facebookresearch/ParlAI

Standardize batchifying image features

Open

#2.461 aberto em 11 de mar. de 2020

Ver no GitHub
 (4 comments) (1 reaction) (0 assignees)Python (2.089 forks)batch import
H2 2020Help WantedSmalldonotreap

Métricas do repositório

Stars
 (10.371 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

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.

Guia do colaborador