facebookresearch/ParlAI

Standardize batchifying image features

Open

#2,461 建立於 2020年3月11日

在 GitHub 查看
 (4 留言) (1 反應) (0 負責人)Python (10,371 star) (2,089 fork)batch import
H2 2020Help WantedSmalldonotreap

描述

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.

貢獻者指南

技術棧
python
領域
machine learningbackend
議題類型
refactor
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
half day
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
clear
前置要求
ParlAI agentsPyTorch DataParallelImage feature batchification
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
65
研究方向
Examine the implementation of batchify image features in both ImageSeq2seqAgent and ImagePolyencoderAgent within the ParlAI codebase. Determine if the differences are necessary due to architectural constraints or if the Polyencoder version can be generalized. If possible, move the Polyencoder's method to TorchImageAgent and remove the duplicate in Seq2seq. Refer to the discussion in issue #2461 for context.