【问题标题】:GCP Custom Prediction Routine unable to include jsonschema depency specified in setup.pyGCP 自定义预测例程无法包含 setup.py 中指定的 json 架构依赖项
【发布时间】:2021-03-02 10:42:39
【问题描述】:

根据 GCP AI Platform 的文档 here,自定义预测例程部署应允许包含 PyPI 依赖项。我在 setup.py 脚本中包含了我对 jsonschema 的依赖,如下所示:

from setuptools import setup
from setuptools import find_packages


REQUIRED_PACKAGES = ['jsonschema']

setup(
    name='custom_code',
    version='1.0.2',
    scripts=['predictor.py', 'preprocess.py'],
    install_requires=REQUIRED_PACKAGES,
    packages=find_packages(),
    include_package_data=True
)

但在部署时收到此错误消息:

ERROR: (gcloud.beta.ai-platform.versions.create) Create Version failed. Bad model detected with error:  "Failed to load model: Unexpected error when loading the model: 'str' object has no attribute 'decode' (Error code: 0)"

在指定像 REQUIRED_PACKAGES = ['jsonschema==3.2.0'] 这样的版本时,同样的错误仍然存​​在。然后我使用了较低的版本:

from setuptools import setup
from setuptools import find_packages


REQUIRED_PACKAGES = ['jsonschema==3.0.0']

setup(
    name='custom_code',
    version='1.0.2',
    scripts=['predictor.py', 'preprocess.py'],
    install_requires=REQUIRED_PACKAGES,
    packages=find_packages(),
    include_package_data=True
)

但现在出现此错误:

ERROR: (gcloud.beta.ai-platform.versions.create) Create Version failed. Bad model detected with error:  "Failed to load model: Unexpected error when loading the model: problem in predictor - DistributionNotFound: The 'jsonschema' distribution was not found and is required by the application (Error code: 0)"

这里有什么问题?

【问题讨论】:

    标签: python google-cloud-platform gcloud google-ai-platform


    【解决方案1】:

    原来最初的错误Bad model detected with error: "Failed to load model: Unexpected error when loading the model: 'str' object has no attribute 'decode' (Error code: 0)" 实际上是由模型格式问题引起的。这似乎是 TensorFlow Keras 的 a known issue(虽然我的 TF 版本是 1.15,但引用的 TF 版本是 2.1.0)。一旦我使用了TensorFlow SavedModel format,错误立即消失了,我还能够在setup.py 文件中包含jsonchema 依赖项。

    【讨论】:

      猜你喜欢
      • 2016-03-02
      • 1970-01-01
      • 1970-01-01
      • 1970-01-01
      • 2018-12-23
      • 2020-02-29
      • 2012-05-21
      • 1970-01-01
      • 2014-03-24
      相关资源
      最近更新 更多