quoccuongle/MultimodalOCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update Readme.md

Browse Source
This commit is contained in:
lz
2023-06-01 23:03:57 +08:00
committed by GitHub
parent 336c984ea4
commit 0a77786372
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Readme.md
View File

@@ -2,7 +2,7 @@
# Results
Results are available in answer_save folder.
Results are available in answer_save folder. It should be noted that for BLIP2OPT, when using the inference code on Hugging Face, the accuracy of text recognition is high, but the model outputs nothing for the VQA tasks. Conversely, when using the LAVIS library for inference, the accuracy of text recognition is low, while the VQA accuracy is normal. We believe that the inference process of BLIP2OPT still needs to be optimized. In our experiments, we take the maximum value of the two methods as the final result.
![image](https://github.com/echo840/MultimodalOCR/assets/87795401/523e0421-7eca-4d15-89f1-3f7348321055)