facebookresearch/ParlAI

Standardize batchifying image features

Open

#2461 aperta il 11 mar 2020

Vedi su GitHub
 (4 commenti) (1 reazione) (0 assegnatari)Python (2089 fork)batch import
H2 2020Help WantedSmalldonotreap

Metriche repository

Star
 (10.371 star)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

Currently, ImageSeq2seqAgent and ImagePolyencoderAgent have two separate .batchify_image_features() methods for preparing image features for encoding. The main advantage of ImagePolyencoderAgent's implementation of this method is that the images are packed into a Tensor for data_parallel. It's worth testing whether ImageSeq2seqAgent really requires a separate .batchify_image_features() method now: if not, it should be removed, and ImagePolyencoderAgent.batchify_image_features() should be moved into TorchImageAgent.

Guida contributor