carpedm20 / carpedm20/DCGAN-tensorflow
Generate test images with different batch size fails
- Dominant language
- JavaScript
- Stars
- 7.2k
- Forks
- 2.6k
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
I am new to tensorflow itself.
I trained the CelebA dataset with a batch size of 64. But, when I was testing it with different batch size it fails like following,
[*] Failed to find a checkpoint
Exception: [!] Train a model first, then run test mode
For test mode also, I need to give a batch size of 64?
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing the reported failure in test mode after training CelebA with batch size 64, then retry with a different batch size. Trace the checkpoint lookup and the "Train a model first" path; done means the supported test-mode batch-size behavior is identified and the failure is corrected or clearly documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100