open-mmlab/mmskeleton

Training on a different dataset

Open

#81 opened on Aug 13, 2018

View on GitHub
 (22 comments) (0 reactions) (0 assignees)Python (1,063 forks)github user discovery
help wanted

Repository metrics

Stars
 (3,117 stars)
PR merge metrics
 (PR metrics pending)

Description

Dataset used

Cooking Activity

Modified the data accordingly. The accuracies are not that great. I have tried changing the parameters multiple times, using pre trained models as well. Still no improvements. Also I get the same sequence of labels as output every time. label_sequence = output.sum(dim=2).argmax(dim=0)

Any idea where it might be going wrong?

Contributor guide

Research direction
Investigate the label sequence decoding logic in the training pipeline. Check if the model is collapsing to a single label due to issues in loss function, softmax, or greedy decoding.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Bug
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.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorchMachine Learning basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30