我正在尝试使用自定义预测例程将预训练的 pytorch model 部署到 AI Platform。按照 here 描述的说明操作后,部署失败并显示以下错误:

ERROR: (gcloud.beta.ai-platform.versions.create) Create Version failed. Bad model detected with error: Model requires more memory than allowed. Please try to decrease the model size and re-deploy. If you continue to have error, please contact Cloud ML.

模型文件夹的内容是 83.89 MB 大并且低于文档中描述的 250 MB 限制。该文件夹中的唯一文件是模型的检查点文件 (.pth) 和自定义预测例程所需的 tarball。

创建模型的命令:
gcloud beta ai-platform versions create pose_pytorch --model pose --runtime-version 1.15 --python-version 3.5 --origin gs://rcg-models/pytorch_pose_estimation --package-uris gs://rcg-models/pytorch_pose_estimation/my_custom_code-0.1.tar.gz --prediction-class predictor.MyPredictor

将运行时版本更改为 1.14 会导致相同的错误。
我已经尝试将 --machine-type 参数更改为 mls1-c4-m2 就像 Parth 建议的那样,但我仍然遇到相同的错误。

生成 setup.pymy_custom_code-0.1.tar.gz 文件如下所示:
setup(
    name='my_custom_code',
    version='0.1',
    scripts=['predictor.py'],
    install_requires=["opencv-python", "torch"]
)

来自预测器的相关代码片段:
    def __init__(self, model):
        """Stores artifacts for prediction. Only initialized via `from_path`.
        """
        self._model = model
        self._client = storage.Client()

    @classmethod
    def from_path(cls, model_dir):
        """Creates an instance of MyPredictor using the given path.

        This loads artifacts that have been copied from your model directory in
        Cloud Storage. MyPredictor uses them during prediction.

        Args:
            model_dir: The local directory that contains the trained Keras
                model and the pickled preprocessor instance. These are copied
                from the Cloud Storage model directory you provide when you
                deploy a version resource.

        Returns:
            An instance of `MyPredictor`.
        """

        net = PoseEstimationWithMobileNet()
        checkpoint_path = os.path.join(model_dir, "checkpoint_iter_370000.pth")
        checkpoint = torch.load(checkpoint_path, map_location='cpu')
        load_state(net, checkpoint)

        return cls(net)

此外,我在 AI Platform 中为模型启用了日志记录,并获得以下输出:
2019-12-17T09:28:06.208537Z OpenBLAS WARNING - could not determine the L2 cache size on this system, assuming 256k
2019-12-17T09:28:13.474653Z WARNING:tensorflow:From /usr/local/lib/python3.7/dist-packages/google/cloud/ml/prediction/frameworks/tf_prediction_lib.py:48: The name tf.saved_model.tag_constants.SERVING is deprecated. Please use tf.saved_model.SERVING instead.
2019-12-17T09:28:13.474680Z {"textPayload":"","insertId":"5df89fad00073e383ced472a","resource":{"type":"cloudml_model_version","labels":{"project_id":"rcg-shopper","region":"","version_id":"lightweight_pose_pytorch","model_id":"pose"}},"timestamp":"2019-12-17T09:28:13.474680Z","logName":"projects/rcg-shopper/logs/ml.googleapis…
2019-12-17T09:28:13.474807Z WARNING:tensorflow:From /usr/local/lib/python3.7/dist-packages/google/cloud/ml/prediction/frameworks/tf_prediction_lib.py:50: The name tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY is deprecated. Please use tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY instead.
2019-12-17T09:28:13.474829Z {"textPayload":"","insertId":"5df89fad00073ecd4836d6aa","resource":{"type":"cloudml_model_version","labels":{"project_id":"rcg-shopper","region":"","version_id":"lightweight_pose_pytorch","model_id":"pose"}},"timestamp":"2019-12-17T09:28:13.474829Z","logName":"projects/rcg-shopper/logs/ml.googleapis…
2019-12-17T09:28:13.474918Z WARNING:tensorflow:
2019-12-17T09:28:13.474927Z The TensorFlow contrib module will not be included in TensorFlow 2.0.
2019-12-17T09:28:13.474934Z For more information, please see:
2019-12-17T09:28:13.474941Z   * https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
2019-12-17T09:28:13.474951Z   * https://github.com/tensorflow/addons
2019-12-17T09:28:13.474958Z   * https://github.com/tensorflow/io (for I/O related ops)
2019-12-17T09:28:13.474964Z If you depend on functionality not listed there, please file an issue.
2019-12-17T09:28:13.474999Z {"textPayload":"","insertId":"5df89fad00073f778735d7c3","resource":{"type":"cloudml_model_version","labels":{"version_id":"lightweight_pose_pytorch","model_id":"pose","project_id":"rcg-shopper","region":""}},"timestamp":"2019-12-17T09:28:13.474999Z","logName":"projects/rcg-shopper/logs/ml.googleapis…
2019-12-17T09:28:15.283483Z ERROR:root:Failed to import GA GRPC module. This is OK if the runtime version is 1.x
2019-12-17T09:28:16.890923Z Copying gs://cml-489210249453-1560169483791188/models/pose/lightweight_pose_pytorch/15316451609316207868/user_code/my_custom_code-0.1.tar.gz...
2019-12-17T09:28:16.891150Z / [0 files][    0.0 B/  8.4 KiB]
2019-12-17T09:28:17.007684Z / [1 files][  8.4 KiB/  8.4 KiB]
2019-12-17T09:28:17.009154Z Operation completed over 1 objects/8.4 KiB.
2019-12-17T09:28:18.953923Z Processing /tmp/custom_code/my_custom_code-0.1.tar.gz
2019-12-17T09:28:19.808897Z Collecting opencv-python
2019-12-17T09:28:19.868579Z   Downloading https://files.pythonhosted.org/packages/d8/38/60de02a4c9013b14478a3f681a62e003c7489d207160a4d7df8705a682e7/opencv_python-4.1.2.30-cp37-cp37m-manylinux1_x86_64.whl (28.3MB)
2019-12-17T09:28:21.537989Z Collecting torch
2019-12-17T09:28:21.552871Z   Downloading https://files.pythonhosted.org/packages/f9/34/2107f342d4493b7107a600ee16005b2870b5a0a5a165bdf5c5e7168a16a6/torch-1.3.1-cp37-cp37m-manylinux1_x86_64.whl (734.6MB)
2019-12-17T09:28:52.401619Z Collecting numpy>=1.14.5
2019-12-17T09:28:52.412714Z   Downloading https://files.pythonhosted.org/packages/9b/af/4fc72f9d38e43b092e91e5b8cb9956d25b2e3ff8c75aed95df5569e4734e/numpy-1.17.4-cp37-cp37m-manylinux1_x86_64.whl (20.0MB)
2019-12-17T09:28:53.550662Z Building wheels for collected packages: my-custom-code
2019-12-17T09:28:53.550689Z   Building wheel for my-custom-code (setup.py): started
2019-12-17T09:28:54.212558Z   Building wheel for my-custom-code (setup.py): finished with status 'done'
2019-12-17T09:28:54.215365Z   Created wheel for my-custom-code: filename=my_custom_code-0.1-cp37-none-any.whl size=7791 sha256=fd9ecd472a6a24335fd24abe930a4e7d909e04bdc4cf770989143d92e7023f77
2019-12-17T09:28:54.215482Z   Stored in directory: /tmp/pip-ephem-wheel-cache-i7sb0bmb/wheels/0d/6e/ba/bbee16521304fc5b017fa014665b9cae28da7943275a3e4b89
2019-12-17T09:28:54.222017Z Successfully built my-custom-code
2019-12-17T09:28:54.650218Z Installing collected packages: numpy, opencv-python, torch, my-custom-code

最佳答案

这是一个常见问题,我们理解这是一个痛点。请执行以下操作:

  • torchvisiontorch 作为依赖项,默认情况下,它从 pypi 中提取 torch

  • 在部署模型时,即使您指定使用自定义的 ai-platform torchvision 包,它也会这样做,因为 torchvision 是由 PyTorch 团队构建的,它被配置为使用 torch 作为依赖项。 pypi 的 torch 依赖项提供了一个 720mb 的文件,因为它包含 GPU 单元
  • 要解决#1,您需要从源代码中提取 build torchvision 并告诉 torchvision 您想从哪里获取 torch,您需要将其设置为转到 torch 网站,因为包较小。使用 Python PEP-0440 direct references 功能重建 torchvision 二进制文件。在 torchvision setup.py 中,我们有:
  • pytorch_dep = 'torch'
    if os.getenv('PYTORCH_VERSION'):
        pytorch_dep += "==" + os.getenv('PYTORCH_VERSION')
    

    更新 setup.py 中的 torchvision 以使用直接引用功能:
    requirements = [
         #'numpy',
         #'six',
         #pytorch_dep,
         'torch @ https://download.pytorch.org/whl/cpu/torch-1.4.0%2Bcpu-cp37-cp37m-linux_x86_64.whl'
    ]
    

    * 我已经为你做了这个* ,所以我建立了 3 个你可以使用的轮文件:
    gs://dpe-sandbox/torchvision-0.4.0-cp37-cp37m-linux_x86_64.whl (torch 1.2.0, vision 0.4.0)
    gs://dpe-sandbox/torchvision-0.4.2-cp37-cp37m-linux_x86_64.whl (torch 1.2.0, vision 0.4.2)
    gs://dpe-sandbox/torchvision-0.5.0-cp37-cp37m-linux_x86_64.whl (torch 1.4.0  vision 0.5.0)
    

    这些 torchvision 包将从 Torch 站点而不是 pypi 获取 torch :(例如: https://download.pytorch.org/whl/cpu/torch-1.4.0%2Bcpu-cp37-cp37m-linux_x86_64.whl )
  • 在将模型部署到 AI Platform 时更新模型 setup.py ,使其不包含 torchtorchvision
  • 重新部署模型如下:
  • PYTORCH_VISION_PACKAGE=gs://dpe-sandbox/torchvision-0.5.0-cp37-cp37m-linux_x86_64.whl
    
    gcloud beta ai-platform versions create {MODEL_VERSION} --model={MODEL_NAME} \
                --origin=gs://{BUCKET}/{GCS_MODEL_DIR} \
                --python-version=3.7 \
                --runtime-version={RUNTIME_VERSION} \
                --machine-type=mls1-c4-m4 \
                --package-uris=gs://{BUCKET}/{GCS_PACKAGE_URI},{PYTORCH_VISION_PACKAGE}\
                --prediction-class={MODEL_CLASS}
    
    

    您可以将 PYTORCH_VISION_PACKAGE 更改为我在 #2 中提到的任何选项

    关于google-cloud-platform - 无法使用自定义预测例程 : Model requires more memory than allowed 将训练好的模型部署到 Google Cloud Ai-Platform,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/59372655/

    10-13 00:41