CODEWITHSUNDEEP
dockertensorflow
user12131586
user12131586

Reputation: 43

using tensorflow inside docker with gpu

I'm trying to use tensorflow in docker, following the instructions at

https://www.tensorflow.org/install/docker

I have docker 19.03 installed on a centos 7.7.1908 machine, and I can run nvidia-smi

docker run --gpus all nvidia/cuda:10.1-base nvidia-smi

my understanding is that the use of nvidia-docker is deprecated. then I download tensorflow

docker pull tensorflow/tensorflow:latest-devel-py3

or

docker pull tensorflow/tensorflow:devel-gpu

but when I run one of them

docker run -it --rm tensorflow/tensorflow:latest-devel-py3 python -c "import tensorflow as tf;"

I get

Traceback (most recent call last): File "", line 1, in ModuleNotFoundError: No module named 'tensorflow' failed to resize tty, using default size

what am I missing?

well, I've since found out that

latest-gpu-py3

allows me to import tensorflow, whereas

latest-devel-py3

doesn't. I'd've thought that all these images would work...

Upvotes: 4

Views: 1055

Answers (1)

Marek Bartosiewicz
Marek Bartosiewicz

Reputation: 26

"devel" image contains tensorflow sources, see: https://hub.docker.com/r/tensorflow/tensorflow/

Quote:

devel images come with Bazel and are ideal for developing changes to TensorFlow at master. /tensorflow_src includes the TensorFlow source tree at the latest nightly commit where the Pip package built successfully in the container. We no longer provide images for developing on top of older versions of TF (1.12.0 was the last release where this was the case).

Upvotes: 1

Related Questions