-
Notifications
You must be signed in to change notification settings - Fork 250
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
VideoDataset has a bug about data normalization #23
Comments
Why do you think this is a bug? Normalizing data to [0, 1] is not always the case. Subtracting the mean RGB values of the used dataset(usually ImageNet) for backbone's pre-training is also common. Function normalize() follows this approach. If you want to prove that normalizing data to [0, 1] leads to higher performance, you have to elaborate more on this. The results that you provided are not comparable to each other. You could validate this by training you model while applying each time one of the two normalization approaches and report the results for the same number of epochs. |
@wave-transmitter The common solution is that Normalization should be done after the data have been scaled to [0,1], we usually call the function I have tested with |
It's not that I don't believe you, I am just trying to understand if you are making a fair comparison between the two normalization methods. You should give more details about your set-up, you haven't even mentioned which model you are trying to train... In my opinion, if you want to evaluate both methods, you should compare the results after a number of epochs where both models have converged. E.g. you can apply an early-stopping after 99.9% accuracy reached in training set, or just train for a higher number of epochs. I have also trained the C3D model(without any changes) in official split1 of UCF101 and posted the results in #14. The 5% accuracy at 15 epochs that you reported does not comply with those results in #14. |
@wave-transmitter I trained |
could you share the paper link. |
How should the code be modified?Training loss is always NAN |
There is a bug about
normalize(self, buffer)
function indataset.py
, it has not normalize data to [0, 1], which we usually do this in Deep Learning training process with PyTorch.And I also tested it, if we don't normalize it, the training process was totally failed when I used the official
train/test
split ofUCF101
, after 54 epochs, the testing accuracy was only around 5%.And if we normalize it, the training process was fine, after 5 epochs, it obtained 8.2% testing accuracy.
pytorch-video-recognition/dataloaders/dataset.py
Line 204 in ca37de9
The text was updated successfully, but these errors were encountered: