carpedm20 / carpedm20/DCGAN-tensorflow

The Model is unstable

Open
#179 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
JavaScript
Stars
7.2k
Forks
2.6k
PR merge metrics
No merged PRs in 30d

Description

After training my own dataset, the model began to become unstable. The effect after visualization as shown:The output of d and d_ begins collapse after the 8 epochs.
Excuse me, what is the cause of this?

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the report with the author's own dataset and the training setup used for DCGAN-tensorflow. Inspect the visualization of d and d_ around epoch 8 and compare it with a known-good training run. Done requires identifying a reproducible cause of the instability and documenting a verified fix or configuration change.

Written by the indexing model from the issue text.

Assessment

Tech stack
tensorflow
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.