tensorflow / tensorflow/java

SavedModelBundle Unable to Load Models with coo_sparse Encoded Input

未关闭
#501 1 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

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:
empty_operand_error_log_censored

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:
coo_sparse_encoded_censored

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

打开贡献指南

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 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

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。