search

qc17-THU / DL-SR

Tensorflow/keras implementation for image transformation from low-resolution (LR) image to super-resolved one, including single wide-field (WF) image super-resolution prediction and SIM reconstruction.
MIT License
98 stars 28 forks source link

about models #18

Open liuxinxjtu opened 1 year ago

liuxinxjtu commented 1 year ago

Hi,

Why train a corresponding sample model for each sample? Also just use the samples of the corresponding model when testing the model?

Thank you in advance.

qc17-THU commented 1 year ago

Hi, Because the customized model trained for each specimen generally outperforms a general model trained with data of all types of specimens. We performed and showed the cross-specimen testing and transfer learning experiments in Extended Data Fig. 10 and Supplementary Fig. 12 in our Nat. Meth. manuscripts.