Use as fixed CRF - Githubissues

MiguelMonteiro / CRFasRNNLayer

Conditional Random Fields as Recurrent Neural Networks (Tensorflow)

MIT License

82 stars 20 forks source link

Use as fixed CRF #21

Closed jgsimard closed 5 years ago

jgsimard commented 5 years ago

Hi, I would like to know what would I need to change to this repo to have a CRF with fixed weight? I don't think it should be too hard. I want to know if I could use this to replace pydensecrf that is a wrapper around the original code in the paper

Efficient Inference in Fully Connected CRFs with Gaussian

Thanks for all the good work!

MiguelMonteiro commented 5 years ago

Yes, it's possible. The easiest way would be to change the tensorflow variables to constants.

Best,

Miguel