microsoft/MMdnn

Cannot convert TF InceptionResNet to IR

Open

#86 opened on Feb 27, 2018

View on GitHub
 (6 comments) (0 reactions) (1 assignee)Python (5,767 stars) (982 forks)batch import
help wanted

Description

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:

Contributor guide

Tech stack
pythontensorflow
Domain
machine learningtooling
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
needs investigation
Prerequisites
TensorFlowCaffePythonDeep learning frameworks
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25
Research direction
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