Spliting model into Encoder and Decoder

MendelXu / SAN

Open-vocabulary Semantic Segmentation

https://mendelxu.github.io/SAN/

MIT License

295 stars 27 forks source link

Spliting model into Encoder and Decoder #12

Closed shenglunch closed 1 year ago

shenglunch commented 1 year ago

Hello! I really like this project. Do you plan to support splitting this model into Encoder and Decoder, and allow to input one image into the model? Thank you very much!

MendelXu commented 1 year ago

Sorry, but I couldn't get your point. Could you provide a more detailed description? Why is it neccessary to split the model into encoder and decoder?