CODEWITHSUNDEEP
tensorflowtensorflow-serving
Berkin Albert Antony W
Berkin Albert Antony W

Reputation: 23

Unable run Tensorflow Serving using config file

I am trying to run the tensorflow/serving docker image with the config file. It throws error regarding file-system access for servable. I tried with single model and multiple model both are not working.

The docker execution command is as follows

sudo docker run -p 8501:8501 --mount type=bind,source=/home/projects/models/model1/,target=/models/model1 --mount type=bind,source=/home/projects/models/model2/,target=/models/model2 --mount type=bind,source=/home/projects/config.conf,target=/models/config.conf -t tensorflow/serving --model_config_file=/models/config.conf


 "E tensorflow_serving/sources/storage_path/file_system_storage_path_source.cc:369] FileSystemStoragePathSource encountered a file-system access error: Could not find base path /home/projects/models/model1/ for servable model1
"

My config file is as below

model_config_list {
 config {
    name: 'model1',
    base_path: '/home/projects/models/model1/',
    model_platform: 'tensorflow'
  }
  config {
    name: 'model2',
    base_path: '/home/projects/models/model2/',
    model_platform: "tensorflow"
  }

}

But without using config file I can run the models individually using docker command.

sudo docker run -t --rm -p 8501:8501    -v "/home/projects/models/model1:/models/model1"     -e MODEL_NAME=model1     tensorflow/serving &

Upvotes: 1

Views: 708

Answers (1)

Snehal
Snehal

Reputation: 757

There's no need to mount each models separately! You can mount all the models like this:

sudo docker run \
-p 8501:8501 \
--mount type=bind,source=/home/projects/models/,target=/models/ \
-t tensorflow/serving \
--model_config_file=/models/config.conf

and your config.conf file now looks like this (put this file under /home/projects/models/):

model_config_list {
  config {
    name: 'model1',
    base_path: '/models/model1',
    model_platform: 'tensorflow'
  },
  config {
    name: 'model2',
    base_path: '/models/model2',
    model_platform: "tensorflow"
  },
}

Upvotes: 1

Related Questions