【发布时间】:2019-05-08 10:59:32
【问题描述】:
我正在尝试使用配置文件运行 tensorflow/serving docker 映像。它会引发有关 servable 的文件系统访问的错误。我尝试使用单个模型和多个模型都不起作用。
docker执行命令如下
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
"
我的配置文件如下
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"
}
}
但不使用配置文件,我可以使用 docker 命令单独运行模型。
sudo docker run -t --rm -p 8501:8501 -v "/home/projects/models/model1:/models/model1" -e MODEL_NAME=model1 tensorflow/serving &
【问题讨论】:
标签: tensorflow tensorflow-serving