🚀 Feature request

Make CLIPFeatureExtractor (or any FeatureExtractor in general) accept batch of images as torch.Tensor.

Motivation

Currently batch of images as torch.Tensor are not treated as a batch, it has to be a List[torch.Tensor] but it is not the case when using native Pytorch DataLoader. Can we update this line so that it accepts batches as torch.Tensor. Maybe we ca

From paper, it mentioned

Instead, the training data generator chooses 15% of tokens at random, e.g., in the sentence my
dog is hairy it chooses hairy.

It means that 15% of token will be choose for sure.

From https://github.com/codertimo/BERT-pytorch/blob/master/bert_pytorch/dataset/dataset.py#L68,
for every single token, it has 15% of chance that go though the followup procedure.

_handle_duplicate_documents and _drop_duplicate_documents in the elastic search document store will always report self.index as the index with the conflict, which is obviously incorrect.

Edit: Upon further investigation, this is actually a lot worse. Using multiple indices with the ElasticSearch DocumentStore is completely broken due to the fact, that this is used in `_handle_duplicate_do

Issue to track tutorial requests:

• Deep Learning with PyTorch: A 60 Minute Blitz - #69
• Sentence Classification - #79