isds-neu / PhyCRNet

Physics-informed convolutional-recurrent neural networks for solving spatiotemporal PDEs
MIT License
118 stars 35 forks source link

Extremely big loss? #12

Open 131131yhx opened 1 year ago

131131yhx commented 1 year ago

I'm doing the experiment on coupled Burger's, following instructions described in README.md that firstly turn the argument "steps" to a relatively small number. However, it turns out to have extremely large loss: [1/20000 0%] loss: 18560561113464832.0000000000 [2/20000 0%] loss: 18553907806470144.0000000000 [3/20000 0%] loss: 18551367970848768.0000000000 [4/20000 0%] loss: 18550044584050688.0000000000 [5/20000 0%] loss: 18548749886291968.0000000000 [6/20000 0%] loss: 18547451732426752.0000000000 Does this happen normally?

YHzhang2021 commented 11 months ago

Hi. I have the same problem, how did you solve it?