SavedModelBundle Unable to Load Models with coo_sparse Encoded Input
还没有人认领这个 Issue。
- 主要语言
- Java
- 星标
- 928
- 派生
- 227
- PR 合并指标
- 30 天内没有已合并 PR
描述
Was trying to load a model using SavedModelBundle.load(savedModelPath, "serve") but ran into the operand "" does not exist on the graph issue. Error log:
Looking into Tensorflow Java source code this error is raised here.
And by inspecting the model being loaded the corresponding input tensor is coo_sparse encoded:
It appears to me that when building TensorDescription the library doesn't take coo_sparse encoded format into account: code link: it's trying to fetch the name field which is always empty for coo_sparse encoded format, because together with the name field it's oneof in TensorInfo proto: code link.
Is this a known unsupported feature or would the model loading just work if the validation is bypassed?
贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
调研方向
从 TensorFlow Java 的 TensorFunction.java 和 Signature.java 开始,然后将它们对 TensorInfo 的处理与 meta_graph.proto 中的 coo_sparse oneof 进行比较。复现所述 SavedModelBundle 的加载,并确定是否需要更改 validation 或模型加载;当已确定受支持的行为,并通过适当的 regression check 覆盖,或将其记录为不受支持时,即视为完成。
由索引模型根据 Issue 内容生成。
评估
- 技术栈
- java
- 领域
- machine-learning
- Issue 类型
- 缺陷
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 活跃度
- 停滞
- 描述清晰度
- 基本清楚
- 新手友好度
- 35/100