pytorch/vision

mnasnet training schedule

Open

#1,163 opened on Jul 25, 2019

View on GitHub
 (7 comments) (0 reactions) (0 assignees)Python (6,858 forks)batch import
awaiting responsehelp wantedmodule: modelstopic: classification

Repository metrics

Stars
 (15,050 stars)
PR merge metrics
 (Avg merge 12d 8h) (14 merged PRs in 30d)

Description

What is the training schedule for MNASNet 1.0 that gives 73.5 top-1? I tried the mobilenet schedule but it not giving the same accuracy as mentioned in torchvision page.

On a side note, mnasnet paper reports 74% top1 but torchvision model is 73.5% top-1.

Contributor guide

Research direction
Review the MNASNet paper and torchvision source code to find the training schedule used for the 73.5% top 1 accuracy. Check if the schedule is documented or can be inferred from training scripts. Compare with MobileNet schedule to identify differences.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorchDeep Learning
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75