carpedm20 / carpedm20/DCGAN-tensorflow
global average pooling
Open
- Dominant language
- JavaScript
- Stars
- 7.2k
- Forks
- 2.6k
- PR merge metrics
- No merged PRs in 30d
Description
The `global average pooling` is used in the discriminator, torch code and illustrated in the DCGAN paper. But here is `fully connection` in the discriminator.
Contributor guide
No contributing guide indexed for this repository
Research direction
Compare the discriminator implementation with the global average pooling used in the referenced torch code and DCGAN paper. Determine whether the current fully connected layer is incorrect, then verify that the discriminator architecture matches the intended design and that existing checks still pass.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- pytorch, tensorflow
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100