Transposed Convolution
Open
- Dominant language
- Jupyter Notebook
- Stars
- 30k
- Forks
- 13.1k
- PR merge metrics
- No merged PRs in 30d
Description
The figure of transposed convolution in edition 2 shows adding empty rows and columns and performing regular convolution. Is this the right approach, other resources compute transpose convolution differently. Could you please clarify?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.