kotlindl
kotlindl copied to clipboard
[WiP] Add ConvTranspose Layers
Closes #124.
Work status:
- [x] Implementation of layer class named as Conv2DTranspose (you can take inspiration from the implementation of Conv2D as reference)
- [x] Implementation of layer class named as Conv3DTranspose (you can take inspiration from the implementation of Conv3D as reference)
- [ ] Implementation of layer class named as Conv1DTranspose
- [ ] Common hierarchy of all ConvTranspose layers with abstract class with the common functionality (reused AbstractConv from standard conv operation)
- [ ] Documentation of layer and all non-private methods
- [ ] JUnit tests in api module
- [ ] Support for export of layer to JSON (see ModelSaver.kt)
- [ ] Support for import of layer from JSON (see ModelLoader.kt)
Hi @avan1235 if you have any questions regarding this PR feel free to ask, I'll try to help
Hi @zaleslaw. Sorry for no actions from my side - I just couldn't find time and motivation after work to work on this issue. I think you can unassign me but I will do my best to finally implement this on my repo and if there will be no other PR candidates I would mention you here to go back to the issue.
Hi @avan1235 you partially implemented this issue and there is no race here to finish it in the 0.3 release, for example, but as you wish I unassigned this issue, hope you will return to work on KotlinDL in the future!
Transpose convolutional layers were implemented in #315.