Virgile Boulanger

Output specifications support for Pytorch converter

12

## 🌱 Describe your Feature Request As the documentation explicitly point it out: "it is good practice to think about the interface to the model. This includes names and types...

Shouldn't be StylePredictor and Transfer Network trained jointly ?

2

Hi, Thanks for your work and sharing your code ! [Here in the Style Predictor code](https://github.com/philipjackson/style-augmentation/blob/master/styleaug/stylePredictor.py#L66) you say you detach the embedding vector because you don't want to train "end-to-end"....

Training on FFHQ - 1024px

4

Hi and thanks for sharing your implementation. After successfully trained the model on FFHQ at 256 and 512 resolutions, i want to scale at 1024, but got some size mismatch...

Setting : Neural Bandit When setting `keep_only_top_n` to `True`, the model keeps the original number of features, resulting in a Pytorch matmul error for the first linear layer: `RuntimeError: mat1...

- [ ] Add model architecture specificities for vocal melody extraction task - [ ] Add vocal melody extraction task dataset

- [ ] Add model architecture specificities for vocal melody extraction task - [ ] Add vocal melody extraction task dataset