Training ERRor
caijinana opened this issue · comments
Hello Dear @ThibaultGROUEIX professor:
when i am training the code i got the error as the picture,but i can training 1 epoch in the morning ,but when i traing again in the afternoon i got the error, i used training successfully in the january, how should i do ?Thank you
Hi @caijinana ,
Nice hearing from you again. I have not changed the code since January but you probably switched machines?
I would say you don't have enough RAM to train. You could consider two things:
- use another machine with more RAM
- split the training data into chunks and load the chunk sequentially
Best regards,
Thibault
@ThibaultGROUEIX Thank you very much,now my project is working but i have not change the coda ,So strange ,now i want to ask you another question ,i want to training my own data ,it have 6480 points ,can I set the random_sampling false, but when i set false,i got the error, how can i do ? and set the random_sampling false only affect the visualization or effect the result?
The bug above is only related to visualisation and does not affect the results.
Visdom is a package similar to tensorboard in case you don't know it. It used to be my favourite but now I mostly use tensorboard.
Bets regards
Thank you ,Love you
Best wishes!
Happy every day!
Love your spirit ! Cheers