

keras_applications.resnet_v2.ResNet50V2()

这就给出了错误

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'

在搜索该错误时，this answer建议使用keras.applications包。我很困惑。如何加载ResNetv2模型？

注意:我能够加载ResNet50。只有ResNet50v2才有问题

from keras.applications.resnet50 import ResNet50

Answer 1

​

import keras

keras.applications.resnet_v2.ResNet50V2()

以上代码在jupyter笔记本中执行。

在安装Keras之前，请安装它的一个后端引擎TensorFlow

​

• pip安装tensorflow
• pip安装keras

​

​