Vatsal Saglani
Vatsal Saglani
The only thing I have figured out is that we can put a representational data loader which represents images(used MAML for Computer Vision project) from every class/category and then use...
From the MiniImageNet train file, while making the Dataloader, the **task_num** is taken, which is clear that it depicts **batch_size**. Generally, in meta-learning, we have batches, and inside batches, we...
@gbertb that can be exposed, will try to add it soon
`pip install -r requirements.txt` should be downloading this package. Isn't it doing that?
It's been a long time since I worked on this. But as far as I remember here, the transformer treats source and target sequence as one sequence instead of source...
This might occur if your `vocab_size` is less than the amount of unique input IDs present in your data. Suppose you have 20,000 movies or 20,000 items then your vocab...