AlibabaResearch / AlibabaResearch/AdvancedLiterateMachinery

VGT模型配置中,VOCAB_SIZE也许应该为30522而不是30552

Open
#83 0 comments 1 reaction 0 assignees View on GitHub
Dominant language
C++
Stars
1.8k
Forks
195
PR merge metrics
No merged PRs in 30d

Description

下载Readme中D4LA对应模型,并执行inference.py

`
python inference.py \
--image_root 'xxx' \
--grid_root 'xxx' \
--image_name 'budget_0000022278' \
--dataset D4LA \
--output_root output/ \
--config Configs/cascade/D4LA_VGT_cascade_PTM.yaml \
--opts MODEL.WEIGHTS model/D4LA_VGT_model.pth \
MODEL.WORDGRID.USE_PRETRAIN_WEIGHT False
`

产生一条警告,且输出的图片中没有任何检测结果:

`
Skip loading parameter 'Wordgrid_embedding.embedding.weight' to the model due to incompatible shapes: (30522, 768) in the checkpoint but (30552, 768) in the model! You might want to double check if this is expected.
`

修改yaml文件中的VOCAB_SIZE为30522后,不再产生警告,并且输出图片有了检测结果框。

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.