facebookresearch/ParlAI

Standardize batchifying image features

Ouverte

#2 461 ouverte le 11 mars 2020

 (4 commentaires) (1 réaction) (0 personne assignée)Python (2 089 forks)batch import
H2 2020Help WantedSmalldonotreap

Métriques du dépôt

Stars
 (10 371 étoiles)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

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.

Guide contributeur