New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Questions about the training from scratch #23
Comments
@gonglixue - when you visualised your training results, did you ever get a blocky output for your visualization? We're running into similar problems, and I'm wondering if this is a problem for you too |
same problem... :( |
I have trained it from scratch successfully : ) |
Thanks! i will try |
I didn't come across the blocky output problem. Using the code in |
can you please provide me more details? my Thanks :) |
My full training process is as follow:
# detach_network=True in __init__()
# if self.detach_network and can_detach:
if self.detach_network:
x_pre = x_pre.detach() In this step, I set
if self.detach_netwrok and can_detach:
x_pre = x_pre.detach() In this step, I find that the theta loss almost converges while the inlier loss decreases slowly. So decrease the weight of theta loss with
My training process seems a little complicated. For some video data, I have to adjust the hyper parameters back and forth... |
Thank you very much for the detailed answer, you are great! |
Thanks so much for the help! Out of curiosity how many epochs did each of the steps take? i.e. How much training did you do before you unfroze the feature extractor? |
Hi. I used the provided code to train TimeCycle on some other video datasets. Finetuning the network with the provided
checkpoint_14.pth.tar
works fine. But when I training the network from scratch, both the inlier loss and theta loss did not decrease. Is there any training tips when training TimeCycle from scratch?The text was updated successfully, but these errors were encountered: