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
ImageNet performance? #7
Comments
Hi, I am also planning to test out AutoAugment in PyTorch, ImageNet. According to your numbers, the improvements seems very insignificant. Did you use the hyper-parameter settings mentioned in the original paper? For example, epochs? |
You are right, that might be the issue. I only run for 90 epochs as the official implementation. Maybe longer training epochs can help get the results in the paper. |
Dear @hszhao , I am currently doing CIFAR-10/100 (WRN28-10) experiments with the AutoAugment provided in this repository, and there are extra modifications upon baseline WRN + AutoAugment. There are extra Shake-Shake / ShakeDrop / CutOut, and cosine learning rate schedule(possibly lower initial learning rates). I think the cosine lr schedule is for better training set fit, since my initial experiment without cosine schedule fails to overfit to the training set. I am concurrently doing ImageNet ResNet-50 experiments. Since it takes ~2days for each experiment w/ 4GPUs for 90epochs, I can get back in a week maybe. |
It takes so long to train with AutoAugment :( Here's my settings & result:
In fact, I skipped last several epochs due to my tight schedule (and sth wrong with my server), but it's only a few epochs, so probably this is very close to or exactly the best we can get. Two different aspects from the original paper: (1) I did not use inception-style pre-processing and (2) batch size is 512, not 4096 as the paper. You can see the AutoAugment experiment training log here / Without AutoAugment here
|
One thing to notice here is the loss or error rate of the two experiments. I should have done the experiments with Inception-style augmentation for fair comparison :( |
@Jongchan Hi, Jongchan, thanks for the results. They are very close to the ones in the paper. It seems that more epochs are needed for various augmentation. In mixup paper, they also trained for longer epochs (200 epochs). |
Do you know how to use the policy given in the article to train our own models? What is the training process like? I train a model according to my own understanding, but the test accuracy of the model was very low. I use 10000 images from cifar10, According to the policy given in the article, do the autoaugment, and get the autoaugment 10000 images. Last , use the 10000 images to train the model. |
Do you know how to use the policy given in the article to train our own models? What is the training process like? I train a model according to my own understanding, but the test accuracy of the model was very low. I use 10000 images from cifar10, According to the policy given in the article, do the autoaugment, and get the autoaugment 10000 images. Last , use the 10000 images to train the model. |
Hi, does anyone gets the performance on ImageNet with the provided autoaugment?
Here is my results with autoaugment using official implementation, compared to official results, no impressive improvements are got?
Results of ResNet50,101,152 in terms of top1/5 accuracy:
official without autoaugment: 76.15/92.87, 77.37/93.56, 78.31/94.06.
mine with autoaugment: 75.33/92.45, 77.57/93.78, 78.51/94.07.
Update: all the above results are tested with training epochs as 90, a longer one such as 270 used in the paper may help get the reported results.
The text was updated successfully, but these errors were encountered: