stanwinata

Results 5 comments of stanwinata

Hey guys, I was wondering if the pytorch team are open for public contributions to these models? 🤔 I assume we can follow similar PR formats to the one [here](https://github.com/pytorch/vision/pull/3252/files)...

> @stwinata Thanks for offering. Which models do you have in mind to contribute? @datumbox thanks for the quick reply! I am interested in [DETR](https://github.com/facebookresearch/detr) or **EfficientDet**. I was thinking...

> (mainly due to the training bit) @datumbox Does this come down to lack of GPU resources? Or is it due to the need to validate that it can properly...

@datumbox These comments makes sense 😃 > 1. To reproduce the paper it's an iterative process of code + recipe + training. Getting a PR that just adds the implementation...

@Jostarndt, perhaps not, since you need 4 self.linears: 1. linear_Q (to project query) 2. linear_K (to project key) 3. linear_V (to project value) 4. linear_O (to project output) It's true...