这篇教程keras2环境安装详细记录写得很实用，希望能帮到您。
在tf2之后，不再分cpu和GPU版本，安装tf2之后也不必安装keras，keras已经封装在tf2.
ubuntu22.4 anaconda 3 下开始创建:
创建名为py374的虚拟环境：conda create -n py374 python=3.7
切到py374：conda activate py374
查看可用的cudatoolkit: conda search cudatoolkit
(py374) zjy@zjy-System-Product-Name:~/tang/17flowers$ conda search cudatoolkit
Loading channels: done
# Name Version Build Channel
cudatoolkit 9.0 h13b8566_0 pkgs/main
cudatoolkit 9.2 0 pkgs/main
cudatoolkit 10.0.130 0 pkgs/main
cudatoolkit 10.1.168 0 pkgs/main
cudatoolkit 10.1.243 h6bb024c_0 pkgs/main
cudatoolkit 10.2.89 hfd86e86_0 pkgs/main
cudatoolkit 10.2.89 hfd86e86_1 pkgs/main
cudatoolkit 11.0.221 h6bb024c_0 pkgs/main
cudatoolkit 11.3.1 h2bc3f7f_2 pkgs/main
cudatoolkit 11.8.0 h6a678d5_0 pkgs/main
根据自己的tf版本需求选择对应的版本安装
这里选择安装tf2.1，对应的keras为2.3.1，cuda10.1,cudnn7.6
conda install cudatoolkit==10.1.243
(py374) zjy@zjy-System-Product-Name:~/tang/17flowers$ conda search cudnn
Loading channels: done
# Name Version Build Channel
cudnn 7.0.5 cuda8.0_0 pkgs/main
cudnn 7.1.2 cuda9.0_0 pkgs/main
cudnn 7.1.3 cuda8.0_0 pkgs/main
cudnn 7.2.1 cuda9.2_0 pkgs/main
cudnn 7.3.1 cuda10.0_0 pkgs/main
cudnn 7.3.1 cuda9.0_0 pkgs/main
cudnn 7.3.1 cuda9.2_0 pkgs/main
cudnn 7.6.0 cuda10.0_0 pkgs/main
cudnn 7.6.0 cuda10.1_0 pkgs/main
cudnn 7.6.0 cuda9.0_0 pkgs/main
cudnn 7.6.0 cuda9.2_0 pkgs/main
cudnn 7.6.4 cuda10.0_0 pkgs/main
cudnn 7.6.4 cuda10.1_0 pkgs/main
cudnn 7.6.4 cuda9.0_0 pkgs/main
cudnn 7.6.4 cuda9.2_0 pkgs/main
cudnn 7.6.5 cuda10.0_0 pkgs/main
cudnn 7.6.5 cuda10.1_0 pkgs/main
cudnn 7.6.5 cuda10.2_0 pkgs/main
cudnn 7.6.5 cuda9.0_0 pkgs/main
cudnn 7.6.5 cuda9.2_0 pkgs/main
cudnn 8.2.1 cuda11.3_0 pkgs/main
cudnn 8.9.2.26 cuda11_0 pkgs/main
conda install cudnn==7.6.5
pip install tensorflow==2.1.0
pip install keras==2.3.1 (不装也可以用)
运行后，出现如下错误：
TypeError: Descriptors cannot not be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:
1. Downgrade the protobuf package to 3.20.x or lower.
2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).
More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates
升级一下protobuf
(py374) zjy@zjy-System-Product-Name:~/tang/17flowers$ pip install protobuf==3.20.0
ModuleNotFoundError: No module named 'sklearn'
(py374) zjy@zjy-System-Product-Name:~/tang/17flowers$ pip install sklearn
Collecting sklearn
Downloading sklearn-0.0.post9.tar.gz (3.6 kB)
Preparing metadata (setup.py) ... error
error: subprocess-exited-with-error
× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [18 lines of output]
The 'sklearn' PyPI package is deprecated, use 'scikit-learn'
(py374) zjy@zjy-System-Product-Name:~/tang/17flowers$ pip install scikit-learn
ModuleNotFoundError: No module named 'imutils'
解决：pip install imutils
ModuleNotFoundError: No module named 'matplotlib'
pip install matplotlib
返回列表
Keras实现注意力机制(self-attention)中文的文本情感分类（详细注释） |
