Ubuntu 系统下安装支持 GPU 的 tensorflow 和 keras

最新推荐文章于 2021-07-12 15:45:50 发布

原创最新推荐文章于 2021-07-12 15:45:50 发布 · 361 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#tensorflow #cuda #gpu #深度学习 #ubuntu

生物信息同时被 2 个专栏收录

13 篇文章

订阅专栏

深度学习

2 篇文章

订阅专栏

本文详细介绍如何在Ubuntu 18.04上为TensorFlow 2.0配置GPU环境，包括安装NVIDIA驱动、CUDA 10.1、cuDNN 7.6.4及TensorRT等关键组件。通过bash命令行操作，确保GPU被正确识别并优化深度学习性能。

安装 tensorflow 前，需要先安装 NVIDIA 驱动，cuda 和 libcudnn 库。注意 tensorflow 对 cuda 版本要求比较严格，目前是需要 cuda10.1，如果安装了其他版本，tensorflow 会报找不到 cuda 动态链接库的错误。

亲测根据以下 bash 命令行安装所需要的驱动和 cuda 库，能够正常工作。安装命令行来自 https://tensorflow.google.cn/install/gpu

# Add NVIDIA package repositories
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-repo-ubuntu1804_10.1.243-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu1804_10.1.243-1_amd64.deb
sudo apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/7fa2af80.pub
sudo apt-get update
wget http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/nvidia-machine-learning-repo-ubuntu1804_1.0.0-1_amd64.deb
sudo apt install ./nvidia-machine-learning-repo-ubuntu1804_1.0.0-1_amd64.deb
sudo apt-get update

# Install NVIDIA driver
sudo apt-get install --no-install-recommends nvidia-driver-418
# Reboot. Check that GPUs are visible using the command: nvidia-smi

# Install development and runtime libraries (~4GB)
sudo apt-get install --no-install-recommends \
    cuda-10-1 \
    libcudnn7=7.6.4.38-1+cuda10.1  \
    libcudnn7-dev=7.6.4.38-1+cuda10.1
    
# Install TensorRT. Requires that libcudnn7 is installed above.
sudo apt-get install -y --no-install-recommends libnvinfer6=6.0.1-1+cuda10.1 \
    libnvinfer-dev=6.0.1-1+cuda10.1 \
    libnvinfer-plugin6=6.0.1-1+cuda10.1

以上步骤执行完后，运行 nvidia-smi，应该可以看到类似下面的输出

$ nvidia-smi
Sun May  3 22:33:26 2020
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 440.64.00    Driver Version: 440.64.00    CUDA Version: 10.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce RTX 208...  On   | 00000000:3B:00.0 Off |                  N/A |
| 22%   30C    P8    20W / 250W |      0MiB / 11019MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+
|   1  GeForce RTX 208...  On   | 00000000:AF:00.0 Off |                  N/A |
| 22%   27C    P8    22W / 250W |      0MiB / 11019MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

接下来安装 tensorflow 和 keras 就很容易了，直接 pip 安装即可。tensorflow 2.0 以后默认支持 GPU，无需像 1.0 版本那样区分 GPU 版和 CPU 版。命令如下

pip3 install tensorflow
pip3 install keras