microsoft/MMdnn

Cannot convert TF InceptionResNet to IR

Open

#86 创建于 2018年2月27日

在 GitHub 查看
 (6 评论) (0 反应) (1 负责人)Python (5,767 star) (982 fork)batch import
help wanted

描述

Platform (like ubuntu 16.04/win10):ubuntu16.04

Python version:3.5

Source framework with version (like Tensorflow 1.4.1 with GPU):TF 1.5 with GPU

Destination framework with version (like CNTK 2.3 with GPU):Caffe

Pre-trained model path (webpath or webdisk path): https://yadi.sk/d/OnH0586P3SqoV3

Running scripts:

贡献者指南

技术栈
pythontensorflow
领域
machine learningtooling
议题类型
bug
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
3-5 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
needs investigation
前置要求
TensorFlowCaffePythonDeep learning frameworks
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
25
研究方向
Investigate the conversion of TensorFlow InceptionResNet model to IR in MMdnn. Start by examining the TensorFlow parser in the codebase, specifically the handling of InceptionResNet layers. Check if the model file from the provided link (Yandex disk) is accessible. Review the comments in the issue for any additional clues. The goal is to reproduce the error and identify where the conversion fails.
Cannot convert TF InceptionResNet to IR · microsoft/MMdnn#86 | Good First Issue