Malo Marrec malomarrec
jorgemf
/ Dockerfile_TFserving_1_6
Last active
July 19, 2018 14:07
Dockerfile to compile TensorFlow Serving 1.6 using GPU
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # docker build --pull -t tf/tensorflow-serving --label 1.6 -f Dockerfile . | |
| # export TF_SERVING_PORT=9000 | |
| # export TF_SERVING_MODEL_PATH=/tf_models/mymodel | |
| # export CONTAINER_NAME=tf_serving_1_6 | |
| # CUDA_VISIBLE_DEVICES=0 docker run --runtime=nvidia -it -p $TF_SERVING_PORT:$TF_SERVING_PORT -v $TF_SERVING_MODEL_PATH:/root/tf_model --name $CONTAINER_NAME tf/tensorflow-serving /usr/local/bin/tensorflow_model_server --port=$TF_SERVING_PORT --enable_batching=true --model_base_path=/root/tf_model/ | |
| # docker start -ai $CONTAINER_NAME | |
| FROM nvidia/cuda:9.0-cudnn7-devel-ubuntu16.04 | |