Closed lminjy closed 1 year ago
Hi,
This is probably due to bad initialization of GRU. The easiest solution is to re-start the training several times until GRU is randomly initialized to a relatively good starting point. Of course, you could also try some more advanced initialization methods to stablize the starting phase of training.
Best regards, Xiaoyong
Ok, after many tries, the training worked. I am new to neural networks and Kalman filtering, and I have some questions. Would you please explain.
3.How do I train with your particular network?I mean where do they run?
1 To check whether the network initialize to a good point.
2 Yes.
3 In the main files.
I checked all the calls and found no training for kg There are indeed steps to run here, but I didn't find out how they work
I run main_linear and main_linear_estH, but do not see calls to these functions
They are called inside the pipeline file. where you do forward step of the KNet model.
oh, thank you very much