tensorflow / tensorflow/models
global step nasnet
Open
@marksandler2 is already working on this.
Since May 20, 2020.
models:research
type:support
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
Sorry in advance if the issue is formulated incorrectly or not clear.
My customized dataset:
training: 1413(images) * 4(classes) = 5652(total)
validation: 354(images) * 4(classes) = 1416(total)
I am training my customized dataset
I don't get why the global step in the terminal is already at 10580 and still training. Haven't it had to stop at 7068?
Thank you!
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.