Azure / Azure/MachineLearningNotebooks
Model with ' ' in `model_path` fails ACI deployment
- 主要語言
- Jupyter Notebook
- 星號
- 4.4k
- 分支
- 2.6k
- PR 合併指標
- 30 天內沒有已合併 PR
描述
To reproduce:
1. rename `tutorials/image-classification-mnist-data/sklearn_mnist_model.pkl` to `sklearn mnist model.pkl`
2. edit `tutorials/image-classification-mnist-data/img-classification-part2-deploy.ipynb` to reflect Step 1 (in model-registration, cell 1, and in `score.py`, cell 3)
3. run `img-classification-part2-deploy.ipynb`- the "Deploy in ACI" step fails:
```
Service deployment polling reached non-successful terminal state, current service state: Transitioning
Operation ID: b8141a0c-55e4-4cd4-b30d-da7d1debd3e1
More information can be found using '.get_logs()'
Error:
{
"code": "DeploymentTimedOut",
"statusCode": 504,
"message": "The deployment operation polling has TimedOut. The service creation is taking longer than our normal time. We are still trying to achieve the desired state for the web service. Please check the webservice state for the current webservice health. You can run print(service.state) from the python SDK to retrieve the current state of the webservice.
Please refer to https://aka.ms/debugimage#dockerlog for more information."
}
```
The ACI deployment also failed when `model_path` specifies a folder with spaces in its name. This did _not_ appear to affect `LocalWebservice` or AKS deployments.
貢獻指南
這個儲存庫沒有索引到貢獻指南
研究方向
按照 tutorials/image-classification-mnist-data/img-classification-part2-deploy.ipynb 重現此故障,包括模型註冊儲存格 1 和 score.py 儲存格 3 中重新命名後的模型路徑。比較 ACI 部署行為與回報的 LocalWebservice 和 AKS 行為。當模型檔案或資料夾路徑包含空格時 ACI 部署能夠成功,即表示完成。
由索引模型根據 Issue 內容生成。
評估
- 技術堆疊
- azure, jupyter-notebook, python
- 領域
- cloud, machine-learning
- Issue 類型
- 缺陷
- 難度
- 4/5
- 預估耗時
- 3-5 天
- 活躍度
- 停滯
- 描述清晰度
- 描述清楚
- 新手友好度
- 35/100