carpedm20 / carpedm20/DCGAN-tensorflow
MNISTdata set
- Dominant language
- JavaScript
- Stars
- 7.2k
- Forks
- 2.6k
- PR merge metrics
- No merged PRs in 30d
Description
Hi, blogger, I am working on the MNIST handwritten data set. The test has generated 100 composite large images by default. How can I compare the test generated data with the real data? How can I get the real data? I tried some methods to read the MNIST data online, and the results were all 28*28, a graph with only one number. But I, like you, generate an 8-row, 8-column, 64-digit image per image. Thank you!
Contributor guide
No contributing guide indexed for this repository
Research direction
Begin by identifying where the project creates the 100 composite images and where the MNIST data is loaded. Compare the real 28x28 samples with the generated 8-row, 8-column composite layout, and document a reproducible way to obtain and compare the data.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100