ViTAE-Transformer / DeepSolo

The official repo for [CVPR'23] "DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting" & [ArXiv'23] "DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting"
Other
250 stars 34 forks source link

Implement on CPU #63

Open rwood-97 opened 7 months ago

rwood-97 commented 7 months ago

This PR implements DeepSolo on CPU by calling the pytorch implementation of multiscale deformable attention if cuda is not found. I have also organised the cpu/cuda files into cpu/cuda folders respectively just for clarity.

rwood-97 commented 7 months ago

Fixes #22 as well